Recent advances in Reinforcement Learning (RL) have made significant contributions in past years by offering intelligent solutions to solve robotic tasks. However, most RL algorithms, especially the model-free RL, are plagued by low learning efficiency and safety problems. In this paper, we propose using the Bayesian Neural Networks (BNNs) to guide the agent exploring actively to enhance the learning efficiency in RL and investigate the potential of recognizing safety risks in working environments with uncertainty information. We compare two types of uncertainty quantification methods in both action and state spaces. To validate our method, we visualize the quantified uncertainty in robot environments with or without safety hazards. Moreover, we evaluate the learning efficiency and safety performance of the RL agents learned with BNNs on different robotic tasks.

In manufacturing, the current trend-shift from mass-production to mass-personalization is enabled, among others, by the emerging field of human-robot collaboration (HRC), in which humans collaborate or work in proximity with robots. In HRC scenarios, robots need to exert a desired behaviour that maximizes utility without sacrificing safety and responsiveness. To maximize safety and utility in static environments, state-of-the-art offline motion-planners use computationally-heavy algorithms for approximating the collision-free robot reachability and accordingly generate (sub-)optimal robot trajectories. To enable real-time responsiveness, we propose an integrated global planner to generate sub-optimal trajectories. It relies on a closed-loop reactive controller for executing the global plan while ensuring safety with practical assumptions about the environment. We evaluate GLIR in simulation. In our experiments, our global planner operates at 25 Hz and the local planner at 100 Hz, enabling their execution in dynamic environments. In all experiments on static scenes with static and dynamic goals, GLIR keeps a safety distance from obstacles. We showcase some simulation experiments and a real-world demonstration in the video available at https://mohamedgalil.github.io/glir/.

Human-Robot Interaction (HRI) is becoming increasingly viable for flexible and resilient manufacturing, combining the intelligence and dexterity of humans with the precision and strength of robots. However, HRI incurs the breakage of well-established safety procedures and requires robots to be aware of their environment, especially their human co-workers. This calls for human motion prediction, which can improve the performance in HRI scenarios and contribute towards safer HRI. In this regard, we propose PredNet, a simple recurrent neural network architecture designed to predict human motion in a prediction window of 1 second. To address the lack of production-related HRI scenarios for training and validating PredNet, we develop simple HRI scenarios in a simulation environment, consisting of the following human actions: walking, lifting boxes and wiping. For a real world validation, we use Mogaze dataset. Furthermore, we propose a novel metric, namely, Volumetric Occupancy Error (VOE) towards measuring the safety performance of motion prediction architectures aimed to be applied in industrial settings. On both HRI scenarios and Mogaze datasets, PredNet performs better than baseline RED architecture.

Safety in Human-Robot Collaboration (HRC) is a bottleneck to HRC-productivity in industry. With robots being the main source of hazards, safety engineers use over-emphasized safety measures, and carry out lengthy and expensive risk assessment processes on each HRC-layout reconfiguration. Recent advances in deep Reinforcement Learning (RL) offer solutions to add intelligence and comprehensibility of the environment to robots. In this paper, we propose a framework that uses deep RL as an enabling technology to enhance intelligence and safety of the robots in HRC scenarios and, thus, reduce hazards incurred by the robots. The framework offers a systematic methodology to encode the task and safety requirements and context of applicability into RL settings. The framework also considers core components, such as behavior explainer and verifier, which aim for transferring learned behaviors from research labs to industry. In the evaluations, the proposed framework shows the capability of deep RL agents learning collision-free point-to-point motion on different robots inside simulation, as shown in the supplementary video.