![Application of AI in DL in advanced manufacturing process and robots [5] .](https://www.researchgate.net/profile/Mohsen-Soori/publication/369818981/figure/fig7/AS:11431281145562059@1681431393868/Application-of-AI-in-DL-in-advanced-manufacturing-process-and-robots-5_Q320.jpg)
![AI applications in collision avoidance and road hazard warning [88].](https://www.researchgate.net/profile/Mohsen-Soori/publication/369818981/figure/fig2/AS:11431281138361892@1680736482415/AI-applications-in-collision-avoidance-and-road-hazard-warning-88_Q320.jpg)
![Mobile edge computing and AI in drone navigations [94].](https://www.researchgate.net/profile/Mohsen-Soori/publication/369818981/figure/fig3/AS:11431281138351964@1680736482508/Mobile-edge-computing-and-AI-in-drone-navigations-94_Q320.jpg)
Content uploaded by Mohsen Soori
Author content
All content in this area was uploaded by Mohsen Soori on Apr 14, 2023
Content may be subject to copyright.
Cognitive Robotics 3 (2023) 54–70
Contents lists available at ScienceDirect
Cognitive Robotics
journal homepage: http://www.k eaipublishing.com/en/journals/cogniti ve-robotics/
Articial intelligence, machine learning and deep learning in
advanced robotics, a review
Mohsen Soori
a , ∗
, Behrooz Arezoo
b
, Roza Dastres
c
a
Department of Aeronautical Engineering, University of Kyrenia, Kyrenia, North Cyprus, Via Mersin 10, Turkey
b
CAD/CAPP/CAM Research Center, Department of Mechanical Engineering, Amirkabir University of Technology (Tehran Polytechnic), 424 Hafez
Avenue, Tehran 15875-4413, Iran
c
Department of Computer Engineering, Cyprus International University, North Cyprus, Via Mersin 10, Turkey
Keywords:
Articial intelligence
Machine learning
Deep learning
Advanced robotics
Articial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have revolution-
ized the eld of advanced robotics in recent years. AI, ML, and DL are transforming the eld
of advanced robotics, making robots more intelligent, ecient, and adaptable to complex tasks
and environments. Some of the applications of AI, ML, and DL in advanced robotics include au-
tonomous navigation, object recognition and manipulation, natural language processing, and pre-
dictive maintenance. These technologies are also being used in the development of collaborative
robots (cobots) that can work alongside humans and adapt to changing environments and tasks.
The AI, ML, and DL can be used in advanced transportation systems in order to provide safety,
eciency, and convenience to the passengers and transportation companies . Also, the AI, ML,
and DL are playing a critical role in the advancement of manufacturing assembly robots, enabling
them to work more eciently, safely, and intelligently. Furthermore, they have a wide range of
applications in aviation management, helping airlines to improve eciency, reduce costs, and
improve customer satisfaction. Moreover, the AI, ML, and DL can help taxi companies in order to
provide better, more ecient, and safer services to customers. The research presents an overview
of current developments in AI, ML, and DL in advanced robotics systems and discusses various
applications of the systems in robot modication. Further research works regarding the appli-
cations of AI, ML, and DL in advanced robotics systems are also suggested in order to ll the
gaps between the existing studies and published papers. By reviewing the applications of AI, ML,
and DL in advanced robotics systems, it is possible to investigate and modify the performances
of advanced robots in various applications in order to enhance productivity in advanced robotic
industries.
1. Introduction
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are all important technologies in the eld of robotics
[1] . The term articial intelligence (AI) describes a machine’s capacity to carry out operations that ordinarily require human intel-
lect, such as speech recognition, understanding of natural language, and decision-making. Robots can detect and interact with their
surroundings, make judgments, and carry out dicult tasks with the aid of AI. [2] . A branch of AI known as "machine learning" uses
algorithms to give robots the ability to learn from data and get better over time [3] . It’s possible to program robots to carry out certain
jobs in robotics, such as grasping, object identication, and path planning. Articial neural networks are used in deep learning, a
∗ Corresponding author.
E-mail address: Mohsen.soori@kyrenia.edu.tr (M. Soori) .
https://doi.org/10.1016/j.cogr.2023.04.001
Received 31 March 2023; Received in revised form 5 April 2023; Accepted 5 April 2023
Available online 6 April 2023
2667-2413/© 2023 The Authors. Publishing Services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd. This is an open access article
under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
type of machine learning (ML), to help computers learn from massive volumes of data [4] . DL has been particularly useful in robotics
for tasks such as image and speech recognition, natural language processing, and object detection. Together, these technologies have
enabled the development of robots that can perform a wide range of tasks, from simple pick-and-place operations to complex manip-
ulation and navigation in unstructured environments [5] . The application of AI, ML, and DL in robotics has the potential to transform
the eld, enabling robots to become more intelligent, autonomous, and eective in a wide range of applications. Robotics is a rapidly
evolving eld, and the use of AI, ML, and DL is likely to continue to play a key role in shaping the future of robotics [6] .
In advanced robotic systems, AI is used to create robots that can perceive, reason, and act autonomously in complex environments.
Machine Learning is used to enable robots to learn from their experiences and improve their performance over time. Deep Learning
is used to solve specic problems that are dicult to solve with traditional Machine Learning techniques, such as image and speech
recognition. By combining these technologies, advanced robotics systems can be designed to perform complex tasks that were once
thought impossible. The relationship between them are inclusive in terms of analysis and modication of advanced robotic systems.
These are just a few examples of how AI, ML, and DL are used in robotics. Here are some examples of how they are used in dierent
robotic systems as,
1. Object Detection and Recognition: Object detection and recognition are critical tasks in robotics that have become possible thanks
to deep learning. By training neural networks with massive amounts of labeled data, robots can identify and classify objects in
their environment with high accuracy [7] .
2. Predictive Maintenance: Predictive maintenance is a maintenance approach that uses AI and ML to detect potential issues before
they occur. By analyzing data from sensors and other sources, predictive maintenance algorithms can predict when a robot’s
components may fail, allowing for proactive repairs or replacements [8] .
3. Gesture and Speech Recognition: Gesture and speech recognition are also important applications of AI and ML in robotics. For
example, robots like Pepper can recognize and respond to human gestures and speech, making them useful in a variety of contexts
such as customer service or healthcare [9] .
4. Robotic Surgery: Robotic surgery is a eld where AI and ML are revolutionizing the way operations are performed. By using
advanced algorithms, robotic surgeons can assist human surgeons during complex procedures, reducing the risk of complications
and improving outcomes. Surgical robots use AI, ML, and DL to aid surgeons in performing complex operations with greater
precision and accuracy [10] .
5. Medical applications: DL techniques are particularly useful in analyzing medical images due to their ability to recognize patterns
and features that are not easily identiable by humans [11] . This can help doctors to identify subtle changes in the images that
may indicate the presence of disease [12] . Machine learning models used in drug delivery for infectious disease treatment is shown
in the Fig. 1 [13] . Ensemble algorithm, decision trees and random forest, instance based algorithms and articial neural network
are used to enhance drug delivery of infectious diseases.
6. Military robotics: Robotics is used in military operations for tasks such as reconnaissance, surveillance, and bomb disposal. AI and
ML algorithms are used to analyze data and make decisions based on the information gathered [14] .
7. Agriculture: AI and ML are being used to develop robots that can autonomously navigate and manage crops, increasing eciency
and reducing labor costs. Robotics is used to automate tasks in agriculture, such as planting, harvesting, and spraying. AI and
ML algorithms are used to optimize the farming operations, such as predicting weather patterns, optimizing water usage, and
monitoring crop health [15] .
8 Service robotics: Robotics is used to provide services to humans, such as cleaning, food delivery, and customer service. AI and ML
algorithms are used to enable robots to interact with humans and understand their needs and preferences [16] .
9 Autonomous driving: AI and ML are used to help cars navigate roads and make driving decisions on their own. For example,
self-driving cars use computer vision to detect and recognize objects on the road, and ML algorithms to learn and adapt to
new situations and road conditions [17] . For instance, robots like self-driving cars use AI to detect obstacles and predict trac
movements. Meanwhile, ML algorithms use data from sensors, cameras, and GPS to make navigation decisions [18] .
10. Robotics manufacturing: Robotics is used to automate tasks in manufacturing plants, such as assembly line tasks, painting, and
welding. AI and ML algorithms are used to optimize the robotic operations, such as improving the eciency and accuracy of
movements [2] .
There are various applications of Articial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) in analysis and
modication of advanced robotics. Some of the performance data of these methods in advanced robotics are discussed below:
1. Object Recognition: Object recognition is a crucial task in robotics, and it is essential for autonomous navigation and manipulation.
Deep learning techniques such as Convolutional Neural Networks (CNN) have achieved impressive results in object recognition.
2. Motion Planning: Motion planning is a key task in robotics that involves nding a collision-free path for a robot to move from one
point to another. Reinforcement Learning (RL) is a powerful machine learning technique that has been used to achieve impressive
results in motion planning. For example, the Deep Deterministic Policy Gradient (DDPG) algorithm has been used to generate
smooth and ecient paths for robotic manipulators.
3. Control: Control is another important task in robotics, and it involves regulating the movement of robots. Deep Reinforcement
Learning (DRL) has been used to achieve impressive results in control tasks. For example, the Proximal Policy Optimization (PPO)
algorithm has been used to train a robotic arm to grasp and move objects.
