Fig 5 - uploaded by Raffaele Carli
Content may be subject to copyright.
Source publication
The fourth industrial revolution, also known as Industry 4.0, is reshaping the way individuals live and work while providing a substantial influence on the manufacturing scenario. The key enabling technology that has made Industry 4.0 a concrete reality is without doubt
collaborative robotics
, which is also evolving as a fundamental pillar of th...
Contexts in source publication
Context 1
... HRC applications, safety requirements are the primary need, as can be seen from the large number of articles focused on this concept, as highlighted in Fig. 3. For this reason, several control techniques and state-of-the-art control frameworks, schematized in Fig. 5, have been developed to meet the 'safety first' slogan in the digital industry. All the papers from the safety point of view are synthesized in this section outlining the relationships between ...
Context 2
... large amount of cobotics safety schemes rely on precollision systems, which aim at predicting the human intention, with the help of four classes of approaches: 1) learningbased techniques, 2) exteroceptive and proprioceptive sensors, 3) speed and separation monitoring and 4) power and force limiting (see Fig. 5), allowing the cobot to stop or modify its trajectory before impact ...
Context 3
... physical contact is required in HRC tasks. Therefore, learning-based methods and non-linear optimization problems (see Fig. 5) that provide safety by detecting collisions are developed to meet this ...
Context 4
... HR contacts, leveraging on the operator's motion prediction. The first part of this section deals with learning-based control and non-linear optimization problems, whereas the second one with model predictive control, probabilistic-based control, compliance control, reinforcement learning, admittance control and filter-based generation (see Fig. ...
Context 5
... sub-section includes all the works that aim at designing advanced controllers for a safe HRC without specifically referring to any of the control problems addressed in the previous sub-sections. The employed approaches are summarized in Fig. 5. They incorporate optimal control, MPC, learning-based control, AC/IC, sliding mode control (SMC), and compliance ...
Similar publications
Attracting and retaining newcomers are critical aspects for OSS projects, as such projects rely on newcomers sustainable contributions. Considerable effort has been made to help newcomers by identifying and overcoming the barriers during the onboarding process. However, most newcomers eventually fail and drop out of their projects even after succes...
The aim of change detection in remote sensing usually is not to find all differences between the observations, but rather only specific types of change, such as urban development, deforestation, or even more specialized categories like roadwork. However, often there are no large public datasets available for very fine-grained tasks, and to collect...
In this paper, we present a novel collaborative bidirectional style transfer network based on generative adversarial network (GAN) for cross modal facial image synthesis, possibly with large modality gap. We think that representation decomposed into content and style can be effectively exploited for cross modal facial image synthesis. However, we h...
Reinforcement learning can achieve excellent performance in the field of robotic grasping if the grasping target is stable. However, during applications in the real world, robot needs to overcome the effects of a complex working environment with different types of target objects, so it is more difficult to maintain the quality of action planning, e...
Referring segmentation aims to generate a segmentation mask for the target instance indicated by a natural language expression. There are typically two kinds of existing methods: one-stage methods that directly perform segmentation on the fused vision and language features; and two-stage methods that first utilize an instance segmentation model for...
Citations
... In the paradigm of industry 4.0, the robots in the automation process are expected to perform complex tasks like grasping, pick and place, and assembling in the manufacturing industry accurately using human robot collaboration (HRC) in a cyber physical environment [4,15,16]. The automated robotic manipulator with multiple degrees of freedom is a coupled system with non-linearity, parametric uncertainties, and disturbances [17][18][19]. ...
Position controlled industrial robots are used for trajectory tracking with fast and precise motion. The modelling and control technique in such a case depends on manipulator structure, material, servo control and inertial force. This paper proposes a scheme of fractional order modelling of a two-link manipulator (TLM) system with non-linearities, parametric uncertainties and disturbances, in joint space. A newly developed L1 adaptive control ( L1 AC) strategy is modified by introducing a fractional-order predictor and fractional order adaptation laws to achieve desired variations of joint angles of the TLM. The novelty of this paper lies in the fact that the proposed FO- L3 AC scheme works in synchronism with the FOTLM system to deal with the non-linearities, parametric uncertainties and disturbances during real-life experimentation. The stability of the overall close loop system is precisely guaranteed utilizing the Lyapunov theory, and all the closed-loop variables are bounded employing L1 norm-based conditions. Real-life experimental studies demonstrate the superiority of the proposed control strategy.
... The collaboration between humans and robots, also known as Human-Robot Collaboration (HRC), leads to the achievement of more efficient tasks with superior process quality and task optimization [23][24][25]. This efficiency can be attributed to the fact that, through collaboration with the robot, humans are motivated to maintain the pace set by it. ...
