# TactileStep：用于调节人形机器人运动中足-地相互作用的足底触觉学习

> 原文链接：https://robotics.hellobike.com/papers/2026-09-24-2609-28959
> 频道：papers | 更新日期：2026-09-24 | 标签：arxiv, cs.RO
> 核心摘要：TactileStep通过对齐足底压力仿真与真实鞋垫并用阶段感知奖励，在仿真和Unitree G1多地形上改善落脚与支撑。

# TactileStep：用于调节人形机器人运动中足-地相互作用的足底触觉学习

::: v-pre
> 原文链接：[TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion](https://arxiv.org/abs/2609.28959)（arXiv 2609.28959 · 发布日期：2026-09-24）

**TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion**

TactileStep通过对齐足底压力仿真与真实鞋垫并用阶段感知奖励，在仿真和Unitree G1多地形上改善落脚与支撑。

## 核心要点

- 动机：跑酷策略虽能完成任务，但可能掩盖重落地、边缘接触和支撑不稳。
- 方法：将足底压力感知引入控制，对齐触觉仿真与真实压力鞋垫特征。
- 训练：结合触觉与运动线索识别足接触阶段，施加阶段感知奖励。
- 结果：峰值落地力最多降48.8%，噪声最多降30.1 dB，接触面积最多增23.8%。

**验证范围与局限**：验证范围为仿真及一台Unitree G1人形机器人在多种地形上的评估。

## 英文摘要 (Abstract)

Humanoid parkour policies can traverse various terrains, but task completion may mask challenges of harsh landings, edge contacts, and unstable stance contacts. Humans naturally regulate foot-terrain interaction through tactile feedback, modulating contact compliance according to terrain stiffness. This highlights a key domain gap between humans and humanoid robots: the absence of rich tactile sensing in most humanoid systems. We address this problem with TactileStep, a deployable tactile learning framework that brings sole pressure sensing into humanoid locomotion control for softer touchdowns and more stable support. TactileStep aligns tactile simulation with the real pressure insole, allowing the policy to learn from the same contact features available on hardware. During training, we use tactile and motion cues to recognize different foot-contact phases and apply phase-aware rewards that encourage safer landing and more stable stance. Evaluated in simulation and on a Unitree G1 humanoid across diverse terrains, TactileStep reduces peak touchdown force by up to 48.8% and peak A-weighted impact noise by up to 30.1 dB over a strong perceptive baseline, while increasing stance contact area by up to 23.8%.

作者：Zizhuo Wang, Ming-ju Lee, Shaoting Zhu, Haozhe Lou, Hang Zhao, Yiming Li
:::

## 原始参考来源 (Sources)

- [arXiv 2609.28959：TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion](https://arxiv.org/abs/2609.28959)