4. Localization: Localization is the process of determining the position of a robot in its environment. Machine Learning techniques
such as Support Vector Machines (SVM) and Random Forests have been used to achieve impressive results in localization tasks.
For example, a Random Forest-based method achieved an accuracy of 98.8% in a robot localization task.
55
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 1. Drug delivery using machine learning algorithms is utilized to treat infectious diseases [13] .
5. Object Detection: Object detection is the process of detecting and localizing objects in an image. Deep Learning techniques such
as Faster R-CNN and YOLO have achieved impressive results in object detection tasks.
AI in robotics can be used to enable robots to recognize objects, navigate complex environments, and even make decisions based
on real-time data. ML can be used to teach robots to learn from experience and adapt to changing situations. DL can be used to enable
robots to perform complex tasks that would otherwise be impossible using traditional programming methods [19] . There are many
programming languages used in Robotics, such as Python, C ++ , MATLAB, and ROS (Robot Operating System). These programming
languages have various libraries and tools that make it easier to incorporate AI, ML, and DL into robotic systems [20] . For example,
TensorFlow and PyTorch are popular deep learning frameworks which can be used in robotics programming applications. Tesla
machines use AI, ML, and DL in a variety of ways. For example, Tesla’s Autopilot system uses AI and ML to enable semi-autonomous
driving, and to recognize and respond to trac conditions. Tesla’s manufacturing processes also use AI and ML to optimize production
eciency and quality [21] .
CNC machining is a crucial technology in the development and maintenance of advanced robotics, allowing for the creation of
highly precise and complex parts and components that are essential for the performance and reliability of robots. CNC machining is
used in the maintenance and repair of robots. When a robot component fails, it is often necessary to create a replacement part that
ts precisely and functions correctly. CNC machining makes it possible to quickly produce replacement parts that meet the required
specications, reducing downtime and ensuring the robot is back in operation as soon as possible.
56
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
To evaluate and enhance CNC machining in virtual environments, Soori et al. proposed virtual machining approaches [22–26] .
To examine and improve eciency in the process of component manufacture using welding processes, Soori et al. [27] proposed
an overview of recent advancements in friction stir welding techniques. Soori and Asamel [28] investigated the utilization of vir-
tual machining technologies to lessen residual stress and deection error during turbine blade ve-axis milling operations. In order
to evaluate and lower the cutting temperature during milling operations of dicult-to-cut components, Soori and Asmael [29] de-
veloped applications of virtualized machining systems. To enhance surface qualities during ve-axis milling operations of turbine
blades, Soori et al. [30] presented an enhanced virtual machining technique. In order to minimize deection error during ve-axis
milling procedures of impeller blades, Soori and Asmael [31] developed virtual milling procedures. In order to analyze and enhance
the parameter optimization approach of machining operations, Soori and Asmael [32] oered a synopsis of current advances from
published works. In order to increase energy usage eectiveness, data quality and availability throughout the supply chain, and
precision and reliability during the component production process, Dastres et al. [33] conducted a research of RFID-based wireless
manufacturing systems. In order to increase eciency and added value in component production processes utilizing CNC machining
operations, Soori et al. [34] examined machine learning and articial intelligence in CNC machine tools. To measure and reduce
residual stress during machining operations, Soori and Arezoo [35] provided a review in the subject. Soori and Arezoo [36] described
optimal machining settings utilizing the Taguchi optimization technique to reduce surface integrity and residual stress during grind-
ing operations of Inconel 718. Soori and Arezoo [37] investigated several tool wear prediction techniques to lengthen cutting tool
life during machining processes. In order to increase eciency in the component production process, Soori and Asmael [38] studied
computer assisted process planning. In order to provide decision - making support systems for data warehouse operations, Dastres
and Soori [39] discussed advancements in web-based decision support systems. In order to develop the implementation of articial
neural networks in performance enhancement of engineering products, Dastres and Soori [40] presented a review of recent research
and uses of articial neural networks in a variety of disciplines, including risk analysis systems, drone control, welding quality anal-
ysis, and computer quality analysis. To minimize cutting tool wear in drilling operations, application of virtual machining system is
developed by Soori and Arezoo [41] . To enhance quality of prodcued parts using abrasive water jet machining, residual stress and
surface roughness are minimized by Soori and Arezoo [42] . Dastres and Soori [43] discussed using information and communica-
tion technology in environmental conservation to lessen the impact of technological progress on natural disasters. Dastres and Soori
[44] proposed the secure socket layer in order to improve network and data online security. In order to create the methodology of
decision support systems by assessing and recommending the gaps between presented methodologies, Dastres and Soori [45] analyze
the advancements in web-based decision support systems. Dastres and Soori [46] provided an assessment of current developments
in network threats in order to improve security measures in networks. Dastres and Soori [47] analyze image processing and analysis
systems to expand the possibilities of image processing systems in many applications.
AI, ML and DL are transforming the eld of advanced robotics by enabling the development of intelligent machines that can
perform complex tasks with high accuracy and eciency. A review in recent development of AI, ML and DL in advanced robotics
system is presented and dierent applications of the systems in modications of robots are also discussed in the study. The gaps
between the published research works in the applications of AI, ML and DL in advanced robotics system are also suggested as future
research works in the interesting research eld. As a result, performances of advanced robots in dierent applications can be analyzed
and modied by reviewing the applications of AI, ML and DL in advanced robotics system in the study. Thus, accuracy as well as
productivity in applications of advanced robots can be enhanced.
2. Advantages of AI, ML and DL applications in advanced robotics
AI (Articial Intelligence), ML (Machine Learning), and DL (Deep Learning) applications have brought about signicant advance-
ments in the eld of robotics [48] . Some of these advantages of AI, ML and DL applications in advanced robotics include:
1. Automation: AI, ML, and DL can automate many repetitive and mundane tasks in robotics, freeing up human resources to focus
on more complex tasks [49] .
2. Enhanced accuracy: These technologies can improve the accuracy and precision of robotic systems, reducing errors and improving
overall performance.
3. Adaptability: AI-powered robots can adapt to changing environments and tasks, making them highly versatile and useful in a
range of industries and applications [48] .
4. Predictive Maintenance: Machine learning algorithms can help robots to predict when maintenance or repairs are required, leading
to reduced downtime and cost savings [50] .
5. Improved Decision Making: AI and ML algorithms can analyze large amounts of data and make informed decisions based on that
data, allowing robots to make better decisions and take appropriate actions [51] .
6. Improved eciency: By optimizing processes and reducing waste, AI, ML, and DL can improve the overall eciency of robotics
systems, resulting in cost savings and increased productivity.
7. Better decision-making: AI, ML, and DL can enable robots to make better decisions based on data analysis and pattern recognition,
leading to improved performance and outcomes [52] .
8. Adaptability: These technologies can enable robots to adapt to changing environments and situations, making them more versatile
and capable of handling a wider range of tasks [53] .
9. Increased safety: By automating hazardous or dangerous tasks, AI, ML, and DL can improve safety in the workplace, reducing the
risk of accidents and injuries.
57
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
10. Cost Reduction: The implementation of AI and ML applications in advanced robotics can signicantly reduce costs associated with
labor and maintenance [54] .
11. Improved Decision-making: By using AI and ML algorithms, robots can make informed decisions based on data analysis, resulting
in better overall performance [55] .
Overall, the use of AI, ML, and DL in robotics has the potential to revolutionize the eld and unlock new levels of performance,
eciency, and safety.
3. Challenges of AI, ML and DL in robotics applications
While these technologies oer many benets, they also pose signicant challenges. One of the biggest challenges is the need for
large amounts of high-quality data to train AI and ML algorithms. However, data collection, labeling, and annotation can be expensive
and time-consuming, and the data may be noisy or biased, which can aect the accuracy and reliability of the models [48] . This can
be particularly challenging in robotics, where data can be dicult to obtain and may be subject to noise and uncertainty. In addition,
robotics applications often require real-time processing, which can be computationally expensive and may require specialized hard-
ware [56] . Furthermore, in order to analyze massive volumes of data, build models, and make predictions in real-time, AI/ML/DL
systems need a lot of processing power. This can be dicult in robotics applications since robots are constrained by energy and
computing power limitations [57] .
Robotics applications often require robots to operate in dynamic and changing environments which need adaptability in oper-
ations [58] . AI/ML/DL models must be designed to adapt to new situations and learn from experience, which can be challenging.
Another challenge is the need for robots to be able to operate safely and eectively in a wide range of environments [15] . As robots
become more autonomous and interact with humans, ensuring their safety becomes a critical challenge. AI/ML/DL algorithms must
be designed to prevent accidents, detect and respond to potential hazards, and avoid collisions with humans and other objects [59] .
This requires the development of robust AI and ML algorithms that can handle unpredictable situations and adapt to changing con-
ditions. It also requires the development of sensors and other hardware that can provide accurate and reliable data about the robot’s
surroundings [60] . In addition, there are ethical and societal challenges associated with the use of AI and robotics. For example,
there are concerns about the impact of automation on jobs and the potential for AI systems to be biased or to perpetuate existing
inequalities. There are also concerns about the potential for robots to be used for harmful purposes, such as military applications or
surveillance [61] .
Overall, while AI, ML, and DL oer many opportunities for robotics, there are also signicant challenges that must be addressed
in order to realize their full potential. Researchers and engineers in this eld must work to develop robust algorithms, hardware, and
ethical frameworks that can support the safe and eective use of these technologies.