... The integration of collaborative robots has experienced continuous expansion, aiming to facilitate cooperation between humans and robotic entities within the industrial domain [9,25]. This evolution reflects the direction in which technology is heading towards a tighter and more efficient interaction between humans and robots in the production environment. ...
This scientific paper explores the increasingly widespread use of collaborative and industrial robots in the industrial environment, highlighting them as a solution to challenges related to the high costs of human labor and associated management difficulties. The authors focus on the process of defining requirements for the implementation of collaborative and industrial robots, providing strategies based on mathematical management models. This approach translates into significant benefits for companies, such as cost reduction, quality improvement, and increased operational efficiency. Additionally, the paper proposes an innovative mathematical model for assessing total costs, budgeting, profitability, and electric power consumption associated with the operation of collaborative and industrial robots. This model allows for a comparison between the costs involved in using human labor and those associated with collaborative and industrial robots, providing critical information for technological investment decisions. The efficiency of this mathematical model is demonstrated through a practical application, where collaborative robots were integrated into a production environment and costs and efficiency were evaluated compared to the use of human labor and industrial robots. This scientific paper provides a systematic and efficient approach to implementing collaborative robots in industrial processes, benefiting from strategies based on mathematical management models and an original mathematical model for evaluating performance and associated costs.
... Control systems and collision detection mechanisms are pivotal in safe collaboration [57,58]. Research focuses on AI applications controlling safety and ergonomic performance [59][60][61][62]. ...
This chapter explores the synopsis of the Industry 5.0 paradigm, focusing on Human-robot collaboration, encompassing critical elements from following the progression of evolution from Industry 4.0 to Industry 5.0 to the implementation of cutting-edge technologies and human-centric approaches within this framework. Industry 5.0 paradigm shift builds upon the foundation laid by Industry 4.0, with a renewed focus on integrating human intelligence and creativity with the capabilities of robots. The Operator of Industry 5.0 embodies the idea of skilled human operators working alongside automated systems to optimize performance and efficiency. Industry 5.0 technologies encompass collaborative robots (cobots) and advancements in robot learning, enabling safe and efficient collaboration between humans and machines and facilitating dynamic partnerships in shared workspaces. Human-centric approaches within Industry 5.0 technologies ensure that technological advancements align with human needs and preferences, fostering a work environment where humans and robots collaborate harmoniously. The concept of the Human Digital Twin offers a compelling instrument for identifying and optimizing human behavior within the context of Industry 5.0, enabling organizations to tailor processes and workflows to individual capabilities and preferences.
... More recent research focus on control strategies to improve pivotal goals of HRC, which are the efficiency, safety, and ergonomics [23], by the use of proactive strategies. The proactive strategies focus on providing a solution before any contact with the user happens. ...
Collaborative robots, designed to work alongside humans in industrial manufacturing, are becoming increasingly prevalent. These robots typically monitor their distance from workers and slow down or stop when safety thresholds are breached. However, this results in reduced task execution performance and safety-related uncertainty for the worker. To address these issues, we propose an alternative safety strategy, where the worker is responsible for their own safety and the robot executes its task without modifying its speed except in the case of imminent contact with the worker. The robot provides precise situation-awareness information to the worker using a mixed-reality display, presenting information about relative distance and movement intentions. The worker is then responsible for placing themselves with respect to the robot. A user study was conducted to evaluate the efficiency of task execution, worker safety, and user experience. Results suggest a good user experience and safety perception while maintaining worker safety, which would support social sustainability of human activities in industrial production contexts that require collaboration with robots.
... The collaboration between humans and robots, also known as Human-Robot Collaboration (HRC), leads to the achievement of more efficient tasks with superior process quality and task optimization [23][24][25]. This efficiency can be attributed to the fact that, through collaboration with the robot, humans are motivated to maintain the pace set by it. ...
... The integration of collaborative robots has experienced continuous expansion, aiming to facilitate cooperation between humans and robotic entities within the industrial domain [9,25]. This evolution reflects the direction in which technology is heading towards a tighter and more efficient interaction between humans and robots in the production environment. ...
This scientific paper explores the increasingly widespread use of collaborative robots in the industrial environment, highlighting them as a solution to challenges related to the high costs of human labour and the associated management difficulties. The authors focus on the process of defining requirements for the implementation of collaborative robots, providing strategies based on mathematical management models. This approach translates into significant benefits for companies, such as cost reduction, quality improvement, and increased operational efficiency. Additionally, the paper proposes an innovative mathematical model for assessing total costs, budgeting, profitability, and electric power consumption associated with the operation of collaborative robots. This model allows for a comparison between the costs involved in using human labour and those associated with collaborative robots, providing critical information for technological investment decisions. The efficiency of this mathematical model is demonstrated through a practical application, where collaborative robots were integrated into a production environment, and costs and efficiency were evaluated compared to the use of human labour. This scientific paper provides a systematic and efficient approach to implementing collaborative robots in industrial processes, benefiting from strategies based on mathematical management models and an original mathematical model for evaluating performance and associated costs.
