Fig 5 - uploaded by Raja Masood Larik
Content may be subject to copyright.
Source publication
Traditional flight controllers consist of Proportional Integral Derivates (PID), that although have dominant stability control but required high human interventions. In this study, a smart flight controller is developed for controlling UAVs which produces operator less mechanisms for flight controllers. It uses a neural network that has been traine...
Similar publications
A communication system based on unmanned aerial vehicles (UAVs) is a viable alternative for meeting the coverage and capacity needs of future wireless networks. However, because of the limitations of UAV-enabled communications in terms of coverage, energy consumption, and flying laws, the number of studies focused on the sustainability element of U...
![Comparison of obstacle sensing solutions proposed in [66].](publication/356952908/figure/tbl1/AS:1099641827409940@1639186450877/Comparison-of-obstacle-sensing-solutions-proposed-in-66_Q320.jpg)
Unmanned aerial vehicles’ (UAVs) safety has gained great research interest due to the increase in the number of UAVs in circulation and their applications, which has inevitably also led to an increase in the number of accidents in which these vehicles are involved. The paper presents a classification of UAV safety solutions that can be found in the...
The unmanned aerial vehicle (UAV) is one of the mobile robots which has grown rapidly in popularity in recent years. UAVs have been used in various activities to convey important information on the aerial transportation system. However, an application to get real-time information from UAVs remains a challenging task. Therefore, this paper presents...
Unmanned aerial vehicle (UAV) is regarded as a powerful tool to expand the existing ground wireless network into aerial space. Since high mobility is an essential characteristic for UAV, it is important to carry out an accurate, real-time, and high-precision localization in terms of safe operation and communication link maintenance. The cellular ne...
Citations
... Wei et al. 2020 used multiple classifiers, such as convolutional neural networks, long shortterm memories, and recurrent neural networks, to categorize 3D hand movements. According to the findings, the CNN classifier performed the best, with an accuracy rate of 98.12% [13]. In conclusion, several optimization techniques, including E-Grasshopper Optimizer, Improved Grasshopper, Grasshopper OA, Adam, and SGD, have been suggested and evaluated using a variety of benchmark functions [24] . ...
________________________________________________________________________________________________________ Abstract: The Enhanced Grasshopper Optimizer (EGO) for the feature map optimization of 3D and depth map hand gestures is the objective of this paper's benchmarking experiment. Using a dataset of 3D and depth map hand gestures, the effectiveness of the EGO algorithm is examined and contrasted to alternative optimizers. The optimized feature map is tested using the Rosenbrock benchmark test function with EGO and SGD, the findings demonstrate that the EGO algorithm performs better than the alternative techniques in terms of precision and computational time. The execution time of EGO is also benchmarked in this study with the different numbers of input features and shows dominance in performing feature selection for 3D hand gesture detection and classification.
... Wei et al. 2020 used multiple classifiers, such as convolutional neural networks, long shortterm memories, and recurrent neural networks, to categorize 3D hand movements. According to the findings, the CNN classifier performed the best, with an accuracy rate of 98.12% [13]. In conclusion, several optimization techniques, including E-Grasshopper Optimizer, Improved Grasshopper, Grasshopper OA, Adam, and SGD, have been suggested and evaluated using a variety of benchmark functions [24] . ...
Abstract: The Enhanced Grasshopper Optimizer (EGO) for the feature map optimization of 3D and depth map hand gestures is the objective of this paper's benchmarking experiment. Using a dataset of 3D and depth map hand gestures, the effectiveness of the EGO algorithm is examined and contrasted to alternative optimizers. The optimized feature map is tested using the Rosenbrock benchmark test function with EGO and SGD, the findings demonstrate that the EGO algorithm performs better than the alternative techniques in terms of precision and computational time. The execution time of EGO is also benchmarked in this study with the different numbers of input features and shows dominance in performing feature selection for 3D hand gesture detection and classification.
... speed and control the UAV to move up, down, left, or right to avoid obstacles [16]. There are also some ways to extend the UAV's action space to 3D space [17,18]. For example, when the UAV is moving, it may move up, down, or obliquely. ...
