# Spark-0：面向机器人灵巧操作的空间对齐触觉预训练扩展

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-22342
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：针对接触丰富灵巧操作中视觉难感知的问题，Spark-0以空间对齐VTLA结合触觉监督与条件控制，并在SparkArena和Ego Humanoid上验证。

# Spark-0：面向机器人灵巧操作的空间对齐触觉预训练扩展

::: v-pre
> 原文链接：[Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation](https://arxiv.org/abs/2610.22342)（arXiv 2610.22342 · 发布日期：2026-10-15）

**Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation**

针对接触丰富灵巧操作中视觉难感知的问题，Spark-0以空间对齐VTLA结合触觉监督与条件控制，并在SparkArena和Ego Humanoid上验证。

## 核心要点

- 通用机器人策略受益于视觉预训练，但难以从图像观察力、顺应性和初始滑移。
- Spark-0用接触图和冻结3D几何教师监督视觉token，并以触觉通路条件化动作专家。
- 构建1,000小时HumanTouch，并与自我中心视频、机器人数据和仿真共同预训练。
- 发布SparkArena；Spark-0在两条赛道平均成功率最高，并在八项聚合指标居首。

**验证范围与局限**：验证包括SparkArena的纯视觉仿真任务、触觉条件真机任务，以及Ego Humanoid Manipulation Benchmark。

## 英文摘要 (Abstract)

Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and incipient slip are hard to observe from images. We present Spark-0, a spatially aligned vision-tactile-language-action (VTLA) model that uses touch in two complementary ways. During pretraining, image-space contact maps derived from tactile gloves, together with features from a frozen 3D geometry teacher, supervise the visual tokens; these objectives are removed at inference. In parallel, a tactile pathway encodes regional force histories and 3D taxel states to condition the action expert. A single checkpoint therefore supports both vision-only and tactile-conditioned deployment. To scale this supervision, we build HumanTouch, a 1,000-hour dataset of full-hand tactile human manipulation, and pretrain Spark-0 on it together with egocentric video, robot data, and simulation. We also release SparkArena, which pairs vision-only simulated tasks with tactile-conditioned real-robot tasks on one dexterous embodiment. Spark-0 achieves the highest mean success rate on both SparkArena tracks and ranks first on all eight aggregate metrics of the Ego Humanoid Manipulation Benchmark. Compared with vision-only pretraining on the same data and compute with touch discarded, retaining the touch of 1,000 hours of HumanTouch raises vision-only success on Ego Humanoid from 52.5% to 71.7%, and success on SparkArena-Real, where touch is also used at deployment, from 44.0% to 52.0%, indicating that touch serves not only as a policy input but also as scalable supervision for dexterous visuomotor pretraining. The Website is available at: https://xsparkai.com/Spark-0.

作者：Tianxing Chen, Wenwei Lin, Chuqiao Lyu, Peicheng Xiang, Junyuan Tang, Tian Nian, Zijian Cai, Kehe Ye, Chenze Yu, Wenxuan Zhu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.22342：Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation](https://arxiv.org/abs/2610.22342)