Interleaving Monte Carlo Tree Search and Self-Supervised Learning for Object Retrieval in Clutter
Interleaving Monte Carlo Tree Search and Self-Supervised Learning for Object Retrieval in Clutter
复制标题
DOI：
10.1109/icra46639.2022.9812132
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Baichuan Huang;Teng Guo;Abdeslam Boularias;Jingjin Yu
中科院分区：
文献类型：
--
作者：
Baichuan Huang;Teng Guo;Abdeslam Boularias;Jingjin Yu
在这项研究中，处理杂物中对象检索的任务，我们开发了一个机器人学习框架，在该框架中，首先应用了蒙特卡洛树搜索（MCT），以启用深层神经网络（DNN）来学习机器人之间的复杂相互作用手臂和一个包含许多物体的复杂场景，允许DNN部分克隆MCT的行为。努力。体现系统2→系统1的学习理念，由卡尼曼（Kahneman）提出的学习理念，在那里学习的知识正确，可以帮助加快速度随着时间的推移，可以在https://github.com/arc-l/more上找到耗时的决策过程。
In this study, working with the task of object retrieval in clutter, we have developed a robot learning framework in which Monte Carlo Tree Search (MCTS) is first applied to enable a Deep Neural Network (DNN) to learn the intricate interactions between a robot arm and a complex scene containing many objects, allowing the DNN to partially clone the behavior of MCTS. In turn, the trained DNN is integrated into MCTS to help guide its search effort. We call this approach learning-guided Monte Carlo tree search for Object REtrieval (MORE), which delivers significant computational efficiency gains and added solution optimality. MORE is a self-supervised robotics framework/pipeline capable of working in the real world that successfully embodies the System 2 → System 1 learning philosophy proposed by Kahneman, where learned knowledge, used properly, can help greatly speed up a time-consuming decision process over time. Videos and supplementary material can be found at https://github.com/arc-l/more.