发表机构
Peking University; The Hong Kong University of Science and Technology; University of California, Berkeley（北京大学; 香港科技大学; 加州大学伯克利分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对机器人抓取难以复刻人类视觉-触觉融合自适应能力的问题，提出AdaDexGrasp视觉-触觉融合抓取框架，通过3D表示融合实现接触感知抓取生成与优化，实验验证其提升了抓取成功率与泛化性。
AI 中文摘要
人类通过无缝整合视觉感知与触觉反馈实现稳定且自适应的抓取，这一能力在机器人系统中仍难以复刻。现有机器人抓取方法主要依赖视觉输入，缺乏接触后的触觉引导自适应机制，限制了鲁棒性与泛化性。为解决该挑战，本文提出一种统一的视觉-触觉融合抓取框架，整合抓取生成、可行性预测与自适应优化。该方法核心是引入高效的视觉-触觉表示，通过将触觉信号与手指身份关联，紧密融合物体几何与触觉反馈。此统一表示支持规划阶段的接触感知抓取位姿生成，以及接触后的触觉引导优化，使系统能推理细粒度的手指-物体交互并动态调整抓取。在仿真与真实环境中的综合实验表明，该方法显著提升了不同物体间的抓取成功率与泛化性。
英文摘要
Humans achieve stable and adaptive grasps by seamlessly integrating visual perception and tactile feedback, a capability that remains challenging to replicate in robotic systems. Existing robotic grasping approaches predominantly rely on visual inputs and lack mechanisms for tactile-guided adaptation after contact, limiting robustness and generalization. To address this challenge, we propose a unified visuo-tactile-fusion grasping framework that integrates grasp generation, feasibility prediction, and adaptive refinement. At its core, our method introduces an efficient visuo-tactile representation that tightly fuses object geometry with tactile feedback by associating tactile signals with finger identities. This unified representation supports contact-aware grasp pose generation during planning and tactile-guided refinement after contact, enabling the system to reason about fine-grained finger-object interactions and adjust grasps dynamically. Comprehensive experiments in both simulation and real-world environments demonstrate that our approach significantly enhances grasp success rates and generalization across diverse objects.
CommentsAccepted at ECCV 2026
