Human-robot interaction (HRI) is the future of robotics. It is essential in the expanding markets, such as surgical, medical, and therapy robots. However, existing industrial systems can also benefit from safe and effective HRI. Many robots are now being fitted with joint torque sensors to enable effective human-robot collision detection. Many existing and off-the-shelf industrial robotic systems are not equipped with these sensors. This work presents and demonstrates a method for effective collision detection on a system with motor current feedback instead of joint torque sensors. The effectiveness of this system is also evaluated by simulating collisions with human hands and arms. Joint torques are estimated from the input motor currents. The joint friction and hysteresis losses are estimated for each joint of an SIA5D 7 Degree of Freedom (DOF) manipulator. The estimated joint torques are validated by comparing to joint torques predicted by the recursive application of Newton-Euler equations. During a pick and place motion, the estimation error in joint 2 is less than 10 Newton meters. Acceleration increased the estimation uncertainty resulting in estimation errors of 20 Newton meters over the entire workspace. When the manipulator makes contact with the environment or a human, the same technique can be used to estimate contact torques from motor current. Current-estimated contact torque is validated against the calculated torque due to a measured force. The error in contact force is less than 10 Newtons. Collision detection is demonstrated on the SIA5D using estimated joint torques. The effectiveness of the collision detection is explored through simulated collisions with the human hands and arms. Simulated collisions are performed both for a typical pick and place motion as well as trajectories that transverse the entire workspace. The simulated forces and pressures are compared to acceptable maximums for human hands and arms. During pick and place motions with vertical and lateral end effector motions at 10mm/s and 25mm/s, the maximum forces and pressures remained below acceptable levels. At and near singular configurations some collisions can be difficult to detect. Fortunately, these configurations are generally avoided for kinematic reasons. / text

Les systèmes s’adaptant à leur environnement et en interaction physique avec l’homme se développent de plus en plus dans des domaines comme le médical, l’assistance aux personnes ou le travail en usine. Ils diffèrent des systèmes classiques par leur capacité à s’adapter à l’environnement et à prendre des décisions en tenant compte de leur perception de l’environnement et notamment de l’homme. La défaillance de tels systèmes pouvant avoir des conséquences catastrophiques sur l’homme, l’analyse et la démonstration du niveau de confiance que l’ont peut leur accorder vis-à-vis de la sécurité-innocuité, et a fortiori leur certification, constituent aujourd’hui un vrai défi. La construction d’argumentaire de sécurité (ou dossier de sécurité, ou safety case), est un des moyens permettant de préparer la certification de tels systèmes. Il s’agit principalement de justifier pour chaque danger comment il a été traité et ramené à un niveau acceptable. Malheureusement, dans le cas des systèmes robotiques, de nombreuses incertitudes subsistent, et il n’existe pas à l’heure actuelle de méthode systématique permettant la construction de tels dossiers de sécurité et la démonstration du niveau de confiance sous-jacent. L’objectif des travaux est de contribuer à la définition d’une telle méthode en partant d’une technique d’analyse du risque dédiée à l’analyse des interactions humain-robot, puis en s’appuyant sur des modèles formalisés de construire l’argumentaire de sécurité et d’évaluer automatiquement le niveau de confiance dans cet argumentaire. / Robotic systems that continuously adapt to their environment and physically interact with human are increasingly used in various fields like personal assistance or factory work. They are characterised by their ability to adapt to the environment, to take decision in the light of their perception of the environment and particularly of the human. As the failure of such systems may lead to catastrophic consequences, analysis and justification of the level of confidence in these systems with regards to safety, and furthermore their certification is a real challenge. The construction of a Safety Case is one of the means that can be used to support the certification of such systems. It is aimed at describing and justifying how every hazard has been mitigated and its severity maintained as low as reasonably possible. However, for robotic systems that have to deal with many uncertainties, there is a lack of a systematic approach to support the construction of their Safety Case and the assessment of its underlying confidence. Our research aims at contributing to the development of such a systematic approach starting with a risk analysis focusing on human-robot interactions, followed by Safety Case construction from formalized models and finally an automatic assessment of the confidence in safety argumentation. As a case study, the safety of a rehabilitation robot for strolling is analysed and justified based on the approaches developed in this thesis.