... In their pursuit to enhance competitiveness and sustainability, companies are adopting new technological concepts to support their businesses and improve their performance and flexibility (Mukherjee et al., 2022;Özdemir and Hekim, 2018). The emergence of Industry 4.0 (I4.0) is driving the development of new technologies, which broadly integrates information and communication technologies into an industrial manufacturing environment (Proia et al., 2021;Villani et al., 2018). ...
The Industry 4.0 (I4.0) revolution has led to new concepts and transformations toward technological innovations. In the manufacturing sector, the use of collaborative robots (cobots) has significantly increased in the last few years, enabling them to work safely alongside humans in a shared workspace. Within this perspective, small- and medium-sized enterprises (SMEs) have been facing several challenges compared to large organisations regarding the adoption of cobots. Based on the literature, this paper aims to introduce a techno-economic feasibility model to evaluate the viability of using cobots in a shared workplace, with a focus on SMEs. Consistent with the paper’s aim, a conceptual model was developed, supported by experts’ opinions using the Delphi method. The results of this work incorporate contributions to both the academic and industrial communities.
... For this reason, novel methods must be built upon the safety module, enabling efficient and secure robot control. Researchers have investigated this problem at various levels, proposing adaptive task planners [37,146], motion planners [33,38,122], and controllers [29,63,134]. ...
In recent years, there has been a significant increase in robots sharing workspace with human operators, combining the speed and precision inherent to robots with human adaptability and intelligence. However, this integration has introduced new challenges in terms of safety and collaborative efficiency. Robots now need to swiftly adjust to dynamic changes in their environment, such as the movements of operators, altering their path in real-time to avoid collisions, ideally without any disruptions. Moreover, in human-robot collaborations, replanned trajectories should adhere to safety protocols, preventing safety-induced slowdowns or stops caused by the robot's proximity to the operator.
In this context, quickly providing high-quality solutions is crucial for ensuring the robot's responsiveness. Conventional replanning techniques often fall short in complex environments, especially for robots with numerous degrees of freedom contending with sizable obstacles.
This thesis tackles these challenges by introducing a novel sampling-based path replanning algorithm tailored for robotic manipulators. This approach exploits pre-computed paths to generate new solutions in a few hundred milliseconds. Additionally, it integrates a cost function that steers the algorithm towards solutions that comply with the ISO/TS 15066 safety standard, thereby minimizing the need for safety interventions and fostering efficient cooperation between humans and robots. Furthermore, an architecture for managing the replanning process during the execution of the robot's motion is introduced. Finally, a software tool is presented to streamline the implementation and testing of path replanning algorithms.
Simulations and experiments conducted on real robots demonstrate the superior performance of the proposed method compared to other popular techniques.
... Robot control Humanoid control represents a strong type of manipulation of humanoids or external objects, where a humanoid influences, directs or manages its behaviors, actions or their processes. The objectives and tasks of robot control are varied [38]. A robot may control its parts such as head, eyes, emotion, gait, legs and hands. ...
... Humanoid ethics Robot ethics 38 [20] concerns about the privacy, manipulation, opacity and bias of robotic systems and the equilibrium effect and consequence of robotic designs, mechanisms (e.g., autonomy and predictive decisionmaking) and behaviors during operations, decision-making and human-robot interaction, etc. Ethical robots are built with transparent, fair and unbiased design and decision-making; proactive compliance, due process and auditing to potential effects, influences, vulnerability, deception, misinformation, synthetic issues, failures, changes and uncertainty; and accountable compliance, interference and intervention measures and mechanisms. Humanoid robots may further involve humane aspects such as confirmation bias, deception, malicious design, attack and manipulation. ...
In the approximately century-long journey of robotics, humanoid robots made their debut around six decades ago. The rapid advancements in generative AI, large language models (LLMs), and large multimodal models (LMMs) have reignited interest in humanoids, steering them towards real-time, interactive, and multimodal designs and applications. This resurgence unveils boundless opportunities for AI robotics and novel applications, paving the way for automated, real-time and humane interactions with humanoid advisers, educators, medical professionals, caregivers, and receptionists. However, while current humanoid robots boast human-like appearances, they have yet to embody true humaneness, remaining distant from achieving human-like intelligence. In our comprehensive review, we delve into the intricate landscape of AI robotics and AI humanoid robots in particular, exploring the challenges, perspectives and directions in transitioning from human-looking to humane humanoids and fostering human-like robotics. This endeavour synergizes the advancements in LLMs, LMMs, generative AI, and human-level AI with humanoid robotics, omniverse, and decentralized AI, ushering in the era of AI humanoids and humanoid AI.
