# TaRL：从触觉演示中学习通用且物理的奖励

> 原文链接：https://robotics.hellobike.com/papers/2026-09-29-2609-36785
> 频道：papers | 更新日期：2026-09-29 | 标签：arxiv, cs.RO
> 核心摘要：TaRL从触觉变形图演示学习任务进度奖励，在仿真和真实操作任务中提升强化学习效率与成功率。

# TaRL：从触觉演示中学习通用且物理的奖励

::: v-pre
> 原文链接：[TaRL: Learning General and Physical Rewards from Tactile Demonstrations](https://arxiv.org/abs/2609.36785)（arXiv 2609.36785 · 发布日期：2026-09-29）

**TaRL: Learning General and Physical Rewards from Tactile Demonstrations**

TaRL从触觉变形图演示学习任务进度奖励，在仿真和真实操作任务中提升强化学习效率与成功率。

## 核心要点

- 接触丰富操作需精确接触、稳定抓握和定向施力，稀疏或密集奖励设计限制RL表现。
- TaRL输入触觉变形图序列，从成功与失败演示中回归任务完成进度以形成奖励。
- 该奖励捕捉局部机器人-物体交互，反馈牢固抓握和定向施力，并对物体位置变化鲁棒。
- 仿真四任务、真实两任务均有提升；与视觉奖励结合进一步提升，并提供项目页。

**验证范围与局限**：验证范围为仿真中的四个操作任务和真实世界中的两个操作任务。

## 英文摘要 (Abstract)

Contact-rich manipulation requires robots to sequence precise contacts, maintain stable grasps, and apply directed forces. Reinforcement learning (RL) can acquire such behaviors automatically, but its performance hinges on reward design: sparse rewards reduce the learning efficiency, while dense rewards are hard to specify. Visual reward learning addresses this by inferring rewards from action-free demonstrations. Because it conditions only on visual observations, it fails to capture rewards beyond visual goals. We propose Tactile Reward Learning (TaRL), a framework that learns rewards from tactile demonstrations. TaRL takes a sequence of tactile deformation maps as input, and regresses task-completion progress from both successful and failed demonstrations. Because TaRL captures local robot-object interaction, it provides informative feedback to learn firm grasps and correctly directed forces; meanwhile, it is robust to changes in scene layout such as object position. We evaluate TaRL on four manipulation tasks in simulation and two in the real world. Used as a shaping reward, it substantially improves both sample efficiency and final success rate, raising success on Nut threading from 34% to 56% in simulation and on cube pickup from 37% to 97% in the real world. Combining tactile with visual rewards improves performance further. TaRL also generalizes across object instances: trained on box placement and directly deployed to can placement, it significantly improves policy learning on the new task. Project page is available at https://embodiedai-ntu.github.io/tarl.

作者：Po-Yi Wu, Dao-Jan Chang, Shang-Ya Hsiao, Hong-Ming Chen, Yu-Cheng Su, Tsung-Wei Ke
:::

## 原始参考来源 (Sources)

- [arXiv 2609.36785：TaRL: Learning General and Physical Rewards from Tactile Demonstrations](https://arxiv.org/abs/2609.36785)