This paper focuses on the continuous control of the unmanned aerial vehicle (UAV) based on a deep reinforcement learning method for a large-scale 3D complex environment. The purpose is to make the UAV reach any target point from a certain starting point, and the flying height and speed are variable during navigation. In this work, we propose a deep reinforcement learning (DRL)-based method combined with human-in-the-loop, which allows the UAV to avoid obstacles automatically during flying. We design multiple reward functions based on the relevant domain knowledge to guide UAV navigation. The role of human-in-the-loop is to dynamically change the reward function of the UAV in different situations to suit the obstacle avoidance of the UAV better. We verify the success rate and average step size on urban, rural, and forest scenarios, and the experimental results show that the proposed method can reduce the training convergence time and improve the efficiency and accuracy of navigation tasks. The code is available on the website https://github.com/Monnalo/UAV_navigation.
... Existing networks for classifying plant diseases and pests rely heavily on mature network architectures in computer vision, AlexNet [16], GoogleNet [17], and VGGNet [18]. CNNs, short for Convolutional Neural Networks, have a sophisticated network topology and are capable of performing convolutional operations [19]. ...
The technological revolution for farmers, especially for the safety of their crops from pests, plays evident change and convenience for the agriculture industry. The current research presented the classification of different types of pests using federated learning-based UAVs. The designed scenarios comprise four different sites connected with a global model where different parameters for these sites are received from the local model. State-of-the-art EfficientNet deep model with B03 configurations provides the best accuracy for classifying nine types of pests. The system is capable of achieving an accuracy of 99.55% with the augmentation of images into different degrees of angles. The federated learning designed UAVs have been found to be the most reliable connection with very less computation power during the classification of pests for the agriculture environment.
... Proportional Integral Derivates (PID) and fuzzy controllers help the aviation industry to design these technologies but with certain limitation such as professional knowledge for control, electronic noise from the remote controllers, sensor-based collision avoidance, etc. The hardware design mentioned in [2] utilizes the Inertial Measurement Unit (IMU) with the sensors for yaw, pitch and roll to provide the values to formulate the reward functions for the decision to mobilize the UAV. The best reward is estimated where after each episode a reset function is defined to learn the best path during training. ...
The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades. Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle (UAV) required maximum accuracy. In this paper, we designed a hybrid framework, which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures. The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient (DDPG) to receive the best reward and take actions according to 3D hand gestures input. The UAV consist of a Jetson Nano embedded testbed, Global Positioning System (GPS) sensor module, and Intel depth camera. The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function. The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives (PID) flight controller. There are six reward functions estimated for 2500, 5000, 7500, and 10000 episodes of training, which have been normalized between 0 to-4000. The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value. The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.
The escalating number of vehicles on the roads has exacerbated traffic congestion, presenting a significant and inevitable challenge for road users. Traffic congestion not only increases the travel time of road users, it also causes air pollution since more vehicles are stuck on the road. To address this issue, deep learning algorithms, including YOLOv5 and DeepSORT, have been leveraged to enable vehicle detection and estimate the number of vehicles through image processing. This study focuses on training a custom YOLOv5 dataset of vehicles and compares its performance with a pretrained YOLOv5 dataset in terms of feasibility for detecting and estimating the number of vehicles. In the proposed approach, YOLOv5 is employed to detect vehicles in video streams, DeepSORT is used for vehicle tracking and counting as they pass through the detection zone, and the number of vehicles in each lane is estimated with the aid of Supervision. The custom dataset's validation demonstrates promising results, with the precision curve indicating convergence for all classes at 97.4% precision and an 87% accuracy in predicting vehicle classes. Additionally, the precision-recall curve assesses the ability to detect individual vehicle categories, such as bus, car, motorcycle, and truck, with accuracies of 68.2%, 95.2%, 79.9%, and 70.1%, respectively. Furthermore, the overall accuracy for detecting all vehicle classes combined is 78.3%. The F1 curve indicates that the system achieves a confidence level of 30.9% F1 score, ensuring 78% confidence in accurately predicting all classes. Both the pretrained and custom datasets exhibit similar accuracy in counting the total number of vehicles passing through the detection zone as well as estimating the number of vehicles in each lane. However, it is evident that the custom dataset's performance can be further improved by incorporating more extensive and diverse datasets during the training process to enhance the accuracy of vehicle detection and estimation. In conclusion, the integration of deep learning algorithms, specifically YOLOv5 and DeepSORT, offers a promising solution for addressing traffic congestion Keywords Deep learning, YOLOv5, DeepSORT Online Journal for TVET Practitioners Vol. 0 No. 0 (YEAR) p. 1-6 2 by efficiently detecting and estimating vehicle numbers, which allow traffic systems to identify which lane is congested and prioritise ensuring the congested lane has a smooth traffic flow. Continued research with larger datasets can lead to further advancements and refined results in the field of traffic management and optimization.
