arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08560cs.RO
收藏

CONTACT: 基于接触感知的触觉学习用于机器人拆解

CONTACT: CONtact-aware TACTile Learning for Robotic Disassembly

Department of Industrial Engineering, Purdue University(工业工程系,普渡大学);Department of Mechanical Engineering, Texas A&M University(机械工程系,德克萨斯农工大学)

Yosuke Saka, Jyun-Chi Hu, Adeesh Desai, Zhiyuan Zhang, Bihao Zhang, Quan Khanh Luu, Md Rakibul Islam Prince, Minghui Zheng, Yu She

AI总结:

CONTACT通过对比视觉、触觉RGB和触觉力场三种感知配置,发现触觉力场在机器人拆解任务中表现最佳,尤其在接触依赖和变形场景中效果显著。

摘要:

机器人拆解涉及丰富的接触交互,在此过程中,成功的操作不仅取决于几何对齐,还依赖于力依赖的状态转换。尽管基于视觉的策略在结构化环境中表现良好,但其可靠性在高精度、接触主导或变形场景中往往会下降。在本工作中,我们通过仿真和实际实验系统地研究了触觉感知在机器人拆解中的作用。我们构建了五个具有递增几何约束和提取难度的刚体拆解任务,在仿真中进行测试。我们进一步设计了五个实际任务,包括三个刚性和两个变形场景,以评估接触依赖的操作。在统一的学习框架中,我们比较了三种感知配置:仅视觉、视觉+触觉RGB(TacRGB)和视觉+触觉力场(TacFF)。在仿真和实际实验中,基于TacFF的策略始终实现了最高的成功率,特别是在接触依赖和变形场景中表现尤为突出。值得注意的是,简单融合TacRGB和TacFF的效果不如单独使用任一模态,表明简单的拼接可能会稀释任务相关的力信息。我们的结果表明,触觉感知在机器人拆解中扮演着关键且任务依赖的角色,结构化的力场表示在接触主导的场景中特别有效。

英文摘要:

Robotic disassembly involves contact-rich interactions in which successful manipulation depends not only on geometric alignment but also on force-dependent state transitions. While vision-based policies perform well in structured settings, their reliability often degrades in tight-tolerance, contact-dominated, or deformable scenarios. In this work, we systematically investigate the role of tactile sensing in robotic disassembly through both simulation and real-world experiments. We construct five rigid-body disassembly tasks in simulation with increasing geometric constraints and extraction difficulty. We further design five real-world tasks, including three rigid and two deformable scenarios, to evaluate contact-dependent manipulation. Within a unified learning framework, we compare three sensing configurations: Vision Only, Vision + tactile RGB (TacRGB), and Vision + tactile force field (TacFF). Across both simulation and real-world experiments, TacFF-based policies consistently achieve the highest success rates, with particularly notable gains in contact-dependent and deformable settings. Notably, naive fusion of TacRGB and TacFF underperforms either modality alone, indicating that simple concatenation can dilute task-relevant force information. Our results show that tactile sensing plays a critical, task-dependent role in robotic disassembly, with structured force-field representations being particularly effective in contact-dominated scenarios.

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。

↑