A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance
This addresses the challenge of real-time collision avoidance for robots operating in dynamic environments with humans, though it appears incremental as it builds on existing motion planning methods.
The paper tackles the problem of scalable and safe robot navigation among multiple robots and humans by introducing a framework that precomputes tracking error margins, uses confidence-aware human motion predictions, and coordinates robots with sequential priority ordering, demonstrating it with two robots and two humans in hardware and in a larger simulation.
Robust motion planning is a well-studied problem in the robotics literature, yet current algorithms struggle to operate scalably and safely in the presence of other moving agents, such as humans. This paper introduces a novel framework for robot navigation that accounts for high-order system dynamics and maintains safety in the presence of external disturbances, other robots, and non-deterministic intentional agents. Our approach precomputes a tracking error margin for each robot, generates confidence-aware human motion predictions, and coordinates multiple robots with a sequential priority ordering, effectively enabling scalable safe trajectory planning and execution. We demonstrate our approach in hardware with two robots and two humans. We also showcase our work's scalability in a larger simulation.