Hybrid Task and Motion Planning with Reactive Collision Handling for Multi-Robot Disassembly of Complex Products: Application to EV Batteries

arXiv cs.RO / 4/22/2026

💬 OpinionDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

The paper introduces a vision-driven hybrid TAMP framework for coordinating two robots on complex disassembly task sequences, integrating task decomposition/allocation with a learning-based RRT motion planner.
A GMM-informed planner is combined with a hybrid safety layer that uses predictive collision checking via a MoveIt/FCL digital twin alongside reactive, vision-based avoidance and replanning.
The system runs in closed loop by repeatedly scanning the scene and tracking completion state to update the remaining task sequence, avoiding reliance on a fixed open-loop plan.
In EV battery disassembly experiments, the proposed approach substantially reduces cumulative end-effector path length (48.8→17.9 m) and swept volumes/overlap while also improving makespan versus a Default-RRTConnect baseline.
Overall, results suggest that predictive planning plus reactive collision handling can yield safer, more compact motion and better scalability for multi-robot sequential manipulation tasks.

Abstract

This paper addresses the problem of multi-robot coordination for complex manipulation task sequences. We present a vision-driven task-and-motion planning (TAMP) framework for a real dual-agent platform that integrates task decomposition and allocation with a learning-based RRT planner. A GMM-informed motion planner is coupled with a hybrid safety layer that combines predictive collision checking in a MoveIt/FCL digital twin with reactive vision-based avoidance and replanning. This integration is challenging as the system jointly satisfies task precedence, geometric feasibility, dynamic obstacle avoidance, and dual-arm coordination constraints. The framework operates in closed loop by updating the remaining task sequence from repeated scene scans and completion-state tracking rather than executing a fixed open-loop plan. In EV battery disassembly experiments, compared with Default-RRTConnect under identical perception and task assignments, the proposed system reduces cumulative end-effector path length from 48.8 to 17.9~m (

-63.3\%

), improves makespan from 467.9 to 429.8~s (

-8.1\%

), and reduces swept volumes (R1:

0.583\rightarrow0.139\,\mathrm{m}^3

, R2:

0.696\rightarrow0.252\,\mathrm{m}^3

) and overlap (

0.064\rightarrow0.034\,\mathrm{m}^3

). These results show that combining predictive planning and reactive collision avoidance in a real dual-arm disassembly scenario improves motion compactness, safety, and scalability to broader multi-robot sequential manipulation tasks.