Safety Of Human Operators Research Articles

Near Time-Optimal Trajectories with ISO Standard Constraints for Human–Robot Collaboration in Fabric Co-Transportation

Enabling robots to work safely close to humans requires both adherence to safety standards and the development of appropriate strategies to plan and control robot movements in accordance with human movements. Collaboration between humans and robots in a shared environment is a joint activity aimed at completing specific tasks, requiring coordination, synchronisation, and sometimes physical contact, in which each party contributes its own skills and resources. Among the most challenging tasks of human–robot cooperation is the co-transport of deformable materials such as fabrics. This paper proposes a method for generating the trajectory of a collaborative manipulator. The method is designed for the co-transport of materials such as fabrics. It combines a near time-optimal control strategy that ensures responsiveness in following human actions while simultaneously guaranteeing compliance with the safety limits imposed by current regulations. The combination of these two elements results in a viable co-transport solution which preserves the safety of human operators. This is achieved by constraining the path of the robot trajectory with prescribed velocities and accelerations while simultaneously ensuring a near time-optimal control strategy. In short, the robot movement is generated in such a way as to ensure both the tracking of humans in the co-transportation task and compliance with safety limits. As a first attempt to adopt the proposed approach to integrate time-optimal strategies into human–robot interaction, the simulations and preliminary experimental result obtained are promising.

Deep reinforcement learning based proactive dynamic obstacle avoidance for safe human-robot collaboration

Ensuring the health and safety of human operators is paramount in manufacturing, particularly in human-robot collaborative environments. In this paper, we present a deep reinforcement learning-based trajectory planning method for a robotic manipulator designed to avoid collisions with human body parts in real-time while achieving its goal. We modelled the human arm as a freely moving cylinder in 3D space and formulated the dynamic obstacle avoidance problem as a Markov decision process. The algorithm was tested in a simulated environment that closely mimics our laboratory environment, with the goal of training a deep reinforcement learning model for autonomous task completion. A composite reward function was developed to balance the effects of different environmental variables, and the soft-actor critic algorithm was employed. The trained model demonstrated a 93% success rate in avoiding dynamic obstacles while achieving its goals when tested on a generated data set.

Localization of hotspots via a lightweight system combining Compton imaging with a 3D lidar camera

Efficient and secure decommissioning of nuclear facilities demands advanced technologies. In this context, gamma-ray detection and imaging are crucial in identifying radioactive hotspots and monitoring radiation levels. Our study is dedicated to developing a gamma-ray detection system tailored for integration into robotic platforms for nuclear decommissioning, offering a safe and automated solution for this intricate task and ensuring the safety of human operators by mitigating radiation exposure and streamlining hotspot localization.Our approach integrates a Compton camera based 3D reconstruction algorithm with a single Timepix3 detector. This eliminates the need for a second detector and significantly reduces system weight and cost. Additionally, combining a 3D camera with the setup enhances hotspot visualization and interpretation, rendering it an ideal solution for practical nuclear decommissioning applications.In a proof-of-concept measurement utilizing a 137Cs source, our system accurately localized and visualized the source in 3D with an angular error of 1° and estimated the activity with a 3% relative error. This promising result underscores the system's potential for deployment in real-world decommissioning settings. Future endeavors will expand the technology's applications in authentic decommissioning scenarios and optimize its integration with robotic platforms.The outcomes of our study contribute to heightened safety and accuracy for nuclear decommissioning works through the advancement of cost-effective and efficient gamma-ray detection systems.

Adaptive technique for physical human–robot interaction handling using proprioceptive sensors

The work focuses on the development of an adaptive technique for the physical interaction handling between a human and a robot, as well as its experimental validation. The proposed technique is based on the deep residual neural network and dedicated finite state machine, where the states are the robot behavior modes and transitions are the switchings between the states that depend on the interaction parameters and characteristics. It ensures the human operator safety and improves the human–robot collaboration performance by implementing various scenarios. In the scope of this technique, the parameters of human–robot interaction are used to select an appropriate robot reaction strategy using data from internal robot sensors only, i.e. proprioceptive sensors. These parameters define the interaction force vector and its application point on the robot surface, which allow to classify the interaction within the set of predefined categories. This classification distinguishes interactions applied at the tool or intermediate link (Tool/Link), having soft or hard nature (Soft/Hard), as well as having different intention (Intl/Accd) or duration (Short/Long). Based on identified category and the current robot state, the algorithm chooses an appropriate robot reaction. To confirm the efficiency the developed technique, an experimental study was conducted, which involved the collaboration between the real industrial manipulator KUKA LBR iiwa and the human operator.

