LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space

2026-06-28

AI Summary

This work addresses the combinatorial explosion in joint planning of contact configurations, coupled dynamics, and collision avoidance for multi-robot long-horizon manipulation tasks in highly cluttered environments. To tackle this challenge, the paper introduces the LAMP framework, which integrates a generative manipulation model with two complementary planners: LAMPA* systematically explores the coupled object–robot state space, while LAMP-Lazy enables efficient real-time replanning through lazy evaluation. This approach achieves, for the first time, scalable search over the full coupled manipulation space in dense, long-horizon scenarios, overcoming the limitations of existing end-to-end learning or oversimplified planning methods. The framework successfully completes complex tasks in simulation that are infeasible for current approaches.

Abstract

Multi-robot manipulation requires jointly reasoning about contact formations, robot motions under coupled dynamics, and collision avoidance. Systematically searching over this large space is difficult and becomes increasingly intractable as the number of robots grows, the task horizon lengthens, or the scene becomes more cluttered. Existing approaches therefore either learn to solve the problem end-to-end via reinforcement learning or restrict planning to a simpler surrogate problem, such as planning object motions while learning short-horizon contact primitives. However, neither paradigm scales to the problem instances we target: longhorizon multi-robot manipulation in extremely dense environments. In this paper, we propose a Long-horizon Adaptive Manipulation Planning (LAMP) framework with two planners that enable tractable search over the full coupled space by combining a learned generative manipulation model: a LAMPA* planner that systematically searches over the coupled objectrobot space, and LAMP-Lazy: a lazy planner that enables real-time replanning through deferred evaluation. Experiments in challenging simulated environments demonstrate that our approach solves complex long-horizon tasks in highly cluttered environments that prior methods cannot handle.

Problem

• multi-robot manipulation
• long-horizon planning
• cluttered environments
• contact reasoning
• collision avoidance

Innovation

• multi-robot manipulation
• long-horizon planning
• coupled dynamics
• generative manipulation model
• lazy replanning