PredActor：单一扩散策略实现人形机器人可引导的机载控制
PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control
把扩散模型控制策略跑进宇树 G1 实机：Jetson 上单帧不到 20ms，文本指定动作比基线更准
arXiv 论文提出 PredActor，一种预测式动作扩散策略，仅凭本体感知历史和可选任务上下文，同时生成可执行动作与内部未来状态轨迹。仿真中 PredActor 到达全部 15 个目标点，文本检索得分 0.580，条件动作扩散基线为 0.373，抗扰动存活率相近。借助滚动去噪与保算力运行时优化，完整回调在 Jetson Orin NX 上中位数 16.790 ms、p95 为 19.383 ms，均低于 20 ms 控制周期。该策略已部署到 Unitree G1 实机，执行时不需要独立的动作参考跟踪器或外部全身状态估计输入。
PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control
Diffusion models offer flexible motion generation, but translating this flexibility into feedback-responsive humanoid control remains challenging. Hierarchical systems steer motion through references that may exceed a separate tracker's capabilities, leaving recovery and physical execution largely to the tracker. Action-only diffusion generates actions directly but lacks an explicit future-state trajectory for test-time motion objectives. Joint state-action diffusion provides this representation, yet representative controllers often depend on privileged full-body states, and support for learned behavior selection and test-time motion steering remains fragmented. We present PredActor, a predictive action diffusion policy that brings these complementary steering capabilities into one directly executed policy using proprioceptive observations. Conditioned on proprioceptive history and optional task context, PredActor jointly generates executable actions and an internal future-state trajectory. Classifier-free guidance strengthens text-conditioned behavior, while classifier guidance steers predicted states toward test-time objectives. Only actions are executed, without a separate motion-reference tracker or externally estimated full-body states as policy inputs. In simulation, PredActor reaches all 15 destination targets and achieves a text retrieval score of 0.580, compared with 0.373 for conditional action diffusion, with similar observed disturbance survival. To make this guided policy practical onboard, 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, both below the 20 ms control period. We deploy PredActor on a Unitree G1; evaluations across simulation and physical hardware demonstrate text-conditioned motion, disturbance response, joystick control, and semantic interpolation.