4. Applications of AI, ML and DL in advanced industrial robots
There are many potential applications of articial intelligence (AI), machine learning (ML), and deep learning (DL) in advanced
manufacturing robots. AI and ML can be used to analyze production data and optimize production planning. AI and ML can be used to
perform quality control checks on manufactured products [62] . AI algorithms can identify defects in products and alert the production
team to make necessary adjustments in real-time. This helps manufacturers to identify and eliminate bottlenecks, reduce waste, and
increase productivity [63] . Some of these applications include:
1. Quality Control: AI, ML, and DL algorithms can be used to monitor the manufacturing process in real-time and identify defects
or anomalies in the products being produced. This can help improve the quality of the products and reduce the need for human
intervention in the quality control process [64] .
2. Predictive Maintenance: When industrial equipment is predicted to fail, maintenance may be carried out before a breakdown
happens thanks to the usage of AI and ML. By doing so, downtime may be decreased and overall productivity can rise [65] .
3. Autonomous Robots: Advanced manufacturing robots can be equipped with AI and ML algorithms that enable them to operate
autonomously. This can be particularly useful in situations where human intervention is not practical or safe, such as in hazardous
environments or in situations where precision is critical [66] .
4. Assembly robots: AI, ML, and DL technologies are enabling robots during assembly process to work smarter, faster, and more
eciently than ever before, and are helping manufacturers to improve quality, reduce costs, and increase productivity [67] . AI
can be used to control and optimize robotic assembly processes [68] . It can enable robots to adapt to changing conditions, work
collaboratively with human operators, and learn from past experiences to improve future performance. Also, AI can be used to
improve the safety of assembly robots by monitoring their movements and identifying potential hazards [69] . This can help to
prevent accidents and reduce the risk of injury to workers. Moreover, AI can be used to optimize the workow of assembly robots,
by analyzing data on the production process and identifying areas where eciency can be improved [70] .
5. Process Optimization: AI, ML, and DL can be employed to determine the most eective way to make a product in order to improve
the manufacturing process. This can save waste and boost overall eectiveness. [71] .
6. Supply Chain Optimization: AI and ML can be used to optimize the supply chain by predicting demand and ensuring that the right
materials are available at the right time. This can help reduce inventory costs and improve overall eciency [72] .
58
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 2. Application of AI in DL in advanced manufacturing process and robots [5] .
7. Collaborative Robots: AI and ML can be used to enable robots to work alongside human workers in a collaborative environment.
This can help improve productivity and safety by allowing robots to perform repetitive or dangerous tasks while humans focus
on more complex tasks [73] .
AI, ML, and DL have a wide range of applications in advanced manufacturing, including in robotics and automated guided vehicles
(AGVs) [74] . The technologies are essential for optimizing the performance of advanced manufacturing robots and AGVs, allowing
them to work more eciently, accurately, and safely in a variety of settings [75] . Some examples of these applications include:
1. Object detection and recognition: AI and ML algorithms can be used to identify and recognize dierent objects in a manufacturing
environment. This can be useful for robots and AGVs to navigate and interact with their surrounding [76] .
2. Real-time decision making: AI algorithms can enable robots and AGVs to make real-time decisions based on sensor data, allowing
them to adapt to changing conditions in a manufacturing environment [77] .
3. Path optimization: AI algorithms can be used to optimize the path that a robot or AGV takes through a manufacturing facility,
reducing travel time and increasing eciency [78] .
Application of AI in DL in advanced manufacturing process and robots is shown in the Fig. 2 [5] . This owchart explains a crucial
idea from the viewpoint of system requirements when assessing the applicability of any AI technology to guarantee that overall
objectives are satised and sub-optimization is avoided.
Overall, by increasing productivity, cutting costs, and raising product quality, the employment of AI, ML, and DL in advanced
industrial robots has the potential to completely transform the manufacturing sector.
5. Applications of AI, ML and DL in advanced transportation systems
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are increasingly being used in advanced transportation
systems to improve safety, eciency, and convenience [79] . Here are some of the most notable applications of these technologies in
transportation:
1. Intelligent Transportation Systems (ITS): AI-based ITS can help improve trac ow, reduce congestion, and enhance safety on
roads. ML algorithms can analyze trac patterns and optimize signal timings at intersections, while DL algorithms can identify
potential hazards and alert drivers in real-time.
59
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 3. Applications of AI in intelligent trac management.
2. Trac Management: AI, ML, and DL techniques are used to monitor and analyze trac patterns. This helps in optimizing trac
ow and reducing congestion [80] . Applications of AI in intelligent trac management is shown in the Fig. 3 . Smart cameras and
trac lights which are controlled by using the AI can monitor and analyze trac patterns in order to increase the performances
of trac management systems.
3. Autonomous Vehicles: AI, ML, and DL are essential components of autonomous vehicles. These technologies enable vehicles to
perceive and interpret their surroundings, make decisions based on data, and navigate roads safely without human intervention
[81] .
4. Intelligent Transportation Systems (ITS): AI, ML, and DL algorithms are used to develop ITS. ITS includes technologies like smart
trac signals, electronic toll collection systems, and intelligent parking systems, which help in optimizing the transportation
system [82] .
5. Predictive Maintenance: ML algorithms can analyze data from sensors installed on vehicles and predict when maintenance is
needed, allowing for proactive repairs and reducing downtime. This can be especially useful in large eets of vehicles, such as
those used in public transportation [83] .
6. Smart Parking: AI-based parking systems can help drivers nd available parking spots quickly and reduce congestion in busy
areas. ML algorithms can analyze parking data to optimize parking space usage, while DL algorithms can recognize license plates
and enforce parking regulations [84] .
7. Route Optimization: ML algorithms can optimize delivery routes for logistics companies, reducing travel time, and improving fuel
eciency. This can result in cost savings and a reduced environmental footprint [85] .
8. Road Safety: AI, ML, and DL can be used to improve road safety by analyzing trac patterns and identifying areas prone to
accidents. Algorithms can be used to predict and prevent accidents by alerting drivers of potential hazards and suggesting safer
routes [86] .
9. Intelligent Public Transportation: AI and ML can be used to optimize public transportation schedules and routes, providing pas-
sengers with more convenient and ecient services. DL algorithms can also be used to monitor passenger behavior and detect
potential safety issues [87] .
AI applications in collision avoidance and road hazard warning is shown in the Fig. 4 [88] .
Overall, AI, ML, and DL are becoming increasingly important in the development and operation of advanced transportation
systems, helping to improve eciency, safety, and sustainability. The applications of AI, ML, and DL in advanced transportation
systems have the potential to revolutionize the way we travel, making transportation safer, more ecient, and more sustainable.
5.1. Drones
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are all important technologies that can be applied to the
eld of robotics drones. Unmanned aerial vehicles (UAVs), usually referred to as advanced drones, are being utilized more frequently
in a wide range of industries, including agriculture, construction, mining, search and rescue, and military activities [89] . The use of
60
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 4. AI applications in collision avoidance and road hazard warning [88] .
Fig. 5. Mobile edge computing and AI in drone navigations [94] .
AI, ML, and DL in advanced drones has expanded their capabilities and made them more ecient and eective in performing various
tasks of dierent drones [90] . Here’s how:
1. AI in Robotics Drones: AI can help drones to perform complex tasks by using algorithms to analyze data from sensors, cameras,
and other sources. With AI, drones can make decisions on their own based on the data they collect. For example, AI can be used
to identify and track objects, detect obstacles and avoid collisions, and optimize ight paths for maximum eciency [91] .
2. Machine Learning in Robotics Drones: Machine learning is a subset of AI that involves training algorithms to recognize patterns in
data. In the case of robotics drones, machine learning can be used to improve the accuracy of object recognition, object tracking,
and obstacle detection. For example, drones can be trained to recognize dierent types of objects, such as vehicles or people, and
respond accordingly [92] .
3. Deep Learning in Robotics Drones: Deep learning is a subset of machine learning that processes massive quantities of data using
neural networks. Drones can carry out dicult tasks like autonomous navigation and mapping using deep learning. Deep learning,
for instance, may be used to teach drones how to detect and avoid obstacles in real-time [93] . Mobile edge computing and AI in
drone navigations is shown in the Fig. 5 [94] . The Unmanned Aerial Vehicles (UAV) receives divided the task from an IoT device
and transmits the results back after the assignment has been completed. Additionally, in the event that complicated processing
needs exceed the capacity of the onboard cloudlet, the UAV might forward the collected data to the closest ground servers. The
61
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 6. Application of ML in autonomous navigation of drones.
system may incorporate a number of UAVs that support a vast array of deployed Internet of Things devices, such as smartphones,
sensors, cars, and robots. With the use of AI, onboard cloudlets examine and process the user-generated data.
Here are some applications of AI, ML, and DL in advanced drones:
1. Object detection and recognition: AI and ML algorithms can be used to identify and classify objects in drone imagery. This can be
particularly useful in search and rescue missions, where drones can quickly scan a large area and identify objects of interest such
as people, vehicles, or buildings [95] .
2. Autonomous navigation: DL algorithms can be used to enable drones to navigate autonomously without the need for human
intervention. This can be particularly useful in industrial applications where drones need to y in and around obstacles or structures
[96] . Application of ML in autonomous navigation of drones is shown in the Fig. 6 .
3. Precision agriculture: Drones equipped with AI and ML algorithms can be used to collect data on crop health, moisture levels, and
soil conditions. This data can then be used to optimize crop yields and reduce waste [97] .