Task allocation model for human-robot collaboration with variable cobot speed

New technologies, such as collaborative robots, are an option to improve productivity and flexibility in assembly systems. Task allocation is fundamental to properly assign the available resources. However, safety is usually not considered in the task allocation for assembly systems, even if it is fundamental to ensure the safety of human operator when he/she is working with the cobot. Hence, a model that considers safety as a constraint is here presented, with the aim to both maximize the productivity in a collaborative workcell and to promote a secure human robot collaboration. Indexes that consider both process and product characteristics are considered to evaluate the quality of the proposed model, which is also compared with one without the safety constraint. The results confirm the validity and necessity of the newly proposed method, which ensures the safety of the operator while improving the performance of the system.

Fine-tuned RetinaNet models for Vision-based Human Presence Detection

Moving towards Industry 4.0, the idea of human-robot interaction (HRI) and human-robot collaboration (HRC) has been popularized. To introduce more robots into the industries, risk-correlated issues would be always on the hook as robots are not as flexible as human. In fact, although robots can replace human workers in some of the dangerous tasks, still human safety is always the top priority for all industries. The most common way to safeguard the human was to isolate the working space of human workers and robots. To realize the idea of Industry 4.0, it is postulated to have the robots and cobots out of the cage to maximize productivity and efficiency. Hence, studies have been conducted with the attempts to free the robots from the isolated working space while preserve the safety of human operators. The present study seeks to explore the feasibility of transfer learning strategy — fine-tuning to human presence detection tasks as the base of practicing safe HRI. A custom image dataset with 1463 images was collected and separated into train, validation, and test set with a ratio of 70:20:10. Three RetinaNet object detection models with different backbone networks were fine-tuned with the acquired dataset to transfer the knowledge learned from source domain to the target domain, which is the human presence detection tasks. The result has shown that the RetinaNet_ResNet152-V1-FPN has the highest test AP of 74.4% with an inference speed of 13.09 FPS, suggesting that it is the best fine-tuned RetinaNet models. This study has demonstrated the feasibility of using fine-tuning as the strategy to train the object detection models, which can possibly act as the base for improving HRI applications via a deep learning visual-based method. In summary, the research has signified the uses of deep learning models to perform human presence detections and can be further extended for HRI safety applications.

Fault tolerant control of a permanent magnet synchronous machine using multiple constraints Takagi-Sugeno approach

Introduction. Fault diagnosis, and fault tolerant control issues are becoming very important to ensure a good supervision of systems and guarantee the safety of human operators and equipments even if system complexity increases. Problem. In fact, the presence of faults in actuators, sensors and processes can lead to system performance degradation, system breakdown, economic loss, and even disastrous situations. Furthermore, Actuator saturation or control input saturation is probably the most usual nonlinearity encountered in control engineering because of the physical impossibility of applying unlimited control signals and/or safety constraints. Purpose. This article is dedicated to the problem of fault tolerant control for constrained nonlinear systems described by a Takagi-Sugeno model. One of the interests of this type of models is the possibility of extend some tools and methods from linear system case to the nonlinear one. The novelty of the work consists in developing a fault tolerant control algorithm for a nonlinear Permanent Magnet Synchronous Machine model using an observer based state-feedback control technique in order to enhance fault and state estimation despite actuator saturation and system disturbances. Methods. Indeed a sensor fault detection observer based residual generator is synthesized with a guaranteed L2 performance to attenuate the external disturbances effect from one side and to maximize the residual sensitivity to faults from the other side. Based on Lyapunov function, design conditions are formulated in terms of Linear Matrix Inequalities to ensure stability of the global system. Practical value. A detailed study concerning nonlinear permanent magnet synchronous machine model, which is consolidated by simulation results, is conducted to show the used algorithm’s effectiveness guarantying fault estimation and reconfiguration of the control law to maintain stable performance even in the presence of actuator faults, external perturbation and the phenomenon of actuator saturation.

Analysis of Mass Concentration and Morphology of Fume Particles during ECDM of CFRP Composites

Electrochemical discharge machining (ECDM) is a hybrid method used to generate micro-features in hard and brittle materials (glass, ceramics, and composites) in aerospace, microelectromechanical systems (MEMS), and microfluidic applications. A significant improvement was observed in ECDM process but the effect of the process on the health of working operator are rarely investigated. Sustainability in manufacturing is a major concern for a better environment and safety of human operators. In this paper, analysis of fumes mass concentration (FMC), size and morphology of fume particles, and composition of fume particles along with their biological effects are studied during ECDM of CFRP composites. FMC was calculated by varying the concentration of electrolyte from 20 to 50% and duty cycle from 60 to 90% for a fixed sampling duration of 30 minutes. SEM images indicated the presence of spherical, irregular, and loosely packed fumes particles in the fumes generated during machining. EDS was also performed to study the chemical composition of fumes particles.

