arXiv 2602.100932026-02-10cs.RO

UniVTAC：一种用于视觉-触觉操作数据生成、学习和评估的统一仿真平台

UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking

ScaleLab, Shanghai Jiao Tong University（上海交通大学ScaleLab）；D-Robotics；ViTai Robotics；The University of Hong Kong（香港大学）；Nanjing University（南京大学）；Shenzhen University（深圳大学）；Wuhan University（武汉大学）；Fudan University（复旦大学）；Tsinghua University（清华大学）

Baijun Chen, Weijie Wan, Tianxing Chen, Xianda Guo, Congsheng Xu, Yuanyang Qi, Haojie Zhang, Longyan Wu, Tianling Xu, Zixuan Li, Yizhe Wu, Rui Li, Xiaokang Yang… 展开作者

Baijun Chen, Weijie Wan, Tianxing Chen, Xianda Guo, Congsheng Xu, Yuanyang Qi, Haojie Zhang, Longyan Wu, Tianling Xu, Zixuan Li, Yizhe Wu, Rui Li, Xiaokang Yang, Ping Luo, Wei Sui, Yao Mu

备注：: Website: https://univtac.github.io/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

UniVTAC提出了一种统一的视觉-触觉数据生成平台，通过训练触觉中心的编码器和基准任务提升机器人操作的成功率。

摘要：

机器人操作在视觉-语言-动作（VLA）策略的推动下取得了快速进展。然而，视觉-触觉感知对于接触丰富的操作至关重要，例如插入任务仅依靠视觉完成是困难的。同时，在物理世界中获取大规模且可靠的触觉数据仍然成本高且具有挑战性，缺乏统一的评估平台进一步限制了策略学习和系统分析。为了解决这些挑战，我们提出了UniVTAC，一个基于仿真的视觉-触觉数据合成平台，支持三种常用的视觉-触觉传感器，能够可扩展和可控地生成信息丰富的接触交互。基于此平台，我们引入了UniVTAC编码器，该编码器在大规模仿真合成数据上训练，通过设计的监督信号提供以触觉为中心的视觉-触觉表示，用于下游操作任务。此外，我们还提出了UniVTAC基准，包含八个代表性的视觉-触觉操作任务，用于评估触觉驱动的策略。实验结果表明，整合UniVTAC编码器在UniVTAC基准上将平均成功率提高了17.1%，而现实世界中的机器人实验进一步证明了任务成功度提高了25%。我们的网页可在https://univtac.github.io/上访问。

英文摘要：

Robotic manipulation has seen rapid progress with vision-language-action (VLA) policies. However, visuo-tactile perception is critical for contact-rich manipulation, as tasks such as insertion are difficult to complete robustly using vision alone. At the same time, acquiring large-scale and reliable tactile data in the physical world remains costly and challenging, and the lack of a unified evaluation platform further limits policy learning and systematic analysis. To address these challenges, we propose UniVTAC, a simulation-based visuo-tactile data synthesis platform that supports three commonly used visuo-tactile sensors and enables scalable and controllable generation of informative contact interactions. Based on this platform, we introduce the UniVTAC Encoder, a visuo-tactile encoder trained on large-scale simulation-synthesized data with designed supervisory signals, providing tactile-centric visuo-tactile representations for downstream manipulation tasks. In addition, we present the UniVTAC Benchmark, which consists of eight representative visuo-tactile manipulation tasks for evaluating tactile-driven policies. Experimental results show that integrating the UniVTAC Encoder improves average success rates by 17.1% on the UniVTAC Benchmark, while real-world robotic experiments further demonstrate a 25% improvement in task success. Our webpage is available at https://univtac.github.io/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。