ALORE: Autonomous Large-Object Rearrangement with a Legged Manipulator

2026-02-04

AI Summary

This work addresses the challenge of enabling legged robots to autonomously, efficiently, and collision-free rearrange multiple large, heavy objects—such as furniture—in complex environments. The authors propose a hierarchical reinforcement learning–driven autonomous rearrangement system that integrates a unified interaction configuration representation, object planar velocity estimation, whole-body low-level control, and online task-and-motion co-replanning. This framework enables a single policy to generalize robustly across diverse large-object manipulation tasks. Experiments demonstrate strong robustness in both simulation and real-world settings: the system successfully completed eight consecutive rounds of rearranging 32 chairs (approximately 40 minutes) without failure and achieved autonomous long-distance rearrangement over 40 meters, significantly outperforming strong baseline methods.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Endowing robots with the ability to rearrange various large and heavy objects, such as furniture, can substantially alleviate human workload. However, this task is extremely challenging due to the need to interact with diverse objects and efficiently rearrange multiple objects in complex environments while ensuring collision-free loco-manipulation. In this work, we present ALORE, an autonomous large-object rearrangement system for a legged manipulator that can rearrange various large objects across diverse scenarios. The proposed system is characterized by three main features: (i) a hierarchical reinforcement learning training pipeline for multi-object environment learning, where a high-level object velocity controller is trained on top of a low-level whole-body controller to achieve efficient and stable joint learning across multiple objects; (ii) two key modules, a unified interaction configuration representation and an object velocity estimator, that allow a single policy to regulate planar velocity of diverse objects accurately; and (iii) a task-and-motion planning framework that jointly optimizes object visitation order and object-to-target assignment, improving task efficiency while enabling online replanning. Comparisons against strong baselines show consistent superiority in policy generalization, object-velocity tracking accuracy, and multi-object rearrangement efficiency. Key modules are systematically evaluated, and extensive simulations and real-world experiments are conducted to validate the robustness and effectiveness of the entire system, which successfully completes 8 continuous loops to rearrange 32 chairs over nearly 40 minutes without a single failure, and executes long-distance autonomous rearrangement over an approximately 40 m route. The open-source packages are available at https://zhihaibi.github.io/Alore/.

Problem

• large-object rearrangement
• legged manipulator
• autonomous manipulation
• multi-object interaction
• collision-free loco-manipulation

Innovation

• hierarchical reinforcement learning
• unified interaction representation
• object velocity estimation
• task-and-motion planning
• legged manipulation