仅靠指尖单轴力和关节感知，实现无需视觉的可靠多指抓取。
Why Look at It at All?: Vision-Free Multifingered Blind Grasping Using Uniaxial Fingertip Force Sensing
- 用教师-学生框架，从仿真中学习抓取策略并迁移到真实硬件。
- 在18种物体上实测成功率达98.3%，涵盖分布内与分布外物体。
- 适合追求低成本、高鲁棒性的实际机器人抓取系统。
受限感知下的抓取仍是现实机器人操作中的核心挑战，因视觉与高分辨率触觉传感器常带来成本高、易损、集成复杂等问题。本文证明，仅依赖单轴指尖力反馈与关节本体感知，即可实现可靠的多指抓取，无需视觉或多元/触觉传感。为此，我们采用高效的教师-学生训练流程：由强化学习训练的教师利用仅存在于仿真中的完整观测生成示范，通过知识蒸馏训练一个基于Transformer的学生策略，该策略仅使用真实部署时可用的有限传感模态。我们在真实硬件上对18种物体进行了验证，包括分布内与分布外情况，整体抓取成功率高达98.3%。结果表明该方法具有强鲁棒性与泛化能力，显著降低实际抓取系统的传感需求。
原文摘要 · Abstract (English)
Grasping under limited sensing remains a fundamental challenge for real-world robotic manipulation, as vision and high-resolution tactile sensors often introduce cost, fragility, and integration complexity. This work demonstrates that reliable multifingered grasping can be achieved under extremely minimal sensing by relying solely on uniaxial fingertip force feedback and joint proprioception, without vision or multi-axis/tactile sensing. To enable such blind grasping, we employ an efficient teacher-student training pipeline in which a reinforcement-learned teacher exploits privileged simulation-only observations to generate demonstrations for distilling a transformer-based student policy operating under partial observation. The student policy is trained to act using only sensing modalities available at real-world deployment. We validate the proposed approach on real hardware across 18 objects, including both in-distribution and out-of-distribution cases, achieving a 98.3~$\%$ overall grasp success rate. These results demonstrate strong robustness and generalization beyond the simulation training distribution, while significantly reducing sensing requirements for real-world grasping systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。