arXiv cs.CL· Ziyong Wang, Yupei Lin, Runxuan Huang, Liang Lin, Dongyu Zhang, Guangrun Wang·· 12 小时前AI 评分58
GPT-6-Astra 在触觉操作任务上超越视觉-触觉-语言-动作模型
GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models
AI 导读
论文提出 GPT-as-Tactile-Policy 方法，将专家演示总结为任务指引和触觉参考，由 GPT-6-Astra 结合多模态观测与交互历史生成控制指令。该方法无需额外的机器人专用预训练或逐任务策略微调，在五个 UniVTAC 任务上平均成功率达 93.8%，与当前最优策略相当，部分任务更高；在 Insert Hole 任务上，触觉反馈将成功率从 31% 提升到 99%。
正文 · 原文
Abstract:General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide action remains underexplored. We investigate this question using contact-rich manipulation as a representative testbed, examining tactile understanding as a concrete instance of this broader capability. Contact-rich manipulation requires interpreting tactile feedback and adjusting actions after obstruction. Existing learned tactile policies acquire these capabilities through specialized pretraining and per-task optimization, with substantial data and training costs. We present GPT-as-Tactile-Policy, which summarizes expert demonstrations into task guidance and tactile references for contact assessment and corrective action. GPT-6-Astra combines this context with multimodal observations and interaction history to generate control commands and adjust actions through contact feedback. Without additional robotics-specific pretraining or per-task policy fine-tuning, our method achieves 93.8\% mean success across five UniVTAC tasks. Overall performance is comparable to state-of-the-art policies, with higher success on selected tasks. On Insert Hole, tactile feedback improves success from 31\% to 99\%. Execution analysis further demonstrates contact-guided probing and correction, supporting manipulation progress through explicit expert experience and online feedback.
| Comments: | this https URL |
| Subjects: | Robotics (cs.RO); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.28457 [cs.RO] |
| (or arXiv:2610.28457v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28457 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ziyong Wang [view email]
[v1]
Tue, 20 Oct 2026 16:15:02 UTC (2,348 KB)
来源：arXiv cs.CL · arxiv.org