# HumanoidTTT：用于高效人形控制的测试时能力复用

> 原文链接：https://robotics.hellobike.com/papers/2026-09-18-2610-00198
> 频道：papers | 更新日期：2026-09-18 | 标签：arxiv, cs.RO
> 核心摘要：HumanoidTTT面向持续人形控制，测试时复用经验证完整动作，并在实验中验证效率与安全性。

# HumanoidTTT：用于高效人形控制的测试时能力复用

::: v-pre
> 原文链接：[HumanoidTTT: Test-Time Capability Reuse for Efficient Humanoid Control](https://arxiv.org/abs/2610.00198)（arXiv 2610.00198 · 发布日期：2026-09-18）

**HumanoidTTT: Test-Time Capability Reuse for Efficient Humanoid Control**

HumanoidTTT面向持续人形控制，测试时复用经验证完整动作，并在实验中验证效率与安全性。

## 核心要点

- 持续部署中相同动作能力会反复请求，但中间动作会改变入口状态，盲目重放存在安全风险。
- 提出选择性全动作复用，仅从认证适用入口状态直接复用经验证完整动作，跳过重新生成。
- 提出测试时能力整合，用后续部署复用反馈在有界全动作存储中保留合格能力。
- 实验显示零不安全接受、端到端较重新生成加速16.4倍；代码和网站已公开。

## 英文摘要 (Abstract)

Recent advances in motion generation and whole-body tracking have enabled humanoid robots to execute increasingly diverse motions, yet the same motion capabilities may be requested repeatedly during continual deployment. Reliable reuse is challenging because intervening motions can change the robot's entry state, making previously successful motions unsafe to replay blindly. Meanwhile, validated capabilities accumulate during deployment, while bounded storage requires deciding which ones are worth retaining. To address these challenges, we present HumanoidTTT, a framework for test-time capability reuse in continual humanoid control. Specifically, we introduce Selective Full-Motion Reuse, which authorizes direct reuse of validated complete motions only from certified applicable entry states, allowing accepted reuse to bypass fresh generation. We further introduce Test-Time Capability Consolidation, which adapts which qualified capabilities persist in a bounded Full-Motion Store using subsequent deployment reuse as feedback. Experiments demonstrate zero unsafe accepts and a 16.4$\times$ end-to-end speedup over fresh generation, while online consolidation improves avoided generator calls by 13.2 per 200 requests over its frozen counterpart. Overall, HumanoidTTT enables reliable and efficient reuse of validated motion capabilities while adaptively retaining useful capabilities throughout continual deployment. Code: https://github.com/AIGeeksGroup/HumanoidTTT. Website: https://aigeeksgroup.github.io/HumanoidTTT.

作者：Yang Jingtai, Wu, Yining, Yanjun Li, Zeyu Zhang, Hao Tang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.00198：HumanoidTTT: Test-Time Capability Reuse for Efficient Humanoid Control](https://arxiv.org/abs/2610.00198)