Event
PushAround: A New Method for Multi-Robot Collaborative Obstacle Clearance
1 reports · 1 sources
Zili Tang and other authors have released the preprint paper PushAround, proposing a physics-informed hybrid search method that combines geometric connectivity reasoning with short-horizon simulation to generate executable obstacle-clearance plans for mobile robot teams. The method repeatedly queries a W-clearance connectivity graph (WCCG) to identify frontier gaps that need to be widened, ranks them by estimated downstream cost, then generates direct or recursive push-obstacle candidates and selects the obstacle, direction, contact, and force. Numerical experiments compare WCCG with standard connectivity checks and show that the method scales to denser obstacles and teams of up to four robots, and remains robust when physical parameters on the simulated execution side do not match. The paper has been accepted for publication in IEEE Robotics and Automation Letters (RA-L).
Report timeline
- PushAround: Physics-Informed Hybrid Search for Multi-Robot Collaborative Path Clearing
PushAround proposes a physics-informed hybrid search method that combines geometric connectivity reasoning with short-horizon simulation to generate executable clearing plans for mobile robot teams. The method uses repeated W-clearance connectivity graph (WCCG) queries to identify frontier gaps that need widening and ranks them by estimated downstream cost, then generates direct or recursive pushing candidates, selecting obstacles, directions, contacts, and forces.
arXiv cs.RO ·