具身开发者社区

外观

论文arXiv 2609.211071 个月前

从沉浸式人类示范中学习穿越3D杂乱环境的场景感知人形机器人运动 ​

MTC通过VR示范采集与场景感知重定向学习人形机器人避障运动，并在Unitree G1和MTC-Challenge上验证。

AI 整理
  • 本体 SDK 与控制
  • 感知与导航
  • 数据与采集

宇树科技宇树 G1

原文链接：Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations（arXiv 2609.21107 · 发布日期：2026-09-17）

Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations

MTC通过VR示范采集与场景感知重定向学习人形机器人避障运动，并在Unitree G1和MTC-Challenge上验证。

核心要点 ​

  • 密集杂乱环境具有三维几何约束，需要全身运动与场景几何紧耦合以避障。
  • MTC在程序生成的VR环境中采集沉浸式人类示范，避免昂贵的实体场景搭建。
  • 场景感知重定向将示范转为人形轨迹，并严格保持机器人与场景间隙以无碰穿越。
  • 策略部署于Unitree G1，在MTC-Challenge多障碍穿越中达到70.2%无碰率。

验证范围与局限：验证范围为Unitree G1上的部署及MTC-Challenge中的多障碍穿越场景。

英文摘要 (Abstract) ​

While learning from human motions has enabled highly dynamic humanoid skills such as dancing and martial arts in obstacle-free space, traversal through densely cluttered environments remains underexplored. These spaces are three-dimensional and geometrically constrained, requiring scene-aware locomotion that tightly couples whole-body motion with scene geometry for obstacle avoidance. To address these challenges, we present Moving Through Clutter (MTC), a learning-from-demonstration framework for scene-aware humanoid locomotion. To bypass costly physical scene construction, MTC uses procedurally generated Virtual Reality environments for immersive data collection. To transform these human motions into training-ready humanoid motions, we propose a scene-aware motion retargeting algorithm that converts human demonstrations into humanoid trajectories while strictly enforcing robot-scene clearance to guarantee collision-free traversal. These reference trajectories are then used to train a scene-aware locomotion policy that deploys on a Unitree G1 humanoid. Evaluated on our proposed MTC-Challenge for multi-obstacle traversal, the policy demonstrates a 70.2% collision-free rate across diverse scenarios, successfully traversing complex environments through diverse whole-body skills, including crawling through low-clearance passages and squeezing through narrow gaps.

作者：Beichen Wang, Tong Xu, Daniel Kosukhin, Yuen-Hei Yeung, Yuanjie Lu, Xuesu Xiao

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2609.21107：Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations访问 2026-10-21