4. Surveillance and security: Drones equipped with AI and ML algorithms can be used for surveillance and security applications,
such as monitoring borders, detecting intruders, and identifying potential threats [98] .
5. Disaster response: Drones equipped with AI and ML algorithms can be used in disaster response eorts to quickly assess damage
and identify areas where help is needed. This can help rst responders prioritize their eorts and resources [99] .
6. Delivery services: Packages and supplies can be delivered to far-ung or dicult-to-reach regions using drones with AI and ML
algorithms. When drones are delivering packages, these algorithms can guide them and assist them avoid obstacles [100] .
Overall, AI, ML, and DL are all essential technologies in the development of robotics drones. They can help to improve the accuracy,
eciency, and autonomy of drones, making them more useful in a variety of applications. The use of AI, ML, and DL in advanced
drones has expanded their capabilities and made them more ecient and eective in performing various tasks. As these technologies
continue to evolve, we can expect to see even more applications of AI, ML, and DL in advanced drones in the future.
5.2. Ship navigation
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are increasingly being used in robotics, particularly
in ship navigation [101] . These technologies can help ships navigate more eciently, accurately, and safely [102] . Here’s a brief
overview of how AI, ML, and DL are being used in ship navigation:
1. Articial Intelligence (AI): AI can be used in ship navigation to identify patterns and make decisions based on those patterns.
For example, AI algorithms can be used to identify potential hazards or obstacles in a ship’s path and make course corrections to
avoid them [103] . AI can also be used to optimize ship performance, such as fuel consumption and speed, based on environmental
conditions.
2. Machine Learning (ML): ML is a subset of AI that involves training algorithms on data to make predictions or decisions. ML can
be used in ship navigation to learn from past experiences and improve navigation in real-time [104] . For example, ML algorithms
can learn from previous ship routes and weather conditions to make more accurate predictions about future routes.
3. Deep Learning (DL): DL is a subset of ML that uses neural networks to learn from data. DL can be used in ship navigation to
analyze large amounts of data, such as sonar or radar images, to identify potential hazards or obstacles. DL can also be used to
improve ship performance by optimizing engine settings or predicting equipment failures before they occur [105] . Applications of
AI in ship navigation systems is shown in the Fig. 7 [106] . First, in the requirements collection stage, navigation practices in the
open sea, restricted waters, and two-ship and multi-ship interactions are collected and categorized. Second, in the requirements
extraction stage, the collected navigation practices are linked to COLREGs part B to extract the primary rules and keywords on
the topic of collision avoidance. Finally, in the requirements analysis step, the requirements to generate the optimal local path
are analyzed and specied according to the categories identied during the requirements collection and the rules and keywords
dened in the extraction step [106] .
62
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 7. Applications of AI in ship navigation systems [106] .
Some applications of these technologies in ship navigation include:
1. Autonomous navigation: AI and ML algorithms can be used to create autonomous navigation systems that can pilot ships safely
and eciently without human intervention.
2. Collision avoidance: ML models can be trained on historical data to predict potential collisions and provide real-time recommen-
dations to avoid them [107] .
3. Route optimization: AI and ML can be used to analyze weather patterns, currents, and other factors to optimize ship routes for
speed, fuel eciency, and safety [108] .
4. Predictive maintenance: By analyzing sensor data and forecasting equipment breakdowns beforehand, DL algorithms enable proac-
tive maintenance and save downtime.
5. Weather routing: AI and ML algorithms can be used to analyze weather data to identify the safest and most ecient routes for
ships to take, taking into account factors such as wind speed, wave height, and water currents [109] .
6. Autonomous mooring: AI and ML can be used to develop autonomous mooring systems that can safely and eciently dock ships
without human intervention.
Overall, the application of AI, ML, and DL in ship navigation has the potential to greatly improve safety, eciency, and sustain-
ability in the shipping industry [103] .
5.3. Aeronautical industry and aviation managements
The use of AI, ML, and DL in robotics autopilot systems has the potential to improve the reliability and safety of autonomous
vehicles, making them a promising technology for the future of transportation. In robotics autopilot systems, these technologies can
be used to improve the accuracy, eciency, and safety of the system. For example, AI can be used to enable the autopilot system
to make decisions based on real-time data from sensors and cameras [110] . ML can be used to train the system to recognize and
respond to dierent situations, such as changing weather conditions or unexpected obstacles. DL can be used to enable the system
to learn from past experiences and make more accurate predictions about future events. Articial intelligence (AI), machine learning
(ML), and deep learning (DL) are all crucial technologies in the eld of robotics, and they can play a signicant role in improving
the eciency and safety of cargo handling at airports. The creation of intelligent computers with the capacity to carry out activities
that traditionally require human intellect, such as decision-making, natural language processing, and picture recognition, is known
as articial intelligence (AI) [111] . In the context of airport cargo handling, AI can be used to automate tasks such as cargo tracking,
inventory management, and customs processing. ML is a subset of AI that focuses on building algorithms that can learn from data
and make predictions or decisions based on that data [112] . ML algorithms can be used to identify patterns in cargo data, such as
shipping routes, handling times, and delivery destinations, which can be used to optimize cargo handling processes [113] . DL is
a subset of ML that is based on articial neural networks, which are designed to simulate the structure and function of the human
brain. DL algorithms are particularly eective at processing complex data, such as images and video, and can be used to identify cargo
types and detect anomalies, such as damaged or dangerous cargo [114] . In the context of airport cargo handling, robotics systems
can use AI, ML, and DL technologies to perform tasks such as cargo sorting, packing, and transportation. For example, robotic cargo
handlers can use DL algorithms to identify and sort cargo based on size, weight, and destination, and they can use ML algorithms to
optimize their movements and avoid collisions with other cargo handling equipment [115] . Application of AI in dierent sections of
aeronautical industry and aviation managements are shown in the Fig. 8 .
There are a variety of applications of AI (Articial Intelligence), ML (Machine Learning), and DL (Deep Learning) in aviation
management. Here are some examples:
63
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 8. Application of AI in dierent sections of aeronautical industry and aviation managements.
Fig. 9. ML application on aircraft fatigue stress predictions [116] .
1. Predictive maintenance: AI and ML algorithms can be used to predict when maintenance is needed on aircraft components.
This can help airlines to reduce downtime and minimize disruptions to their schedules. ML application on aircraft fatigue stress
predictions is shown in the Fig. 9 [116] .
2. Flight route optimization: AI algorithms can be used to optimize ight routes, taking into account factors such as weather condi-
tions, air trac, and fuel eciency. This can help airlines to reduce fuel consumption and save money [117] .
3. Passenger proling: AI algorithms can be used to analyze passenger data to predict behavior, preferences and improve personalized
service oerings. This can help airlines to tailor their services and improve customer satisfaction [118] .
4. Air trac management: AI and ML algorithms can be used to manage air trac more eciently, reducing the likelihood of delays
and improving safety [119] .
64
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
5. Baggage handling: AI algorithms can be used to optimize the handling of baggage, reducing the risk of lost or delayed luggage
[120] .
6. Crew scheduling: AI and ML algorithms can be used to optimize crew schedules, taking into account factors such as ight times,
rest periods, and seniority. This can help airlines to improve eciency and reduce costs [121] .
7. Fraud detection: AI algorithms can be used to detect fraudulent activity, such as credit card fraud or identity theft, helping airlines
to reduce nancial losses [122] .
Overall, the use of AI, ML, and DL in robotics systems can improve the eciency, safety, and accuracy of airport cargo handling,
which can lead to faster delivery times, reduced costs, and improved customer satisfaction.
5.4. Taxi services
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are all technologies that have the potential to revolu-
tionize the eld of robotics taxi services. These technologies can help improve the safety, eciency, and overall customer experience
of autonomous taxi services [123] . AI is the overarching technology that enables machines to perform tasks that would normally
require human intelligence, such as perception, reasoning, and decision-making. Machine learning is a subset of AI that focuses on
training machines to improve their performance on specic tasks by providing them with data and algorithms [124] . Deep learning
is a subset of machine learning that involves the use of neural networks to analyze large amounts of data and learn patterns [125] .
In the context of robotics taxi services, AI, ML, and DL can be used to achieve several goals. For example:
1. Perception: Autonomous vehicles need to be able to perceive their environment accurately to navigate safely. AI and DL techniques
can be used to process data from sensors such as cameras, lidar, and radar to identify and track objects in real-time [126] .
2. Route planning and optimization: Machine learning can be used to analyze historical data on trac patterns and other factors
that aect travel time, allowing the system to optimize routes and avoid congestion [127] .
3. Decision-making: Autonomous vehicles need to be able to make decisions quickly and accurately in response to changing condi-
tions. AI and DL techniques can be used to develop decision-making algorithms that take into account a wide range of factors,
such as weather, road conditions, and passenger preferences [128] .
4. Route optimization: DL can be used to analyze trac patterns and optimize routes for taxi drivers. This can help them avoid
congestion and take the most ecient route to their destination, which can save time and reduce fuel costs [129] .
5. Customer experience: AI and DL can be used to personalize the customer experience by analyzing data on passenger preferences
and behavior, and providing recommendations for entertainment, food, and other services [130] .
6. Fraud detection: AI algorithms can analyze transaction data to identify fraudulent activities, such as false claims of lost property
or overcharging customers. This can help taxi companies reduce losses and improve customer trust [131] .
7. Chatbots: AI-powered chatbots can be used to provide 24/7 customer support and help passengers book rides, track their taxis,
and get answers to their questions. This can improve customer satisfaction and reduce the workload on call center agents.
