让双足轮式机器人平稳走连续楼梯，靠动态感知的蒸馏学习
DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Locomotion over Continuous Stairs
- 用世界模型增强地形编码，保持动态一致性
- 引入动量目标避免知识迁移时维度崩溃
- 实测在仿真和真实硬件上均提升行走平滑性
近年来的控制进展使双足轮式机器人能够应对坡道和单级障碍物，但连续楼梯仍具挑战性，因现有师生框架存在动态感知表征弱化与地形几何编码不完整的问题。为此，我们提出DynaWM，一种动态感知的表征学习框架。为增强地形编码能力并实现透明评估，引入世界模型作为正则化项，强化前向动力学感知，同时保留完整的地形几何信息，并支持分层编码可视化。为稳定知识迁移，采用动量目标编码器提供一致的蒸馏目标，防止因教师更新非平稳导致的维度坍缩。通过主成分分析（PCA）可视化与量化指标评估，表明本方法能分层捕获地形几何，具备更强的地形编码能力，从而提升地形适应性与运动平滑性。仿真与真实硬件实验结果表明，该方法显著提升地形适应性与运动平滑性，使双足轮式机器人成功跨越多样连续楼梯，如图1所示。
原文摘要 · Abstract (English)
Recent advances in control have enabled bipedal-wheeled robots to traverse slopes and single-step obstacles, yet long staircase traversal remains challenging as current teacher-student frameworks suffer from weakened dynamics-aware representations and incomplete terrain geometry encoding. To bridge this gap, we propose DynaWM, a dynamics-aware representation learning framework. To enhance terrain encoding capability and enable transparent assessment, we introduce a world model as a regularizer to enforce forward-dynamics awareness, preserving comprehensive terrain geometry while facilitating hierarchical encoding visualization. To stabilize knowledge transfer, we employ a momentum target encoder to provide consistent distillation targets, preventing dimensional collapse from non-stationary teacher updates. Evaluation of the learned representations through Principal Component Analysis (PCA) visualization and quantitative metrics reveals that our encoder hierarchically captures terrain geometry with higher terrain encoding capability, leading to enhanced terrain adaptability and motion smoothness. Experimental results in simulation and real hardware demonstrate that our method achieves superior terrain adaptability and motion smoothness, enabling bipedal-wheeled robots to overcome diverse continuous stairs, as shown in Fig. 1.
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。