Skip to Main Content
Obstacle detection and collision avoidance capabilities are the cornerstone of service robotic manipulators, i.e., robots that can work safely in human environments. Though algorithms and methods for collision avoidance already exist, they usually rely on complete CAD models of the environment. Such model are difficult to obtain from dynamic environments involving persons moving in unpredictable ways, thus reactive behaviors based on real-time sensing seems to be a more appropriate solution. This paper presents a prototype of the sensing skin for a robot arm. Rings of sensors are arranged around the robot links, each ring consisting of several infrared range sensors, which can detect objects in a distance range of between 4 and 30 cm, with less influence on the color of reflected obstacles. The resulting array of sensor measurements is fed up into a reinforcement learning scheme whose outputs are motion command for the robot joints. The system is intended to learn in an autonomous way the motions to avoid collisions with surrounding objects in real-time.