整洁度评分引导的蒙特卡洛树搜索用于视觉桌面重排
Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
AI总结：
本文提出TSMCTS框架，结合整洁度判别器与蒙特卡洛树搜索，仅用RGB-D相机解决桌面整洁问题，无需指定目标配置，在多种环境中验证有效。
摘要：
本文提出了一种新颖的框架——整洁度评分引导的蒙特卡洛树搜索（TSMCTS），旨在仅使用RGB-D相机解决桌面整洁问题。我们解决了桌面整洁问题中的两个主要难题：（1）缺乏公开数据集和基准，（2）难以指定未见物体的目标配置。针对前者，我们提出了桌面整洁（TTU）数据集，这是一个在仿真环境中收集的结构化数据集。利用该数据集，我们训练了一个基于视觉的判别器，能够预测整洁度评分。该判别器能够一致地评估未见配置（包括真实世界场景）的整洁程度。针对第二个问题，我们采用蒙特卡洛树搜索（MCTS）来寻找整洁轨迹，而无需指定明确目标。我们证明，基于MCTS的规划器无需提供具体目标，即可利用整洁度评分作为指导，找到多样化的整洁配置。因此，我们提出了TSMCTS，它将整洁度判别器与基于MCTS的整洁规划器相结合，以找到最优的整洁排列。TSMCTS已成功在多种环境中展示了其能力，包括咖啡桌、餐桌、办公桌和浴室。TTU数据集可在以下网址获取：https://github.com/rllab-snu/TTU-Dataset。
英文摘要：
In this paper, we present the tidiness score-guided Monte Carlo tree search (TSMCTS), a novel framework designed to address the tabletop tidying up problem using only an RGB-D camera. We address two major problems for tabletop tidying up problem: (1) the lack of public datasets and benchmarks, and (2) the difficulty of specifying the goal configuration of unseen objects. We address the former by presenting the tabletop tidying up (TTU) dataset, a structured dataset collected in simulation. Using this dataset, we train a vision-based discriminator capable of predicting the tidiness score. This discriminator can consistently evaluate the degree of tidiness across unseen configurations, including real-world scenes. Addressing the second problem, we employ Monte Carlo tree search (MCTS) to find tidying trajectories without specifying explicit goals. Instead of providing specific goals, we demonstrate that our MCTS-based planner can find diverse tidied configurations using the tidiness score as a guidance. Consequently, we propose TSMCTS, which integrates a tidiness discriminator with an MCTS-based tidying planner to find optimal tidied arrangements. TSMCTS has successfully demonstrated its capability across various environments, including coffee tables, dining tables, office desks, and bathrooms. The TTU dataset is available at: https://github.com/rllab-snu/TTU-Dataset.
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。
