多只四足机器人协同推动物体，实现长时序避障操作。
Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing
- 分层强化学习框架：高层规划+中层协同+底层行走
- 成功率达36%提升，完成时间减少24.5%
- 适用于搜救、搬运等真实场景的复杂任务
近期四足机器人的运动能力已取得显著进展，但其在处理大型物体时的操控能力仍有限，制约了其在搜救、建筑、工业自动化及房间整理等现实场景中的应用。本文针对多四足机器人避障长时序推动物体的任务，提出一种三级分层多智能体强化学习框架。高层控制器结合RRT规划器与集中式自适应策略生成子目标；中层控制器采用去中心化的目标条件策略引导机器人向子目标移动；底层使用预训练的行走策略执行动作指令。在仿真环境中评估表明，该方法相较基线显著提升性能，成功率达36.0%更高，完成时间减少24.5%。该框架已在真实Go1机器人上成功实现Push-Cuboid和Push-T等长时序避障推物任务。
原文摘要 · Abstract (English)
Recently, quadrupedal locomotion has achieved significant success, but their manipulation capabilities, particularly in handling large objects, remain limited, restricting their usefulness in demanding real-world applications such as search and rescue, construction, industrial automation, and room organization. This paper tackles the task of obstacle-aware, long-horizon pushing by multiple quadrupedal robots. We propose a hierarchical multi-agent reinforcement learning framework with three levels of control. The high-level controller integrates an RRT planner and a centralized adaptive policy to generate subgoals, while the mid-level controller uses a decentralized goal-conditioned policy to guide the robots toward these sub-goals. A pre-trained low-level locomotion policy executes the movement commands. We evaluate our method against several baselines in simulation, demonstrating significant improvements over baseline approaches, with 36.0% higher success rates and 24.5% reduction in completion time than the best baseline. Our framework successfully enables long-horizon, obstacle-aware manipulation tasks like Push-Cuboid and Push-T on Go1 robots in the real world.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。