Safety assurance in human-robot collaborative systems: A survey in the manufacturing industry

Human-robot collaborative systems have emerged as a solution that aims to satisfy the current demand of highly personalized products by combining the skills of humans and robots within a shared workspace. However, the safety of human operators is of major concern when located next to a robotic companion. The objective of this article is to present a general outlook of safety assurance practices in current collaborative systems of the manufacturing industry. In this sense, the integration of safety standards and technologies is analyzed. A favoring tilt to techno-centered practices is spotted, where policies designed for rigid automation are being used for collaborative systems alike. This brings additional risks to the wellbeing of human operators. Consequently, a human-centered approach is highlighted as the ultimate level of safety compliance.

Latest Advances in Development of Smart Phase Change Material for Soft Actuators

Inspired from the nature, soft actuators have been attracting the incremental attention on account of the benefits in terms of high flexibility and safety for human operators, but material selection and manufacturing process remain challenging. Compared with the conventional actuators in solid state, smart phase change materials (PCMs) are superior for the soft actuation applications because of the capability to change their shapes or properties in response to a wide range of stimulants, such as heat, light, pH, or electrical field. This review provides a comprehensive analysis of smart PCM applications on soft actuators, including metal alloys and their polymer counterparts, shape memory materials and liquid crystalline polymers. Such materials generally exhibit large deformation degrees, high complexity in movement and diverse versatility, which are compliant and well suited for soft actuators in the vast applications of soft mechatronics and robots. Since stiffness variable plays a significant role on actuator transformation, this review focuses on smart materials with an emphasis on the different forms of phase transformation among solid, liquid, and gas phase. This review enables a better understanding of phase transformation, performances, and limitations of smart PCMs, and provides insights into the potential applications for soft actuators.

Fault detection strategy combining NARMAX model and Bhattacharyya distance for process monitoring

The complexity of modern chemical and petrochemical plants is becoming increasingly problematic in the recent years. At the same time, the demands to ensure safety and reliability of process operations rise. Early detection of abnormal event in complex real systems decrease maintenance cost and lead to guarantee the safety of human operators and environment. In the present work, a fault detection (FD) method which exploits the advantages of black-box modeling and statistical measure for fault detection in real chemical process as a distillation column is proposed. This technique is developed by applying the Nonlinear Auto-Regressive Moving Average with eXogenous input (NARMAX) model and Bhattacharyya distance (BD). In order to determine the NARMAX model, a real data set recorded during normal operations is used. Then, the BD is used to quantify on-line the dissimilarity between the current and reference probability distributions of the residual obtained from the NARMAX model for fault detection purposes. The ability of the proposed FD approach is demonstrated using real fault of separation unit. The obtained results indicate that the developed technique produces favorable performance compared to the conventional Cumulative Sum (CUSUM) test.

A Multimodal Approach to Human Safety in Collaborative Robotic Workcells

This article investigates the problem of controlling the speed of robots in collaborative workcells for automated manufacturing. The solution is tailored to robotic cells for cooperative assembly of aircraft fuselage panels, where only structural elements are present and robots and humans can share the same workspace, but no physical contact is allowed, unless it happens at zero robot speed. The proposed approach addresses the problem of satisfying the minimal set of requirements of an industrial human–robot collaboration (HRC) task: precision and reliability of human detection and tracking in the shared workspace; correct robot task execution with minimum cycle time while assuring safety for human operators. These requirements are often conflicting with each other. The former does not only concern with safety only but also with the need of avoiding unnecessary robot stops or slowdowns in case of false-positive human detection. The latter, according to the current regulations, concerns with the need of computing the minimum protective separation distance between the human operator and the robots by adjusting their speed when dangerous situations happen. This article proposes a novel fuzzy inference approach to control robot speed enforcing safety while maximizing the level of productivity of the robot minimizing cycle time as well. The approach is supported by a sensor fusion algorithm that merges the images acquired from different depth sensors with those obtained from a thermal camera, by using a machine learning approach. The methodology is experimentally validated in two experiments: the first one at a lab-scale and the second one performed on a full-scale robotic workcell for cooperative assembly of aeronautical structural parts. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This article discusses a way to handle human safety specifications versus production requirements in collaborative robotized assembly systems. State-of-the-art (SoA) approaches cover only a few aspects of both human detection and robot speed scaling. The present research work proposes a complete pipeline that starts from a robust human tracking algorithm and scales the robot speed in real time. An innovative multimodal perception system composed of two depth cameras and a thermal camera monitors the collaborative workspace. The speed scaling algorithm is optimized to take on different human behaviors during less risky situations or more dangerous ones to guarantee both operator safety and minimum production time with the aim of better profitability and efficiency for collaborative workstations. The algorithm estimates the operator intention for real-time computation of the minimum protective distance according to the current safety regulations. The robot speed is smoothly changed for the psychological advantages of operators, both in the case of single and multiple workers. The result is a complete system, easily implementable on a standard industrial workcell.