8. Safety monitoring: DL can be used to monitor drivers and passengers for safety concerns, such as distracted driving or unruly
behavior. This can help taxi companies maintain high safety standards and reduce the risk of accidents [132] .
9. Autonomous driving: DL is used in autonomous driving technology, which is being developed by taxi companies to reduce labor
costs and improve safety. Autonomous taxis can provide a consistent level of service without the need for drivers [133] .
10. Personalization: ML algorithms can analyze customer data to personalize their experience. For example, by analyzing past trips,
AI can suggest preferred routes or destinations to customers, reducing their travel time and improving their overall experience
[134] .
11. Predictive analytics: AI and ML can be used to analyze historical data to predict future demand for taxi services. This can help taxi
companies optimize their eet management, scheduling, and pricing strategies to ensure that they are providing the right number
of taxis in the right areas at the right times [135] . Intelligent cab service system using the AI based on predictive analytics to
select the best cab for the demand and desire of customers and taxi service company is shown in the Fig. 10 [136] . The wireless
communication network can be used to provide an advanced distributed approach in Cab booking system in order to enhance
eciency of intelligent cab service system.
Overall, the combination of AI, ML, and DL has the potential to make robotics taxi services safer, more ecient, and more enjoyable
for passengers. AI, ML, and DL are transforming the taxi industry by improving eciency, reducing costs, and enhancing customer
experience.
6. Conclusion and future research work directions
Articial intelligence (AI), machine learning (ML), and deep learning (DL) are increasingly being integrated into robotics, providing
robots with the ability to learn, adapt, and improve their performance over time. The elds of robotics and articial intelligence (AI)
are rapidly advancing and merging, with machine learning (ML) and deep learning (DL) playing an increasingly important role
in the development of intelligent robots. Advanced robotics applications that use AI, machine learning, and deep learning include
autonomous vehicles, drone navigation, industrial robots, healthcare robots, and search and rescue robots. These technologies are
transforming the eld of robotics and enabling robots to perform tasks that were once considered too dicult or dangerous for
humans. DL is particularly useful in robotics because it can be used to develop algorithms that enable the robot to learn from large
65
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
Fig. 10. Intelligent cab service system using the AI based on predictive analytics to select the best cab for the demand and desire of customers and
taxi service company [136] .
amounts of sensory data, such as images or audio recordings. This allows the robot to perceive and understand its environment in a
way that is similar to how humans do, and to make decisions based on that understanding. In the case of Tesla machines, AI, ML,
and DL are used to enable a range of advanced capabilities. For example, Tesla’s Autopilot system uses a combination of cameras,
radar, and ultrasonic sensors to detect and respond to obstacles and other vehicles on the road. ML algorithms are used to analyze
this sensor data and make decisions about how to control the vehicle, such as adjusting its speed or steering to avoid collisions.
Additionally, DL algorithms are used to improve the accuracy of object detection and recognition, enabling the vehicle to identify
and track pedestrians, cyclists, and other objects on the road. As Tesla continues to develop its autonomous driving technology, AI,
ML, and DL will likely play an even more important role in enabling safe and ecient self-driving cars. The integration of AI, ML,
and DL into robotics is an exciting and rapidly evolving eld with many potential research directions. Here are some areas of future
research where these technologies could have a signicant impact:
1. Autonomous robots: Autonomous robots that can navigate and interact with their environment without human intervention are
an area of active research. Machine learning algorithms can be used to train robots to recognize and respond to dierent stimuli,
allowing them to perform tasks such as object recognition, path planning, and obstacle avoidance.
2. Reinforcement Learning: Reinforcement learning algorithms enable robots to learn through trial and error, with rewards and
punishments guiding their actions. Further research in this area could focus on developing more ecient and eective algorithms
for training robots in complex tasks, such as navigation and manipulation.
3. Learning from demonstration: ML and DL algorithms can be used to enable robots to learn from demonstration, where a human
operator shows the robot how to perform a task. This can enable robots to quickly learn new tasks and adapt to new environments.
4. Natural Language Processing (NLP): Natural language processing allows robots to understand and respond to human language,
opening up new possibilities for human-robot interaction. Future research could focus on improving the accuracy and speed of
NLP algorithms and developing new applications for language-enabled robots.
66
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
5. Computer Vision: Computer vision is a critical component of robotics, allowing robots to perceive and interact with their envi-
ronment. Further research in this area could focus on improving the accuracy and robustness of object recognition, tracking, and
scene understanding algorithms.
6. Neural networks: By using neural networks, robots can learn from experience and become more ecient over time.
7. Vision-based navigation: Vision-based navigation is a promising area of research in robotics, where robots use cameras and other
sensors to navigate through complex environments. Using ML and DL techniques, robots can learn to recognize and classify
dierent objects in their environment, which can help them to make better decisions and navigate more eectively.
8. Collaborative Robotics: Collaborative robots, or cobots, are designed to work alongside human operators, making them ideal
for tasks that require a combination of human dexterity and robotic precision. Future research could focus on developing new
algorithms and control strategies that enable more eective collaboration between humans and robots.
9. Human-robot interaction: As robots become more common in various settings, it becomes increasingly important to design robots
that can interact with humans in a natural and intuitive way. Machine learning algorithms can be used to analyze human behavior
and preferences, enabling robots to adapt to human needs and preferences.
10. Robotic vision: Robotics relies heavily on vision since it enables robots to interact and comprehend their surroundings. Deep
learning algorithms have shown great success in image and video recognition, enabling robots to recognize objects, people, and
activities in real-time.
11. Object recognition and manipulation: With advancements in computer vision technology, robots can now recognize and manip-
ulate objects with a high degree of accuracy. Future research can focus on developing more sophisticated algorithms that enable
robots to interact with the environment in a more natural and intuitive manner.
12. Robotics in healthcare: Robotics has the potential to revolutionize healthcare by enabling robots to assist with surgeries, deliver
medications, and provide therapy to patients. Machine learning algorithms can be used to analyze medical data, identify patterns,
and make predictions, enabling robots to provide more personalized care.
13. Swarm robotics: Swarm robotics is an emerging eld that focuses on coordinating large groups of robots to perform tasks. Machine
learning algorithms can be used to enable robots to communicate with each other, coordinate their actions, and adapt to changing
environments.
14. Robot control: In robotics, control is the process of determining how a robot should move and interact with its environment. ML
and DL techniques can be used to develop more sophisticated control algorithms that can adapt to changing environments and
improve the performance of robots.
Overall, the combination of AI, ML, and DL with robotics has the potential to create a wide range of applications that can benet
society in various ways. The combination of AI, ML, and DL in advanced robotics is enabling the development of robots that are
more intelligent, versatile, and capable than ever before. In advanced robotics, these technologies are used to create robots that can
perform complex tasks and learn from experience. AI, ML, and DL can be used to improve the accuracy of autonomous vehicles,
allowing robots to operate them more safely and eectively. There are many exciting research directions and applications of AI, ML,
and DL in robotics, and the eld is likely to continue to grow and evolve rapidly in the coming years. Continued research in this eld
is likely to lead to exciting new developments in the years to come.
Declaration of Competing Interest
Dear Editor
I conrm that there is no conict of interest regarding the submitted manuscript with title of Artificial Intelligence, Machine
Learning and Deep Learning in Advanced Robotics, A Review to the Cognitive Robotics.
Thank you so much.
Yours sincerely,
Mohsen Soori
References
[1] M. Woschank, E. Rauch, H. Zsifkovits, A review of further directions for articial intelligence, machine learning, and deep learning in smart logistics, Sustain-
ability 12 (2020) 3760
.
[2] S. Fahle, C. Prinz, B. Kuhlenkötter, Systematic review on machine learning (ML) methods for manufacturing processes–Identifying articial intelligence (AI)
methods for eld application, Procedia CIRP 93 (2020) 413–418
.
[3] D. Vrontis, M. Christo, V. Pereira, S. Tarba, A. Makrides, E. Trichina, Articial intelligence, robotics, advanced technologies and human resource management:
a systematic review, Int. J. Human Res. Manag. 33 (2022) 1237–1266
.
[4] J. Howard, Articial intelligence: implications for the future of work, Am. J. Ind. Med. 62 (2019) 917–926 .
[5] J.F. Arinez, Q. Chang, R.X. Gao, C. Xu, J. Zhang, Articial intelligence in advanced manufacturing: current status and future outlook, J. Manuf. Sci. Eng. (2020)
142
.
[6] I. Andras, E. Mazzone, F.W. van Leeuwen, G. De Naeyer, M.N. van Oosterom, S. Beato, T. Buckle, S. O’Sullivan, P.J. van Leeuwen, A. Beulens, Articial
intelligence and robotics: a combination that is changing the operating room, World J. Urol. 38 (2020) 2359–2366
.
[7] Q. Bai, S. Li, J. Yang, Q. Song, Z. Li, X. Zhang, Object detection recognition and robot grasping based on machine learning: a survey, IEEE Access 8 (2020)
181855–181879
.
[8] W.J. Lee, H. Wu, H. Yun, H. Kim, M.B. Jun, J.W. Sutherland, Predictive maintenance of machine tool systems using articial intelligence techniques applied to
machine condition data, Procedia Cirp 80 (2019) 506–511
.
[9] X. Jiang, S.C. Satapathy, L. Yang, S.-.H. Wang, Y.-.D. Zhang, A survey on articial intelligence in Chinese sign language recognition, Arabian J. Sci. Eng. 45
(2020) 9859–9894
.
