SoftVTBench：用于物理约束下可变形物体机器人操作的安全感知视觉触觉基准测试
SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)
浏览论文内容
中文总结 AI 辅助
研究物理约束下可变形物体操作，提出SoftVTBench基准测试，通过有限元模拟可变形物体，定义任务套件，分别报告目标成功和安全成功，实现基线并实验，表明仅成功评估高估策略性能，触觉传感可提升安全性。
中文摘要 AI 辅助
可变形物体操作除完成任务外，还需保持安全物理交互。现有基准测试多以成功为导向，很少评估策略执行全程的物理安全性。我们提出SoftVTBench，一个用于物理约束下可变形物体操作的安全感知视觉触觉基准测试。它提供多视图RGB观察等，定义四个匹配任务套件，分别报告目标成功和安全成功，实现基线并实验，结果表明仅成功评估高估策略性能，触觉传感可提升安全性并减少物体变形。SoftVTBench为研究物理交互约束下的视觉触觉可变形操作提供了可重复的基准测试。
英文摘要
Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object stably without slip or drop while avoiding excessive deformation. However, existing manipulation benchmarks are predominantly success-oriented and rarely evaluate whether a policy remains physically safe throughout execution. We present SoftVTBench, a safety-aware visuo-tactile benchmark for physically constrained deformable object manipulation. Built in Isaac Sim with finite-element-simulated deformable objects, SoftVTBench provides multi-view RGB observations, RGB tactile sensing with marker motion, proprioception, and language instructions, and defines four matched task suites over object type (deformable vs. rigid) and variation axis (object vs. spatial). It separately reports Goal Success and Safety Success; the latter additionally requires no drop and peak deformation below a calibrated object-specific threshold, measured from policy-hidden privileged Finite Element Method (FEM) states. We implement pi0.5-based baselines under this protocol. Experiments show that success-only evaluation substantially overstates policy performance, as a large fraction of goal-completing rollouts still violate physical safety. Furthermore, incorporating tactile sensing improves Safety Success (e.g., from 21.4% to 35.6% on object-centric deformable tasks) and reduces object deformation during execution, while maintaining comparable Goal Success. SoftVTBench provides a reproducible benchmark for studying visuo-tactile deformable manipulation under physical interaction constraints.
发表机构
- Tuojing Intelligence（拓景智能）
- Tsinghua University（清华大学）
- King’s College London（伦敦国王学院）
- Southeast University（东南大学）
- Stevens Institute of Technology（史蒂文斯理工学院）
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
- University of Manchester（曼彻斯特大学）
- Simple AI（简单人工智能公司）
- Imperial College London（伦敦帝国学院）
- Carnegie Mellon University（卡内基梅隆大学）
- Zhejiang University（浙江大学）
- Beihang University（北京航空航天大学）
- The University of Hong Kong（香港大学）
机构由 AI 辅助整理，请以论文原文为准。