... Following an internal discussion, articles addressing the previously mentioned topics were incorporated exclusively if related studies were deemed highly relevant or had broad applicability. The articles that remain after undergoing this filtering process are recorded in the reference list (from (Kopp et al., 2022;Mukherjee et al., 2022;Simões et al., 2022;Borges et al., 2022;Pinheiro et al., 2022;Quinlan-Smith, 2022;Č orňák et al., 2021;Dzedzickis et al., 2021;Ortenzi et al., 2021;Salm-Hoogstraeten and Müsseler, 2021;Khamaisi et al., 2021;Hancock et al., 2021;Schoeller et al., 2021;Selvaggio et al., 2021;Cini et al., 2021;Sarthou et al., 2021;Weiss et al., 2021;Diamantopoulos and Wang, 2021;Bolano et al., 2021;Li et al., 2021a;Dimitropoulos et al., 2021;Castro et al., 2021;Chacón et al., 2021;Grushko et al., 2021;Pollak et al., 2021;Li et al., 2021b;Rossato et al., 2021;Käppler et al., 2020;Rothstein et al., 2020;Hannum et al., 2020;Mizrahi et al., 2020) to (Beschi et al., 2020;Bhalaji et al., 2021;Bounouar et al., 2022;Bounouar et al., 2020;Buxbaum et al., 2020;Chacón et al., 2020;Colim et al., 2020;Colim et al., 2021;Cunha et al., 2020;Dehkordi et al., 2021;Fischer and Sträter, 2020;Fruggiero et al., 2020;Hagenow et al., 2021;Han et al., 2021;Komenda et al., 2021;Lasota and Shah, 2015;Messeri et al., 2020;Prati et al., 2021b;Proia et al., 2021;Ramaraj, 2021;Subrin et al., 2019;Dani et al., 2020;Abrams and der Pütten, 2020;Gyöngyössy et al., 2020;Domonkos et al., 2020;Antonelli et al., 2021;Baltrusch et al., 2021)). The PRISMA flowchart (Page et al., 2021), which summarizes the abovementioned systematic review, is presented in Fig. 1. ...
... Internet of things (IoT) provided a feasible solution to implement reconfigurable manufacturing systems over the internet, so Lesi et al. [18] adopted control interpreted Petri nets to formalize a discrete event dynamic system and verify system activities. Proia et al. [19] reviewed collaborative technologies in Industry 4.0 from control perspective; they identified some critical needs to develop innovative models and methodologies to implement ergonomic, efficient, and safe human-robotcollaborations. DT-like technologies were adopted to (1) assist robotic welding in which human's intentions of welding operations were recognized and considered the closed-loop control of a welding process [20] and (2) control an adaptive Convery system by range-inspect controls [21]. Liu et al. [22] investigated the challenges in allocating resources in cloud manufacturing for maximized resource utilization and minimized energy consumption, and they used the game theory to solve multi-objective problems. ...
In this paper, the concept of Sustainable Manufacturing (SM) is discussed, and the focus is put on the elimination of wastes in a product’s life cycle. Recent development on enabling technologies to advance SM are surveyed to identify promising research areas. We have found virtual
Verification and Validation
(V&V) should be promoted to enhance the sustainability especially in
Small and Medium sized Enterprises
(SMEs). V&V are typically non-value-added and the effects on V&V should be minimized; while due to lack of expertise, most of SMEs rely heavily on prototyping and physical experiments to evaluate their products. We propose virtual V&V to replace physical experiments to the maximum extent. To show the significance of the proposed concept, a case study of virtual V&V system is developed to reduce the needs of physical prototyping and testing in product development. This benefits greatly to (1) cost savings by replacing numerous physical prototyping and testing by virtual V&V, (2) lead-time reduction for new product to enter emerging markets, and (3) global optimization of product design by analyzing and exploring a large number of design options. The improvement at these aspects contributes to system sustainability significantly. The concept of using virtual V&V to reduce non-value-added prototyping and testing is applicable to manufacturing businesses in most of SMEs who design and test their own products.
Note to Practitioners
—This work is highly motivated by a number of the authors’ industry projects with regional SMEs who put heavy investments in testing to prove products’ quality to clients before the orders for products can be awarded; manufacturing businesses related to testing are non-value-added that should be minimized from the perspective of sustainability. Virtual V&V is proposed as a vital solution to overcome their dilemma, and the proposed solution has its theoretical and practical significance to reduce wastes, shorten lead-times, and optimize products based on parametric study for a wide scope of design alternatives. This helps to increase the lifespan of SMEs ultimately.
