arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00410cs.RO
收藏

具有触觉传感器的机器人操作的仿真到现实迁移

Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory

Tencent Robotics X(腾讯机器人X实验室);Imperial College London(帝国理工学院)

Zihan Ding, Ya-Yen Tsai, Wang Wei Lee, Bidan Huang

摘要:

强化学习(RL)方法已经通过仿真到现实迁移被广泛应用于机器人操作,通常具有本体感受和视觉信息。然而,将触觉感知结合到RL中用于接触丰富的任务缺乏调查。在本文中,我们模拟的触觉传感器,并研究其反馈的影响,在基于RL的机器人控制通过zero-shot模拟到真实的方法与域随机化。我们证明,学习和控制与触觉传感器阵列的反馈在抓手,无论是在模拟和现实中,可以提高抓地力的稳定性,从而导致显着改善机器人的操作性能的开门任务。在现实世界的实验中,车门打开角度增加了45%,平均为转移政策与触觉感知比那些没有它。

英文摘要:

Reinforcement Learning (RL) methods have been widely applied for robotic manipulations via sim-to-real transfer, typically with proprioceptive and visual information. However, the incorporation of tactile sensing into RL for contact-rich tasks lacks investigation. In this paper, we model a tactile sensor in simulation and study the effects of its feedback in RL-based robotic control via a zero-shot sim-to-real approach with domain randomization. We demonstrate that learning and controlling with feedback from tactile sensor arrays at the gripper, both in simulation and reality, can enhance grasping stability, which leads to a significant improvement in robotic manipulation performance for a door opening task. In real-world experiments, the door open angle was increased by 45% on average for transferred policies with tactile sensing over those without it.

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。

↑