Deep reinforcement learning for collision avoidance of robotic manipulators

In this paper a real-time collision avoidance approach using machine learning is presented for safe human-robot coexistence. More specifically, the collision avoidance problem is tackled with Deep Reinforcement Learning (DRL) techniques, applied to robot manipulators with a workspace invaded by unpredictable obstacles. Since the robotic systems are defined in the continuous space, a Normalized Advantage Function (NAF) model-free algorithm has been used. In order to assess the proposal, a robotic system, that is a COMAU-SMART3-S2 anthropomorphic robot manipulator, has been considered. The robotic system has been interfaced with external tools for evaluation, control, and automatic training. Simulations carried out on a virtual environment are finally reported to show the effectiveness of the proposed model-free deep reinforcement learning algorithm.