Intent-Driven LLM Ensemble Planning for Flexible Multi-Robot Disassembly: Demonstration on EV Batteries

TL;DR

This paper presents an intent-driven planning pipeline utilizing ensemble large language models for flexible multi-robot disassembly of EV batteries, demonstrating reliable, low-effort task execution in unstructured scenes.

Contribution

The novel pipeline integrates perception, LLM ensembles, verification, and filtering to robustly generate and verify multi-robot action sequences from simple human instructions.

Findings

Achieved high sequence correctness in 200 real scenes

Demonstrated low user effort and efficient task execution

Validated pipeline's robustness and reliability

Abstract

This paper addresses the problem of planning complex manipulation tasks, in which multiple robots with different end-effectors and capabilities, informed by computer vision, must plan and execute concatenated sequences of actions on a variety of objects that can appear in arbitrary positions and configurations in unstructured scenes. We propose an intent-driven planning pipeline which can robustly construct such action sequences with varying degrees of supervisory input from a human using simple language instructions. The pipeline integrates: (i) perception-to-text scene encoding, (ii) an ensemble of large language models (LLMs) that generate candidate removal sequences based on the operator's intent, (iii) an LLM-based verifier that enforces formatting and precedence constraints, and (iv) a deterministic consistency filter that rejects hallucinated objects. The pipeline is evaluated on an example task in which two robot arms work collaboratively to dismantle an Electric Vehicle battery for recycling applications. A variety of components must be grasped and removed in specific sequences, determined by human instructions and/or by task-order feasibility decisions made by the autonomous system. On 200 real scenes with 600 operator prompts across five component classes, we used metrics of full-sequence correctness and next-task correctness to evaluate and compare five LLM-based planners (including ablation analyses of pipeline components). We also evaluated the LLM-based human interface in terms of time to execution and NASA TLX with human participant experiments. Results indicate that our ensemble-with-verification approach reliably maps operator intent to safe, executable multi-robot plans while maintaining low user effort.