67
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
[10] S. Panesar, Y. Cagle, D. Chander, J. Morey, J. Fernandez-Miranda, M. Kliot, Articial intelligence and the future of surgical robotics, Ann. Surg. 270 (2019)
223–226
.
[11] T.Le Nguyen, T.T.H. Do, Articial intelligence in healthcare: a new technology benet for both patients and doctors, in: 2019 Portland International Conference
on Management of Engineering and Technology (PICMET), IEEE, 2019, pp. 1–15
.
[12] S. Sarker, L. Jamal, S.F. Ahmed, N. Irtisam, Robotics and articial intelligence in healthcare during COVID-19 pandemic: a systematic review, Rob Auton. Syst.
146 (2021) 103902
.
[13] S. He, L.G. Leanse, Y. Feng, Articial intelligence and machine learning assisted drug delivery for eective treatment of infectious diseases, Adv. Drug Deliv.
Rev. 178 (2021) 113922
.
[14] S. Wasilow, J.B. Thorpe, Articial intelligence, robotics, ethics, and the military: a Canadian perspective, AI Magazine 40 (2019) 37–48 .
[15] M.T. Linaza, J. Posada, J. Bund, P. Eisert, M. Quartulli, J. Döllner, A. Pagani, I.G. Olaizola, A. Barriguinha, T. Moysiadis, Data-driven articial intelligence
applications for sustainable precision agriculture, Agronomy 11 (2021) 1227
.
[16] R. Belk, Ethical issues in service robotics and articial intelligence, Serv. Ind. J. 41 (2021) 860–876 .
[17] B.B. Elallid, N. Benamar, A.S. Had, T. Rachidi, N. Mrani, A comprehensive survey on the application of deep and reinforcement learning approaches in
autonomous driving, J. King Saud Univ.-Comput. Inf. Sci. (2022)
.
[18] H. Ning, R. Yin, A. Ullah, F. Shi, A survey on hybrid human-articial intelligence for autonomous driving, IEEE Trans. Intell. Transp. Syst. 23 (2021) 6011–6026 .
[19] M. El-Shamouty, K. Kleeberger, A. Lämmle, M. Huber, Simulation-driven machine learning for robotics and automation, tm-Technisches Messen 86 (2019)
673–684
.
[20] C. Lammie, M.R. Azghadi, Memtorch: a simulation framework for deep memristive cross-bar architectures, in: 2020 IEEE international symposium on circuits
and systems (ISCAS), IEEE, 2020, pp. 1–5
.
[21] P. Cooke, Gigafactory logistics in space and time: tesla’s fourth gigafactory and its rivals, Sustainability 12 (2020) 2044 .
[22] M. Soori, B. Arezoo, M. Habibi, Accuracy analysis of tool deection error modelling in prediction of milled surfaces by a virtual machining system, Int. J.
Comput. Appl. Technol. 55 (2017) 308–321
.
[23] M. Soori, B. Arezoo, M. Habibi, Virtual machining considering dimensional, geometrical and tool deection errors in three-axis CNC milling machines, J. Manuf.
Syst. 33 (2014) 498–507
.
[24] M. Soori, B. Arezoo, M. Habibi, Dimensional and geometrical errors of three-axis CNC milling machines in a virtual machining system, Comput. Aided Des. 45
(2013) 1306–1313
.
[25] M. Soori, B. Arezoo, M. Habibi, Tool deection error of three-axis computer numerical control milling machines, monitoring and minimizing by a virtual
machining system, J. Manuf. Sci. Eng. 138 (2016)
.
[26] M. Soori, B. Arezoo, Dimensional, geometrical, thermal and tool deection errors compensation in 5-Axis CNC milling operations, Austr. J. Mech. Eng. (2023) .
[27] M. Soori, M. Asmael, D. Solyal ı , Recent development in friction stir welding process: a review, SAE Int. J. Mater. Manuf. (2020) 18 .
[28] M. Soori, M. Asmael, Virtual minimization of residual stress and deection error in ve-axis milling of turbine blades, Strojniski Vestnik/J. Mech. Eng. 67
(2021) 235–244
.
[29] M. Soori, M. Asmael, Cutting temperatures in milling operations of dicult-to-cut materials, J. New Technol. Mater. 11 (2021) 47–56 .
[30] M. Soori, M. Asmael, A. Khan, N. Farouk, Minimization of surface roughness in 5-axis milling of turbine blades, Mech. Based Des. Struct. Mach. (2021) 1–18 .
[31] M. Soori, M. Asmael, Minimization of deection error in ve axis milling of impeller blades, Facta Universitatis, Series: Mechanical Engineering, 2021 .
[32] M. Soori, M. Asmael, A review of the recent development in machining parameter optimization, Jordan J. Mech. Ind. Eng. 16 (2022) 205–223 .
[33] R. Dastres, M. Soori, M. Asmael, Radio frequency identication (RFID) based wireless manufacturing systems, a review, Ind. J. Manag. Prod. 13 (2022) 258–290 .
[34] M. Soori, B. Arezoo, R. Dastres, Machine learning and articial intelligence in CNC machine tools, a review, Sustain. Manuf. Service Econ. (2023) 100009 .
[35] M. Soori, B. Arezoo, A review in machining-induced residual stress, J. New Technol. Mater. 12 (2022) 64–83 .
[36] M. Soori, B. Arezoo, Minimization of surface roughness and residual stress in grinding operations of inconel 718, J. Mater. Eng. Perform. (2022) 1–10 .
[37] M. Soori, B. Arezoo, Cutting tool wear prediction in machining operations, a review, J. New Technol. Mater. 12 (2022) 15–26 .
[38] M. Soori, M. Asmael, Classication of research and applications of the computer aided process planning in manufacturing systems, Independ. J. Manag. Prod.
12 (2021) 1250–1281
.
[39] R. Dastres, M. Soori, Advances in web-based decision support systems, Int. J. Eng. Future Technol. 19 (2021) 1–15 .
[40] R. Dastres, M. Soori, Articial neural network systems, Int. J. Imaging Robot. (IJIR) 21 (2021) 13–25 .
[41] M. Soori, B. Arezoo, Cutting tool wear minimization in drilling operations of titanium alloy Ti-6Al-4V, in: Proceedings of the Institution of Mechanical Engineers,
Part J: Journal of Engineering Tribology, 2023
.
[42] M. Soori, B. Arezoo, Minimization of surface roughness and residual stress in abrasive water jet cutting of titanium alloy Ti6Al4V, Proc. Inst. Mech. Eng. Part
E J. Process Mech. Eng. (2023) 09544089231157972
.
[43] R. Dastres, M. Soori, The role of Information and Communication Technology (ICT) in environmental protection, Int. J. Tomogr. Simul. 35 (2021) 24–37 .
[44] R. Dastres, M. Soori, Secure socket layer in the network and web security, Int. J. Comput. Inf. Eng. 14 (2020) 330–333 .
[45] R. Dastres, M. Soori, Advances in web-based decision support systems, Int. J. Eng. Future Technol. (2021) .
[46] R. Dastres, M. Soori, A review in recent development of network threats and security measures, Int. J. Information Sci. Comput. Eng. (2021) .
[47] R. Dastres, M. Soori, Advanced image processing systems, Int. J. Imag. Robot. 21 (2021) 27–44 .
[48] S.K. Baduge, S. Thilakarathna, J.S. Perera, M. Arashpour, P. Shara, B. Teodosio, A. Shringi, P. Mendis, Articial intelligence and smart vision for building and
construction 4.0: machine and deep learning methods and applications, Autom. Constr. 141 (2022) 104440
.
[49] P. Sardar, J.D. Abbott, A. Kundu, H.D. Aronow, J.F. Granada, J. Giri, Impact of articial intelligence on interventional cardiology: from decision-making aid to
advanced interventional procedure assistance, Cardiovasc. Intervent. 12 (2019) 1293–1303
.
[50] J. Dalzochio, R. Kunst, E. Pignaton, A. Binotto, S. Sanyal, J. Favilla, J. Barbosa, Machine learning and reasoning for predictive maintenance in Industry 4.0:
current status and challenges, Comput. Ind. 123 (2020) 103298
.
[51] M. Abdar, A. Khosravi, S.M.S. Islam, U.R. Acharya, A.V. Vasilakos, The need for quantication of uncertainty in articial intelligence for clinical data analysis:
increasing the level of trust in the decision-making process, IEEE Syst., Man, Cybernet. Mag. 8 (2022) 28–40
.
[52] E. Begoli, T. Bhattacharya, D. Kusnezov, The need for uncertainty quantication in machine-assisted medical decision making, Nature Machine Intelligence 1
(2019) 20–23
.
[53] B. Zohuri, M. Moghaddam, F. Mossavar-Rahmani, Business resilience system integrated articial intelligence system, Int. J. Theoret. Computat. Phys. 3 (2022)
1–7
.
[54] D.M. Dimiduk, E.A. Holm, S.R. Niezgoda, Perspectives on the impact of machine learning, deep learning, and articial intelligence on materials, processes, and
structures engineering, Integr. Mater. Manuf. Innov. 7 (2018) 157–172
.
[55] Y.R. Shrestha, V. Krishna, G. von Krogh, Augmenting organizational decision-making with deep learning algorithms: principles, promises, and challenges, J.
Bus. Res. 123 (2021) 588–603
.
