arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11270cs.ROcs.LG
收藏

COCOI:面向可推广非平面推送的接触感知在线上下文推理

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing

Everyday Robots, X The Moonshot Factory(日常机器人,X登月工厂);Robotics at Google(谷歌机器人);University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学)

Zhuo Xu, Wenhao Yu, Alexander Herzog, Wenlong Lu, Chuyuan Fu, Masayoshi Tomizuka, Yunfei Bai, C. Karen Liu, Daniel Ho

摘要:

由于难以理解复杂的接触物理,一般的接触丰富的操作问题是机器人技术中长期存在的挑战。深度强化学习(RL)在解决机器人操作任务方面显示出巨大的潜力。然而,现有的强化学习策略对具有不同动力学特性的环境的适应性有限,这是解决许多接触丰富的操作任务的关键。在这项工作中,我们提出了接触感知的在线上下文推理(COCOI),这是一种深度RL方法,使用丰富的接触交互在线编码动态属性的上下文嵌入。我们研究这种方法的基础上,一个新的和具有挑战性的非平面推动任务,其中机器人使用单目摄像头图像和腕力扭矩传感器读数,推动一个对象到目标位置,同时保持直立。我们进行了大量的实验,以证明COCOI在模拟中的各种设置和动力学特性中的能力,以及在真实机器人上的仿真到现实迁移场景中的能力(视频:https://youtu.be/nrmJYksh1Kc)

英文摘要:

General contact-rich manipulation problems are long-standing challenges in robotics due to the difficulty of understanding complicated contact physics. Deep reinforcement learning (RL) has shown great potential in solving robot manipulation tasks. However, existing RL policies have limited adaptability to environments with diverse dynamics properties, which is pivotal in solving many contact-rich manipulation tasks. In this work, we propose Contact-aware Online COntext Inference (COCOI), a deep RL method that encodes a context embedding of dynamics properties online using contact-rich interactions. We study this method based on a novel and challenging non-planar pushing task, where the robot uses a monocular camera image and wrist force torque sensor reading to push an object to a goal location while keeping it upright. We run extensive experiments to demonstrate the capability of COCOI in a wide range of settings and dynamics properties in simulation, and also in a sim-to-real transfer scenario on a real robot (Video: https://youtu.be/nrmJYksh1Kc)

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。

↑