Collision-Free Kinematics for Redundant Manipulators in Dynamic Scenes using Optimal Reciprocal Velocity Obstacles
This addresses the challenge of safe and efficient robot coordination in shared workspaces with moving obstacles, representing an incremental improvement over existing methods.
The paper tackles the problem of generating collision-free kinematics for multiple high-DOF manipulators in dynamic environments, achieving real-time performance with trajectories computed in milliseconds on Baxter robots.
We present a novel algorithm for collision-free kinematics of multiple manipulators in a shared workspace with moving obstacles. Our optimization-based approach simultaneously handles collision-free constraints based on reciprocal velocity obstacles and inverse kinematics constraints for high-DOF manipulators. We present an efficient method based on particle swarm optimization that can generate collision-free configurations for each redundant manipulator. Furthermore, our approach can be used to compute safe and oscillation-free trajectories in a few milli-seconds. We highlight the real-time performance of our algorithm on multiple Baxter robots with 14-DOF manipulators operating in a workspace with dynamic obstacles. Videos are available at https://sites.google.com/view/collision-free-kinematics