Co-Simulation of Human-Robot Collaboration: from Temporal Logic to 3D Simulation

Human-Robot Collaboration (HRC) is rapidly replacing the traditional application of robotics in the manufacturing industry. Robots and human operators no longer have to perform their tasks in segregated areas and are capable of working in close vicinity and performing hybrid tasks -- performed partially by humans and by robots. We have presented a methodology in an earlier work [16] to promote and facilitate formally modeling HRC systems, which are notoriously safety-critical. Relying on temporal logic modeling capabilities and automated model checking tools, we built a framework to formally model HRC systems and verify the physical safety of human operator against ISO 10218-2 [10] standard. In order to make our proposed formal verification framework more appealing to safety engineers, whom are usually not very fond of formal modeling and verification techniques, we decided to couple our model checking approach with a 3D simulator that demonstrates the potential hazardous situations to the safety engineers in a more transparent way. This paper reports our co-simulation approach, using Morse simulator [4] and Zot model checker [14].

Validation of Trade-Off in Human–Automation Interaction: An Empirical Study of Contrasting Office Automation Effects on Task Performance and Workload

Automation aims to improve the task performance and the safety of human operators. The success of automation can be facilitated with well-designed human–automation interaction (HAI), which includes the consideration of a trade-off between the benefits of reliable automation and the cost of Failed automation. This study evaluated four different types of HAIs in order to validate the automation trade-off, and HAI types were configured by the levels and the statuses of office automation. The levels of automation were determined by information amount (i.e., Low and High), and the statues were decided by automation function (i.e., Routine and Failed). Task performance including task completion time and accuracy and subjective workload of participants were measured in the evaluation of the HAIs. Relatively better task performance (short task completion time and high accuracy) were presented in the High level in Routine automation, while no significant effects of automation level were reported in Failed automation. The subjective workload by the National Aeronautics and Space Administration (NASA) Task Load Index (TLX) showed higher workload in High and Failed automation than Low and Failed automation. The type of sub-functions and the task classification can be estimated as major causes of automation trade-off, and dissimilar results between empirical and subjective measures need to be considered in the design of effective HAI.

A Safe and Energy Efficient Robotic System for Industrial Automatic Tests on Domestic Appliances: Problem Statement and Proof of Concept

In this paper, the design and the development of a robotic platform conceived to perform accelerated life tests on a newly manufactured domestic appliances is presented. The proposed system aims at improving the safety of human operators that share the workspace with the robotic platform which is a common scenario of test laboratories. A deep learning algorithm is used for the human detection and pose estimation, while the integration between a conventional motion planning algorithm with a fast 3D collision checker has been implemented as a global planner plugin for the ROS navigation stack. With the twofold objective of improving safety and saving energy in the battery-powered mobile manipulator used in this project, the problem of minimizing the overall kinetic energy is addressed through a properly designed task priority controller, in which the manipulator inertia matrix is used to weight the joint speeds while satisfying multiple robotic tasks according to a hierarchy designed to interact with the appliances while preserving the safety of the human operators. Simulations are carried out to evaluate the overall control architecture and preliminary results indicate the effectiveness of the developed system in the test laboratory floors.

A simulation-based approach for time allowances assessment during production system design with consideration of worker’s fatigue, learning and reliability

Health and safety of human operators in production systems is tightly linked to overall work system design. Well-designed production systems must grant adequate allowances to operators, to cope with the variability of predictable situations, whether normal or not. In this article, time allowances concept is presented from two standpoints: industrial engineering and occupational risk prevention field. This is followed by an introduction of a new time allowances indicator. Combined with an agent-based simulation model, this indicator can be used to assess time allowances in a given work organization during its design process. The proposed model integrates worker’s fatigue, learning and reliability as relevant human factors. To uphold the article proposal, three production system configurations are investigated: a classical production line designed based on Ford work paradigm, a cellular configuration with autonomous breaks, inspired from Volvo Uddevalla plant and finally, a hybrid configuration, cellular with planned breaks. The simulations showed that cellular configuration with autonomous breaks grants to operators the time allowances they need to carry out their work activity safely and efficiently.

