论文arXiv 2608.18234今天

InterTrack行为世界模型实现人形机器人跨地形全身跟踪81.3%成功率

提出首个面向环境交互的行为世界模型InterTrack，通过Transformer联合预测动作与状态。在复杂地形交互任务中成功率达81.3%，为最优基线4.3倍，跌倒恢复率99.3%，并首次实现人形机器人实时跨地形全身遥操作演示。

AI 整理

本体 SDK 与控制
仿真与训练
具身模型

本文由 AI 根据公开内容整理，可能有误，请以原文为准：GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction（arXiv 2608.18234）

核心内容

针对现有人形机器人运动跟踪器仅适配平地、跨地形控制器指令维度低的问题，研究团队提出InterTrack行为世界模型（BWM）。该模型在复杂地形交互任务中取得81.3%成功率，是现有最优基线的4.3倍，跌倒恢复率达99.3%，同时提升了自由空间跟踪性能，全面超越三种主流跟踪基线，并首次完成人形机器人实时跨地形全身遥操作及物体交互实机验证。

InterTrack采用Transformer架构联合预测下一时刻动作、状态及行为分布，学习环境条件化动力学。为解决交互数据稀缺问题，构建了从重定向运动重建3D支撑几何的自动标注Pipeline以扩展训练集。部署端策略具备“尽力而为”机制，可处理当前环境下不可行的指令，并在缺失支撑时保持稳定响应，有效解决了非结构化环境中的鲁棒控制难题。

关键看点

核心指标：复杂地形交互成功率81.3%，为最优基线4.3倍；跌倒恢复率99.3%，自由空间跟踪性能同步提升
模型架构：基于Transformer的行为世界模型，联合预测动作、状态与行为分布，学习环境条件化动力学
数据工程：构建自动标注Pipeline，从重定向运动中重建3D支撑几何，规模化生成环境交互训练数据
实机验证：首次实现人形机器人实时跨地形全身遥操作，支持物体交互、缺失支撑稳定响应及跌倒恢复

工程与产业观察

InterTrack验证了行为世界模型在非结构化地形全身控制中的有效性，其3D支撑几何自动标注Pipeline为具身交互数据规模化提供了新范式。“尽力而为”策略解决了Sim-to-Real中指令不可行导致的失效问题，对人形机器人野外作业与复杂场景遥操作具有重要工程参考价值。

英文摘要 (Abstract)

General-purpose motion trackers enable humanoid robots to follow diverse whole-body motions while maintaining balance, but are trained only on flat ground, failing to exploit bipedal mobility over complex terrain. Cross-terrain controllers, meanwhile, are task-specific or accept only low-dimensional locomotion commands. We introduce InterTrack, the first behavior world model (BWM) for robust whole-body tracking with environment interaction. Its Transformer jointly predicts the next action, state, and behavior distribution, learning environment-conditioned dynamics. To scale interaction training data, an automatic annotation pipeline reconstructs 3D support geometry from retargeted motions. At deployment, the policy handles commands implausible in the current environment in a "best-effort" manner. Quantitatively, InterTrack achieves an 81.3% success rate on terrain interaction (4.3 times the best evaluated baseline) and a 99.3% fall-recovery rate, while also improving free-space tracking and outperforming three leading tracking baselines across all of these regimes. To our knowledge, we provide the first demonstration of real-time cross-terrain whole-body teleoperation on a humanoid robot, alongside object interaction, stable responses to missing supports, and robust recovery from falls.

作者：Ziyang Cheng, Tianshu Tang, Jinxin Lan, Xinze Chen, Yuhan Gong, Zhichao Liu, Changzhong Wu, Yahao Mao, Zongyan Deng, Mingxuan Ma, Huasen Xi, Yilong Liu, Yutong Wu, Xiaofeng Wang, Borui Zhang, Bingyao…