A Real-Time Reconfigurable Collision Avoidance System for Robot Manipulation

Intelligent robotic systems are becoming fundamental actors in industrial and hazardous facilities scenarios. Aiming to increase personnel safety and machine availability, robots can help perform repetitive and dangerous tasks which humans either prefer to avoid or are unable to do because of hazards, space constraints or the extreme environments in which they take place, such as outer space or radioactive experimental areas. Teleoperated robots need user friendly and safety tools to be safely operated in harsh environments where the intervention scenarios are unstructured and most of the time dangerous for human intervention. In many robotic interventions in harsh environments, a dual arms robotic system is needed to perform difficult task such as cutting, drilling etc. To ensure the safety of the robotic system and the machines to be tele-manipulated, as well as increasing the uptime of the plants, a real-time reconfigurable self-collision avoidance system coupled to a virtual augmented reality scenario is fundamental to help the operator during the intervention. In addition, it is important to provide to the operator a uniform control system, in order to not create confusion when several operations are performed using different robotic platforms. For this reason, it is vital that the self-collision avoidance system is adaptable to the current robot hardware and software configurations. In this paper, a novel reconfigurable collision avoidance system for robot manipulation running in real time is presented. The novelty of the proposed solution is the capability to be adaptable to different robots configuration and installation taking into account different parameters like the type and the number of robotic arms, as well as their orientation. The novel system is able to avoid collision not only within the robot itself, but it can avoid collision also with external unexpected objects. The structure of the novel solution is presented, as well as its validation in the CERN accelerators facilities.