用于自适应仿人 locomotion 鲁棒 sim-to-real 迁移的对比表征学习
Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion
AI总结：
本文提出对比学习框架，使纯本体感知策略编码仿真特权信息并赋能自适应 gait clock，实现前瞻性主动调整，解决鲁棒性与主动性权衡，零样本迁移至全尺寸仿人机器人验证了在复杂地形上的有效鲁棒 locomotion。
摘要：
强化学习在仿人 locomotion 领域取得了显著进展，但实际部署仍面临一个根本困境：策略必须在反应式本体感知控制的鲁棒性与复杂、脆弱的感知驱动系统的主动性之间做出抉择。本文通过引入一种新范式解决了这一困境，该范式赋予纯本体感知策略主动能力，从而在不付出部署时成本的情况下实现感知的前瞻性。我们的核心贡献是一个对比学习框架，该框架迫使 actor 的 latent state 编码来自仿真的特权环境信息。关键在于，这种“蒸馏感知”赋能了自适应 gait clock，使策略能够基于对地形的推断理解主动调整其节奏。这种协同作用解决了刚性时钟步态与不稳定无时钟策略之间的经典权衡。我们通过将方法零样本 sim-to-real 迁移到全尺寸仿人机器人上进行了验证，展示了在具有挑战性的地形上高度鲁棒的 locomotion，包括 30 cm 高的台阶和 26.5° 的斜坡，证明了我们方法的有效性。
英文摘要：
Reinforcement learning has produced remarkable advances in humanoid locomotion, yet a fundamental dilemma persists for real-world deployment: policies must choose between the robustness of reactive proprioceptive control or the proactivity of complex, fragile perception-driven systems. This paper resolves this dilemma by introducing a paradigm that imbues a purely proprioceptive policy with proactive capabilities, achieving the foresight of perception without its deployment-time costs. Our core contribution is a contrastive learning framework that compels the actor's latent state to encode privileged environmental information from simulation. Crucially, this ``distilled awareness" empowers an adaptive gait clock, allowing the policy to proactively adjust its rhythm based on an inferred understanding of the terrain. This synergy resolves the classic trade-off between rigid, clocked gaits and unstable clock-free policies. We validate our approach with zero-shot sim-to-real transfer to a full-sized humanoid, demonstrating highly robust locomotion over challenging terrains, including 30 cm high steps and 26.5° slopes, proving the effectiveness of our method. Website: https://lu-yidan.github.io/cra-loco.
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。
