Safe and proactive motion planning for collaborative robots

Faculty Development Competitive Research Grant Program (General) 2024-2026

The purpose of our project is to design and implement advanced motion planning methodologies for collaborative robots, which are at the same time safe according to the ISO/TS 15066 standard and proactive, i.e., they redefine the robot motion in real time by using predictions of the human motion. On the one hand, methods based on model predictive control (MPC) will be defined, based on explicit predictions of the human motion. On the other hand, deep-learning-based approximations of the above-mentioned methods will also be developed. The use of these strategies will lead to increasing productivity beyond the state of the art, while at the same time guaranteeing safety.