开放世界中关节物体的自适应移动操作

Adaptive Mobile Manipulation for Articulated Objects In the Open World

January 25, 2024

作者: Haoyu Xiong, Russell Mendonca, Kenneth Shaw, Deepak Pathak

cs.AI

摘要

在家庭等开放式非结构化环境中部署机器人一直是一个长期存在的研究问题。然而，机器人通常只在封闭的实验室环境中进行研究，先前的移动操作工作仅限于拾取-移动-放置，这在这一领域可能只是冰山一角。本文介绍了开放世界移动操作系统，这是一种全栈方法，旨在解决现实中的关节对象操作问题，例如开放式非结构化环境中的真实门、橱柜、抽屉和冰箱。该机器人利用自适应学习框架，通过行为克隆从少量数据中进行初始学习，然后通过在线实践学习处理训练分布之外的新对象。我们还开发了一种低成本的移动操作硬件平台，能够在非结构化环境中进行安全和自主的在线适应，成本约为20,000美元。在我们的实验中，我们在CMU校园的4栋建筑中使用了20个关节对象。对于每个对象，系统在线学习不到一个小时，成功率从BC预训练的50%提高到使用在线适应的95%。视频结果请参见https://open-world-mobilemanip.github.io/

English

Deploying robots in open-ended unstructured environments such as homes has been a long-standing research problem. However, robots are often studied only in closed-off lab settings, and prior mobile manipulation work is restricted to pick-move-place, which is arguably just the tip of the iceberg in this area. In this paper, we introduce Open-World Mobile Manipulation System, a full-stack approach to tackle realistic articulated object operation, e.g. real-world doors, cabinets, drawers, and refrigerators in open-ended unstructured environments. The robot utilizes an adaptive learning framework to initially learns from a small set of data through behavior cloning, followed by learning from online practice on novel objects that fall outside the training distribution. We also develop a low-cost mobile manipulation hardware platform capable of safe and autonomous online adaptation in unstructured environments with a cost of around 20,000 USD. In our experiments we utilize 20 articulate objects across 4 buildings in the CMU campus. With less than an hour of online learning for each object, the system is able to increase success rate from 50% of BC pre-training to 95% using online adaptation. Video results at https://open-world-mobilemanip.github.io/