TERRA：面向肌肉骨骼运动的地形感知重建、重定向与控制

中文摘要 AI 辅助

肌肉骨骼建模和强化学习的最新进展使得肌肉驱动的智能体能够再现日益复杂的人体运动。然而，这些能力在很大程度上仍局限于平坦地面，部分原因在于运动数据集很少包含对齐的地形几何信息，且将地形交互重定向到复杂的肌肉骨骼身体具有挑战性。我们提出TERRA，一个用于肌肉骨骼运动的地形感知重定向和控制的端到端流水线。仅从运动学轨迹出发，TERRA结合地形先验、估计接触和负自由空间证据来恢复任务相关的支撑几何。TERRA在重定向过程中进一步考虑解剖学、肌腱连续性和接触约束。利用来自五个数据集的运动-地形对，我们成功地在9.4小时的多样化运动数据上训练了一个单一的肌肉驱动控制策略。在重建、重定向和保留测试跟踪基准上，TERRA提高了地形精度，大幅减少了解剖学和交互违规，并在支持的地形族上实现了最高的完成率。总体而言，TERRA提供了一条从无场景运动数据到多样化非平坦地形上肌肉驱动运动的实用途径。项目网站：此https URL。

英文摘要

Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human motions. Yet these capabilities remain largely confined to flat ground, in part because motion datasets rarely include aligned terrain geometry and because retargeting terrain interactions to complex musculoskeletal bodies is challenging. We present TERRA, an end-to-end pipeline for terrain-aware retargeting and control of musculoskeletal locomotion. From kinematic trajectories alone, TERRA combines terrain priors, estimated contacts, and negative free-space evidence to recover task-relevant support geometry. TERRA further considers anatomical, tendon-continuity, and contact constraints during retargeting. Using the resulting motion-terrain pairs from five datasets, we successfully train a single muscle-actuated control policy on 9.4 hours of diverse locomotion. Across reconstruction, retargeting, and held-out tracking benchmarks, TERRA improves terrain accuracy, sharply reduces anatomical and interaction violations, and achieves the highest observed completion rate over supported terrain families. Overall, TERRA provides a practical route from scene-less motion data to muscle-actuated locomotion over diverse non-flat terrain. Project website: https://cnai.epfl.ch/terra/

发表机构

• EPFL（洛桑联邦理工学院）

机构由 AI 辅助整理，请以论文原文为准。