Design and Modeling of a Compliant Link for Inherently Safe Corobots

In this paper, we propose a variable width compliant link that is designed for optimal trade-off of safety and control performance for inherently safe corobots. Intentionally introducing compliance to mechanical design increases safety of corobots. Traditional approaches mostly focus on the joint compliance, while few of them study the link compliance. Here, we propose a novel method to design compliant robotic links with a safety constraint which is quantified by head injury criterion (HIC). The robotic links are modeled as two-dimensional beams with a variable width. Given a safety threshold, i.e., HIC constraint, the width distribution along the link is optimized to give a uniform distribution of HIC, which guarantees inherent safety for human operators. This solution is validated by a human–robot impact simulation program built in matlab. A static model of the variable width link is derived and verified by finite element simulations. Not only stress in the link is reduced, this new design has a better control and dynamic performance quantified by a larger natural frequency and a larger bandwidth compared with designs made of uniform beams and compliant joints (CJs). The proposed variable width link takes full advantage of the link rigidity while keeps inherent safety during a human–robot impact. This paper demonstrates that the compliant link solution could be a promising alternative approach for addressing safety concerns of human–robot interactions.

Intelligent Multisensor Prodder for Training Operators in Humanitarian Demining.

Manual prodding is still one of the most utilized procedures for identifying buried landmines during humanitarian demining activities. However, due to the high number of accidents reported during its practice, it is considered an outmoded and risky procedure and there is a general consensus about the need of introducing upgrades for enhancing the safety of human operators. With the aim of contributing to reduce the number of demining accidents, this paper presents an intelligent multisensory system for training operators in the use of prodders. The proposed tool is able to provide to deminers useful information in two critical issues: (a) the amount of force exerted on the target and if it is greater than the safe limit and, (b) to alert them when the angle of insertion of the prodder is approaching or exceeding a certain dangerous limit. Results of preliminary tests show the feasibility and reliability of the proposed design and highlight the potential benefits of the tool.

Towards Flexibility in Future Industrial Manufacturing: A Global Framework for Self-organization of Production Cells

The future of manufacturing leads to flexible industrial facilities in which production lines or systems are composed by several production cells. Production cells can be reorganized and reconfigured by introducing new devices, equipment, functionalities or even by re-configuring the communication network. In this context, machine-to-machine communication does not only provide a transport layer for monitoring and control, but also provide a high-level distributed service framework and data management system. In this contribution, the authors address the challenge to manage the self-organization of production cells by means of a global framework. This framework bases on the following technologies: RobotML for the scenario description, OPC UA for service orchestration, object memories for distributed data sharing, Frama-C/Para-C for code verification and SDN for network reconfiguration. This framework has been deployed within a use case involving the SYBOT collaborative robot and a reconfigurable Raspberry-Pi based camera to enhance human operator safety. Experiments show that from a high-level description of the scenario, it was possible to automatically orchestrate at the OPC UA level the different reconfigurations of the production cell.

Accurate sensorless lead-through programming for lightweight robots in structured environments

Nowadays, programming an industrial manipulator is a complex and time-consuming activity, and this prevents industrial robots from being massively used in companies characterized by high production flexibility and rapidly changing products. The introduction of sensor-based lead-through programming approaches (where the operator manually guides the robot to teach new positions), instead, allows to increase the speed and reduce the complexity of the programming phase, yielding an effective solution to enhance flexibility. Nevertheless, some drawbacks arise, like for instance lack of accuracy, need to ensure the human operator safety, and need for force/torque sensors (the standard devices adopted for lead-through programming) that are expensive, fragile and difficult to integrate in the robot controller. This paper presents a novel approach to lead-through robot programming. The proposed strategy does not rely on dedicated hardware since torques due to operator's forces are estimated using a model-based observer fed with joint position, joint velocity and motor current measures. On the basis of this information, the external forces applied to the manipulator are reconstructed. A voting system identifies the largest Cartesian component of the force/torque applied to the manipulator in order to obtain accurate lead-through programming via admittance control. Finally an optimization stage is introduced in order to track the joint position displacements computed by the admittance filter as much as possible, while enforcing obstacle avoidance constraints, actuation bounds and Tool Centre Point (TCP) operational space velocity limits. The proposed approach has been implemented and experimentally tested on an ABB dual-arm concept robot FRIDA.