外观
论文arXiv 2609.248401 个月前
PredActor：用于可转向板载人形控制的预测动作扩散
PredActor用本体感知联合预测动作与内部未来状态，实现可引导人形闭环控制，并在仿真和Unitree G1硬件上验证。
宇树 G1原文链接：PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control（arXiv 2609.24840 · 发布日期：2026-09-21）
PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control
PredActor用本体感知联合预测动作与内部未来状态，实现可引导人形闭环控制，并在仿真和Unitree G1硬件上验证。
核心要点
- 动机：参考轨迹可能超出跟踪器能力，动作扩散又缺少可引导未来状态。
- 方法：基于本体感知历史和可选任务上下文，联合预测动作与内部未来状态轨迹。
- 引导：用classifier-free guidance增强文本条件运动，用classifier guidance转向测试时目标。
- 结果：仿真到达44/45个目标，文本检索分数0.539，高于条件动作扩散的0.424。
验证范围与局限：验证范围包括仿真和一台Unitree G1硬件，任务涵盖文本条件运动、抗扰、摇杆控制和语义插值。
英文摘要 (Abstract)
Diffusion models provide a flexible framework for motion generation, but turning this flexibility into closed-loop humanoid control remains challenging. Hierarchical generator-tracker systems steer motion through reference trajectories, yet these references may exceed the capabilities of the downstream tracker, leaving physical feasibility and disturbance recovery largely to a separate control module. Action-only diffusion avoids this separation by directly generating executable actions, but provides no explicit future-state trajectory that can be steered toward test-time motion objectives. Joint state-action diffusion offers a natural alternative, but existing controllers often rely on privileged full-body states, while learned behavior selection and test-time motion steering remain only partially integrated. We present PredActor, a predictive action diffusion policy that unifies both steering modes in one directly executed policy using proprioception alone. Given proprioceptive history and optional task context, PredActor jointly predicts actions and an internal future-state trajectory that enables guidance: classifier-free guidance strengthens text-conditioned motion, while classifier guidance steers future states toward test-time objectives. Only actions are executed, requiring neither a motion-reference tracker nor privileged full-body states. In simulation, PredActor reaches 44 of 45 destination targets and achieves a text retrieval score of 0.539 versus 0.424 for conditional action diffusion, with similar disturbance survival. Rolling denoising and computation-preserving runtime optimizations reduce the complete callback to 16.790 ms median and 19.383 ms p95 on a Jetson Orin NX, within the 20 ms control period. Deployed on a Unitree G1, PredActor demonstrates text-conditioned motion, disturbance response, joystick control, and semantic interpolation in simulation and hardware.
作者：Lei Ye, Haibo Gao, Yitang Li, Peng Xu, Zetong Jing, Junhan Sun, Fanrong Dong, Ziqi Han, Xue Wang, Jianhua Sun
来源
本页事实对应的公开页面，以原文为准。