Robots clear pathways by pushing obstacles with physics based planning
PushAround: Collaborative Path Clearing via Physics-Informed Hybrid Search
Robotics
Summary
Big vehicles often get stuck when small things block their path and need robots to move those items out of the way. The authors created PushAround, a method that helps teams of robots figure out how to push objects realistically, considering the size, weight, and forces involved. PushAround combines smart path checks with short simulations to find plans that can actually work in the real world. Their tests show it works well for multiple robots in tight spaces and can handle errors in how the physics are modeled.
What this means in practice
- •For mobile robot operators: Generate executable clearing plans for mobile robots to navigate cluttered environments by pushing obstacles while respecting physical constraints.
- •For warehouse automation teams: Plan coordinated pushing actions by robot teams to clear paths around movable obstacles in tight warehouse spaces efficiently.
Authors
Zili Tang, Zongyuan Li, Zishao Qiao, Meng Guo
Abstract
Large vehicles in cluttered environments are often blocked by movable obstacles, motivating mobile robot teams to clear traversable corridors. Navigation Among Movable Obstacles (NAMO) approaches often abstract obstacle displacements while neglecting robot dimensions, obstacle mass, contact geometry and forces, yielding physically infeasible plans. PushAround is a physics-informed hybrid search that couples geometric connectivity reasoning with short-horizon simulation to construct executable clearing plans. Repeated W-clearance connectivity graph (WCCG) queries expose frontier gaps requiring widening and rank them by estimated downstream costs. The search generates direct or recursive pushing candidates, selecting obstacles, directions, contacts and forces, and admits physics-evaluated candidates. Numerical experiments validate WCCG against standard connectivity checks and demonstrate scaling to denser clutter and teams of up to four robots, with robustness to simulated execution-side physical-parameter mismatch.