This study presents a procedure for the estimation of stopping behavior of industrial robots with a trained neural network. This trained network is presented as a single channel in a redundant architecture for safety control applications, where its potential for future integration with an analytical model of robot stopping is discussed. Basic physical relations for simplified articulated manipulators are derived, which motivate a choice of quantities to predict robot stopping behavior and inform the training and testing of a network for prediction of stopping distances and times. Robot stopping behavior is considered in the context of relevant standards ISO 10218-1, ISO/TS 15066 and IS0 13849-1, which inform the definitions for safety related stopping distances and times used in this study. Prior work on the estimation of robot stopping behavior is discussed alongside applications of machine learning to the broader field of industrial robotics, and particularly to the cases of prediction of forward and inverse kinematics with trained networks. A state-driven data collection program is developed to perform repeated stopping experiments for a controlled stop on path within a specified sampling domain. This program is used to collect data for a simulated and real robot system. Special attention is given to the identification of meaningful stopping times, which includes the separation of stopping into pre-deceleration and post-deceleration phases. A definition is provided for stopping of a robot in a safety context, based on the observation that residual motion over short distances (less than 1 mm) and at very low velocities (less than 1 mm/s) is not relevant to robot safety. A network architecture and hyperparameters are developed for the prediction of stopping distances and times for the first three joints of the manipulator without the inclusion of payloads. The result is a dual-network structure, where stopping distance predictions from the distance prediction network serve as inputs to the stopping time prediction network. The networks are validated on their capacity to interpolate and extrapolate predictions of robot stopping behavior in the presence of initial conditions not included in the training and testing data. A method is devised for the calculation of prediction errors for training training, testing and validation data. This method is applied both to interpolation and extrapolation to new initial velocity and positional conditions of the manipulator. In prediction of stopping distances and times, the network is highly successful at interpolation, resulting in comparable or nominally higher errors for the validation data set when compared to the errors for training and testing data. In extrapolation to new initial velocity and positional conditions, notably higher errors in the validation data predictions are observed for the networks considered. Future work in the areas of predictions of stopping behavior with payloads and tooling, further applications to collaborative robotics, analytical models of stopping behavior, inclusion of additional stopping functions, use of explainable AI methods and physics-informed networks are discussed. / Master of Science / As the uses for industrial robots continue to grow and expand, so do the need for robust safety measures to avoid, control, or limit the risks posed to human operators and collaborators. This is exemplified by Isaac Asimov's famous first law of robotics - "A robot may not injure a human being, or, through inaction, allow a human being to come to harm." As applications for industrial robots continue to expand, it is beneficial for robots and human operators to collaborate in work environments without fences. In order to ethically implement such increasingly complex and collaborative industrial robotic systems, the ability to limit robot motion with safety functions in a predictable and reliable way (as outlined by international standards) is paramount. In the event of either a technical failure (due to malfunction of sensors or mechanical hardware) or change in environmental conditions, it is important to be able to stop an industrial robot from any position in a safe and controlled manner. This requires real-time knowledge of the stopping distance and time for the manipulator. To understand stopping distances and times reliability, multiple independent methods can be used and compared to predict stopping behavior. The use of machine learning methods is of particular interest in this context due to their speed of processing and the potential for basis on real recorded data. In this study, we will attempt to evaluate the efficacy of machine learning algorithms to predict stopping behavior and assess their potential for implementation alongside analytical models. A reliable, multi-method approach for estimating stopping distances and times could also enable further methods for safety in collaborative robotics such as Speed and Separation Monitoring (SSM), which monitors both human and robot positions to ensure that a safe stop is always possible. A program for testing and recording the stopping distances and times for the robot is developed. As stopping behavior varies based on the positions and speeds of the robot at the time of stopping, a variety of these criteria are tested with the robot stopping program. This data is then used to train an artificial neural network, a machine learning method that mimics the structure of human and animal brains to learn relationships between data inputs and outputs. This network is used to predict both the stopping distance and time of the robot. The network is shown to produce reasonable predictions, especially for positions and speeds that are intermediate to those used to train the network. Future improvements are suggested and a method is suggested for use of stopping distance and time quantities in robot safety applications.

Robot assisted therapy is becoming increasingly popular. Research has proven it can be of benefit to persons dealing with a variety of disorders, such as Autism Spectrum Disorder (ASD), Attention Deficit Hyperactivity Disorder (ADHD), and it can also provide a source of emotional support e.g. to persons living in seniors’ residences. The advancement in technology and a decrease in cost of products related to consumer electronics, computing and communication has enabled the development of more advanced social robots at a lower cost. This brings us closer to developing such tools at a price that makes them affordable to lower income individuals and families. Currently, in several cases, intensive treatment for patients with certain disorders (to the level of becoming effective) is practically not possible through the public health system due to resource limitations and a large existing backlog. Pursuing treatment through the private sector is expensive and unattainable for those with a lower income, placing them at a disadvantage. Design and effective integration of technology, such as using social robots in treatment, reduces the cost considerably, potentially making it financially accessible to lower income individuals and families in need. The Objective of the research reported in this manuscript is to design and implement a social robot that meets the low-cost criteria, while also containing the required functions to support children with ASD. The design considered contains knowledge acquired in the past through research involving the use of various types of technology for the treatment of mental and/or emotional disabilities.