野外跑酷：利用多专家蒸馏与RL微调学习通用可扩展的敏捷运动策略
Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning
AI总结：
针对足式机器人现有控制方法在非结构化环境泛化性差的问题，提出多专家蒸馏结合RL微调的敏捷运动框架，经多阶段训练与真实机器人部署验证，显著提升多地形技能整合性能，设定足式机器人运动新基准。
摘要：
足式机器人非常适合穿越轮式机器人无法进入的地形，因此在搜救或太空探索等应用场景中极具潜力。然而，当前的控制方法往往难以在多样的非结构化环境中实现泛化。本文提出了一种足式机器人敏捷运动的新型框架，该框架结合多专家蒸馏与强化学习（RL）微调，以实现鲁棒的泛化能力。首先，训练针对特定地形的专家策略以发展专门的运动技能；随后通过DAgger算法将这些策略蒸馏为统一的基础策略；接着在包含真实世界3D扫描数据的更广泛地形集上使用RL对蒸馏后的策略进行微调。该框架可通过重复微调进一步适配新地形，所提出的策略利用深度图像作为外部感知输入，能够在多样的非结构化地形中实现鲁棒导航。实验结果表明，与现有方法相比，该方法在将多地形技能整合到单个控制器方面性能显著提升。在ANYmal D机器人上的部署验证了该策略具备敏捷且鲁棒地穿越复杂环境的能力，为足式机器人运动设定了新的基准。
英文摘要：
Legged robots are well-suited for navigating terrains inaccessible to wheeled robots, making them ideal for applications in search and rescue or space exploration. However, current control methods often struggle to generalize across diverse, unstructured environments. This paper introduces a novel framework for agile locomotion of legged robots by combining multi-expert distillation with reinforcement learning (RL) fine-tuning to achieve robust generalization. Initially, terrain-specific expert policies are trained to develop specialized locomotion skills. These policies are then distilled into a unified foundation policy via the DAgger algorithm. The distilled policy is subsequently fine-tuned using RL on a broader terrain set, including real-world 3D scans. The framework allows further adaptation to new terrains through repeated fine-tuning. The proposed policy leverages depth images as exteroceptive inputs, enabling robust navigation across diverse, unstructured terrains. Experimental results demonstrate significant performance improvements over existing methods in synthesizing multi-terrain skills into a single controller. Deployment on the ANYmal D robot validates the policy's ability to navigate complex environments with agility and robustness, setting a new benchmark for legged robot locomotion.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
