arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.10063cs.RO
收藏

面向交互式在线学习的基于非参数方法的以物体为中心的表示

Object-centric Representations for Interactive Online Learning with Non-Parametric Methods

University of California, San Diego(加州大学圣地亚哥分校)

Nikhil U. Shinde, Jacob Johnson, Sylvia Herbert, Michael C. Yip

AI总结:

针对非结构化环境下机器人交互学习的需求,提出将以物体为中心的表示用于交互式在线学习,通过转换动作到物体坐标系提升推理能力,实现可扩展的机器人-物体交互在线学习,并在多未知物体机械臂导航任务中验证了效果。

摘要:

大型基于离线学习的模型已能让机器人在各类任务中成功与物体交互,但这类模型依赖于一致性较高的结构化环境。针对更非结构化的场景,需要在线学习模块来收集并估计环境中物体的信息,以实现成功交互。遗憾的是,贝叶斯非参数模型这类在线学习方法难以应对环境变化,而环境变化往往是交互类任务的预期结果。我们提出将以物体为中心的表示用于交互式在线学习,该表示通过将机器人动作转换到物体坐标系下生成。我们验证了切换到这一任务相关空间能提升对在线收集的训练数据的推理能力,实现可扩展的机器人-物体交互在线学习。我们通过让机械臂在存在多个未知物体的环境中成功导航且不违反交互约束,展示了该方法的有效性。

英文摘要:

Large offline learning-based models have enabled robots to successfully interact with objects for a wide variety of tasks. However, these models rely on fairly consistent structured environments. For more unstructured environments, an online learning component is necessary to gather and estimate information about objects in the environment in order to successfully interact with them. Unfortunately, online learning methods like Bayesian non-parametric models struggle with changes in the environment, which is often the desired outcome of interaction-based tasks. We propose using an object-centric representation for interactive online learning. This representation is generated by transforming the robot's actions into the object's coordinate frame. We demonstrate how switching to this task-relevant space improves our ability to reason with the training data collected online, enabling scalable online learning of robot-object interactions. We showcase our method by successfully navigating a manipulator arm through an environment with multiple unknown objects without violating interaction-based constraints.

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。

↑