[56] A.I. Károly, P. Galambos, J. Kuti, I.J. Rudas, Deep learning in robotics: survey on model structures and training strategies, IEEE Trans. Syst., Man, Cybernet. 51
(2020) 266–279
.
[57] A.K. Tyagi, P. Chahal, Articial intelligence and machine learning algorithms, in: Research Anthology on Machine Learning Techniques, Methods, and Appli-
cations, IGI Global, 2022, pp. 421–446
.
[58] J. Arents, M. Greitans, Smart industrial robot control trends, challenges and opportunities within manufacturing, Appl. Sci. 12 (2022) 937 .
[59] P.K. Garg, Overview of articial intelligence, in: Articial Intelligence, Chapman and Hall/CRC, 2021, pp. 3–18 .
[60] M. Kamruzzaman, New opportunities, challenges, and applications of edge-AI for connected healthcare in smart cities, in: 2021 IEEE Globecom Workshops (GC
Wkshps), IEEE, 2021, pp. 1–6
.
68
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
[61] A. Kapeller, H. Felzmann, E. Fosch-Villaronga, A.-.M. Hughes, A taxonomy of ethical, legal and social implications of wearable robots: an expert perspective,
Sci. Eng. Ethics 26 (2020) 3229–3247
.
[62] M. Milazzo, F. Libonati, The synergistic role of additive manufacturing and articial intelligence for the design of new advanced intelligent systems, Adv. Intell.
Syst. 4 (2022) 2100278
.
[63] Z. Huang, Y. Shen, J. Li, M. Fey, C. Brecher, A survey on AI-driven digital twins in industry 4.0: smart manufacturing and advanced robotics, Sensors 21 (2021)
6340
.
[64] S. Sundaram, A. Zeid, Articial intelligence-based smart quality inspection for manufacturing, Micromachines (Basel) 14 (2023) 570 .
[65] S. Pookkuttath, M. Rajesh Elara, V. Sivanantham, B. Ramalingam, AI-enabled predictive maintenance framework for autonomous mobile cleaning robots,
Sensors 22 (2022) 13
.
[66] A.A. Gumbs, I. Frigerio, G. Spolverato, R. Croner, A. Illanes, E. Chouillard, E. Elyan, Articial intelligence surgery: how do we get to autonomous actions in
surgery? Sensors 21 (2021) 5526
.
[67] C. Murugamani, S.K. Sahoo, P.R. Kshirsagar, B.R. Prathap, S. Islam, Q. Noorulhasan Naveed, M.R. Hussain, B.T. Hung, D.M. Teressa, Wireless communication
for robotic process automation using machine learning technique, in: Wireless Communications and Mobile Computing, 2022, p. 2022
.
[68] N. Dimitropoulos, T. Togias, N. Zacharaki, G. Michalos, S. Makris, Seamless human–robot collaborative assembly using articial intelligence and wearable
devices, Appl. Sci. 11 (2021) 5699
.
[69] A.W. Hashmi, H.S. Mali, A. Meena, I.A. Khilji, M.F. Hashmi, Articial intelligence techniques for implementation of intelligent machining, Mater. Today: Proc.
56 (2022) 1947–1955
.
[70] A. Simeth, P. Plapper, Articial intelligence based robotic automation of manual assembly tasks for intelligent manufacturing, in: Smart, Sustainable Manufac-
turing in an Ever-Changing World: Proceedings of International Conference on Competitive Manufacturing (COMA’22), Springer, 2023, pp. 137–148
.
[71] S.O. Abioye, L.O. Oyedele, L. Akanbi, A. Ajayi, J.M.D. Delgado, M. Bilal, O.O. Akinade, A. Ahmed, Articial intelligence in the construction industry: a review
of present status, opportunities and future challenges, J. Build. Eng. 44 (2021) 103299
.
[72] R. Toorajipour, V. Sohrabpour, A. Nazarpour, P. Oghazi, M. Fischl, Articial intelligence in supply chain management: a systematic literature review, J. Bus.
Res. 122 (2021) 502–517
.
[73] R. Benotsmane, G. Kovács, L. Dudás, Economic, social impacts and operation of smart factories in Industry 4.0 focusing on simulation and articial intelligence
of collaborating robots, Soc. Sci. 8 (2019) 143
.
[74] S. Sheth, A. Ajmera, A. Sharma, S. Patel, C. Kathrecha, Design and development of intelligent AGV using computer vision and articial intelligence, in: Soft
Computing: Theories and Applications: Proceedings of SoCTA 2016, Springer, 2018, pp. 337–349. Volume 1
.
[75] P. Ba ł azy, P. Gut, P. Knap, Positioning algorithm for AGV autonomous driving platform based on articial neural networks, Robotic Syst. Appl. 1 (2021) 41–45 .
[76] G. Chryssolouris, K. Alexopoulos, Z. Arkouli, Articial intelligence in manufacturing equipment, automation, and robots, in: A Perspective on Articial Intelli-
gence in Manufacturing, Springer, 2023, pp. 41–78
.
[77] D.-.Y. Cho, M.-.K. Kang, Human gaze-aware attentive object detection for ambient intelligence, Eng. Appl. Artif. Intell. 106 (2021) 104471 .
[78] S. Lin, A. Liu, J. Wang, X. Kong, An intelligence-based hybrid PSO-SA for mobile robot path planning in warehouse, J. Comput. Sci. 67 (2023) 101938 .
[79] H. Khawar, T.R. Soomro, M.A. Kamal, Machine learning for internet of things-based smart transportation networks, in: Machine Learning for Societal Improve-
ment, Modernization, and Progress, IGI Global, 2022, pp. 112–134
.
[80] A. Sharma, Y. Awasthi, S. Kumar, The role of blockchain, AI and IoT for smart road trac management system, in: 2020 IEEE India Council International
Subsections Conference (INDISCON), IEEE, 2020, pp. 289–296
.
[81] Y. Ma, Z. Wang, H. Yang, L. Yang, Articial intelligence applications in the development of autonomous vehicles: a survey, IEEE/CAA J. Automat. Sinica 7
(2020) 315–329
.
[82] L.S. Iyer, AI enabled applications towards intelligent transportation, Transport. Eng. 5 (2021) 100083 .
[83] A. Theissler, J. Pérez-Velázquez, M. Kettelgerdes, G. Elger, Predictive maintenance enabled by machine learning: use cases and challenges in the automotive
industry, Reliab. Eng. Syst. Saf. 215 (2021) 107864
.
[84] F. Zantalis, G. Koulouras, S. Karabetsos, D. Kandris, A review of machine learning and IoT in smart transportation, Future Int. 11 (2019) 94 .
[85] S. Olugbade, S. Ojo, A.L. Imoize, J. Isabona, M.O. Alaba, A review of articial intelligence and machine learning for incident detectors in road transport systems,
Mathemat. Comput. Appl. 27 (2022) 77
.
[86] Z. Halim, R. Kalsoom, S. Bashir, G. Abbas, Articial intelligence techniques for driving safety and vehicle crash prediction, Artif. Intell. Rev. 46 (2016) 351–387 .
[87] A. Nikitas, K. Michalakopoulou, E.T. Njoya, D. Karampatzakis, Articial intelligence, transport and the smart city: denitions and dimensions of a new mobility
era, Sustainability 12 (2020) 2789
.
[88] T. Yuan, W. da Rocha Neto, C.E. Rothenberg, K. Obraczka, C. Barakat, T. Turletti, Machine learning for next-generation intelligent transportation systems: a
survey, Trans. Emerging Telecommun. Technol. 33 (2022) e4427
.
[89] O.P. Olawale, K. Dimililer, F. Al-Turjman, AI simulations and programming environments for drones: an overview, Drones Smart-Cities (2020) 93–106 .
[90] A. Heidari, N. Jafari Navimipour, M. Unal, G. Zhang, Machine learning applications in internet-of-drones: systematic review, recent deployments, and open
issues, ACM Comput. Surv. 55 (2023) 1–45
.
[91] T. De Swarte, O. Boufous, P. Escalle, Articial intelligence, ethics and human values: the cases of military drones and companion robots, Artif. Life Robot. 24
(2019) 291–296
.
[92] C. Toma, M. Popa, B. Iancu, M. Doinea, A. Pascu, F. Ioan-Dutescu, Edge machine learning for the automated decision and visual computing of the robots, IoT
embedded devices or UAV-drones, Electronics (Basel) 11 (2022) 3507
.
[93] A. Singh, K. Raj, T. Kumar, S. Verma, A.M. Roy, Deep learning-based cost-eective and responsive robot for autism treatment, Drones 7 (2023) 81 .
[94] Y. Yazid, I. Ez-Zazi, A. Guerrero-González, A. El Oualkadi, M. Arioua, UAV-enabled mobile edge-computing for IoT based on AI: a comprehensive review,
Drones 5 (2021) 148
.
[95] X. Wu, W. Li, D. Hong, R. Tao, Q. Du, Deep learning for unmanned aerial vehicle-based object detection and tracking: a survey, IEEE Geosci. Remote Sens.
Mag. 10 (2021) 91–124
.
[96] S. Bijjahalli, R. Sabatini, A. Gardi, Advances in intelligent and autonomous navigation systems for small UAS, Prog. Aerosp. Sci. 115 (2020) 100617 .
[97] T. Saranya, C. Deisy, S. Sridevi, K.S.M. Anbananthen, A comparative study of deep learning and internet of things for precision agriculture, Eng. Appl. Artif.
Intell. 122 (2023) 106034
.
[98] F.S. Alrayes, S.S. Alotaibi, K.A. Alissa, M. Maashi, A. Alhogail, N. Alotaibi, H. Mohsen, A. Motwakel, Articial intelligence-based secure communication and
classication for drone-enabled emergency monitoring systems, Drones 6 (2022) 222
.
[99] S.K. Abid, N. Sulaiman, S.W. Chan, U. Nazir, M. Abid, H. Han, A. Ariza-Montes, A. Vega-Muñoz, Toward an integrated disaster management approach: how
articial intelligence can boost disaster management, Sustainability 13 (2021) 12560
.
[100] S. Sorooshian, S. Khademi Sharifabad, M. Parsaee, A.R. Afshari, Toward a modern last-mile delivery: consequences and obstacles of intelligent technology,
Appl. Syst. Innov. 5 (2022) 82
.
[101] J.C. Molina-Molina, M. Salhaoui, A. Guerrero-González, M. Arioua, Autonomous marine robot based on AI recognition for permanent surveillance in marine
protected areas, Sensors 21 (2021) 2664
.
[102] B.L. AYLAK, The impacts of the applications of articial intelligence in maritime logistics, Avrupa Bilim ve Teknoloji Dergisi (2022) 217–225 .
[103] R. Yan, S. Wang, L. Zhen, G. Laporte, Emerging approaches applied to maritime transport research: past and future, Commun. Transport. Res. 1 (2021) 100011 .
[104] T. Zhou, Q. Hu, Z. Hu, J. Zhi, Theory and application of vessel speed dynamic control considering safety and environmental factors, J. Adv. Transport. (2022)
2022
.
[105] Y. Qiao, J. Yin, W. Wang, F. Duarte, J. Yang, C. Ratti, Survey of deep learning for autonomous surface vehicles in marine environments, IEEE Trans. Intell.
Transp. Syst. (2023)
.
[106] S.-.W. Ohn, H. Namgung, Requirements for optimal local route planning of autonomous ships, J. Mar. Sci. Eng. 11 (2022) 17 .
69
M. Soori, B. Arezoo and R. Dastres Cognitive Robotics 3 (2023) 54–70
[107] W. Hammedi, B. Brik, S.M. Senouci, Federated deep learning-based framework to avoid collisions between inland ships, in: 2022 International Wireless Com-
munications and Mobile Computing (IWCMC), IEEE, 2022, pp. 967–972
.
[108] C. Zhang, D. Zhang, M. Zhang, W. Mao, Data-driven ship energy eciency analysis and optimization model for route planning in ice-covered Arctic waters,
Ocean Eng. 186 (2019) 106071
.
[109] C. Gkerekos, I. Lazakis, A novel, data-driven heuristic framework for vessel weather routing, Ocean Eng. 197 (2020) 106887 .
[110] V.M.R. Dias, D. Jugend, P. de Camargo Fiorini, C. do Amaral Razzino, M.A.P. Pinheiro, Possibilities for applying the circular economy in the aerospace industry:
practices, opportunities and challenges, J. Air Transport Manag. 102 (2022) 102227
.
[111] A.I. Roadmap, A human-centric approach to AI in aviation, in: European Aviation Safety Agency, 2020, p. 1 .
[112] K. Khan, M. Sohaib, A. Rashid, S. Ali, H. Akbar, A. Basit, T. Ahmad, Recent trends and challenges in predictive maintenance of aircraft’s engine and hydraulic
system, J. Brazil. Soc. Mech. Sci. Eng. 43 (2021) 1–17
.
[113] R. Pranav, H. Gururaja, Explainable stacking machine learning ensemble for predicting airline customer satisfaction, in: Third Congress on Intelligent Systems:
Proceedings of CIS 2022, 1, Springer, 2023, pp. 41–56
.
[114] S.L. Brunton, J. Nathan Kutz, K. Manohar, A.Y. Aravkin, K. Morgansen, J. Klemisch, N. Goebel, J. Buttrick, J. Poskin, A.W. Blom-Schieber, Data-driven aerospace
engineering: reframing the industry with machine learning, AIAA J. 59 (2021) 2820–2847
.
[115] A. Sukhorukov, N. Koryagin, J. Sulyagina, N. Ulitskaya, S. Eroshkin, Digital transformation of airline management as the basis of innovative development, in:
VIII International Scientic Siberian Transport Forum: TransSiberia 2019, 1, Springer, 2020, pp. 845–854
.
[116] E. O’Higgins, K. Graham, D. Daverschot, J. Baris, Machine learning application on aircraft fatigue stress predictions, in: ICAF 2019–Structural Integrity in the
Age of Additive Manufacturing: Proceedings of the 30th Symposium of the International Committee on Aeronautical Fatigue, June 2-7, 2019, Springer, Krakow,
Poland, 2020, pp. 1031–1042
.
[117] S.Y. Choi, D. Cha, Unmanned aerial vehicles using machine learning for autonomous ight; state-of-the-art, Adv. Robot. 33 (2019) 265–277 .
[118] R. Iqbal, F. Doctor, B. More, S. Mahmud, U. Yousuf, Big data analytics and computational intelligence for cyber–physical systems: recent trends and state of
the art applications, Future Generat. Comput. Syst. 105 (2020) 766–778
.
[119] A. Degas, M.R. Islam, C. Hurter, S. Barua, H. Rahman, M. Poudel, D. Ruscio, M.U. Ahmed, S. Begum, M.A. Rahman, A survey on articial intelligence (ai) and
explainable ai in air trac management: current trends and development with future research trajectory, Appl. Sci. 12 (2022) 1295
.
[120] D.Alonso Tabares, F. Mora-Camino, Intelligent and fuzzy applications in aircraft handling services with aviation 4.0, in: Intelligent and Fuzzy Techniques in
Aviation 4.0: Theory and Applications, Springer, 2021, pp. 175–199
.
[121] M. Deveci, N.Ç. Demirel, A survey of the literature on airline crew scheduling, Eng. Appl. Artif. Intell. 74 (2018) 54–69 .
[122] L. Li, R.J. Hansman, R. Palacios, R. Welsch, Anomaly detection via a Gaussian Mixture Model for ight operation and safety monitoring, Transport. Res. Part
C 64 (2016) 45–57
.
[123] T.R. Arbatani, E. Norouzi, A. Omidi, J.M. Valero-Pastor, Competitive strategies of mobile applications in online taxi services: the cases of Snapp and Tap30 in
Iran, Int. J. Emerg. Markets 16 (2021) 113–130
.
[124] B.J. Chelliah, Taxi fare prediction system using key feature extraction in articial intelligence, Turkish J. Comput. Math. Educ. (TURCOMAT) 12 (2021)
3803–3808
.
[125] H. Luo, J. Cai, K. Zhang, R. Xie, L. Zheng, A multi-task deep learning model for short-term taxi demand forecasting considering spatiotemporal dependences,
J. Trac Transport. Eng. (English Edition) 8 (2021) 83–94
.
[126] A. Holzinger, G. Langs, H. Denk, K. Zatloukal, H. Müller, Causability and explainability of articial intelligence in medicine, Wiley Interdiscipl. Rev. 9 (2019)
e1312
.
[127] Z. Ullah, F. Al-Turjman, L. Mostarda, R. Gagliardi, Applications of articial intelligence and machine learning in smart cities, Comput. Commun. 154 (2020)
313–323
.
[128] S. Ajani, S.Y. Amdani, Dynamic path planning approaches based on articial intelligence and machine learning, Turkish J. Comput. Math. Educ. (TURCOMAT)
11 (2020) 2084–2098
.
[129] I.J. Jacob, P.E. Darney, Articial bee colony optimization algorithm for enhancing routing in wireless networks, J. Artif. Intell. 3 (2021) 62–71 .
[130] X. Cheng, L. Qiao, B. Yang, Z. Li, An investigation on the inuencing factors of elderly people’s intention to use nancial AI customer service, Int. Res. (2023) .
[131] X. Wang, W. Liu, H. Lin, J. Hu, K. Kaur, M.S. Hossain, AI-empowered trajectory anomaly detection for intelligent transportation systems: a hierarchical federated
learning approach, IEEE Trans. Intell. Transp. Syst. (2022)
.
[132] R. Singh, R. Sharma, S.V. Akram, A. Gehlot, D. Buddhi, P.K. Malik, R. Arya, Highway 4.0: digitalization of highways for vulnerable road safety development
with intelligent IoT sensors and machine learning, Saf. Sci. 143 (2021) 105407
.
[133] A. Miglani, N. Kumar, Deep learning models for trac ow prediction in autonomous vehicles: a review, solutions, and challenges, Vehicular Commun. 20
(2019) 100184
.
[134] R. Abduljabbar, H. Dia, S. Liyanage, S.A. Bagloee, Applications of articial intelligence in transport: an overview, Sustainability 11 (2019) 189 .
[135] S. Ramani, A. Ghiya, P.S. Aravind, M. Karuppiah, D. Pelusi, Predicting new york taxi trip duration based on regression analysis using ML and time series
forecasting using DL, in: Intelligent Sustainable Systems: Proceedings of ICISS 2022, Springer, 2022, pp. 15–28
.
[136] A. Nath, A. Khandelwal, A. Kanojia, I. Minocha, R. Niyogi, Design and implementation of an intelligent cab service system, in: 2017 Tenth International
Conference on Contemporary Computing (IC3), IEEE, 2017, pp. 1–6
.
70
