Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
This work addresses the problem of visual tabletop rearrangement for robotics and AI systems, providing a solution for tidying up with unseen objects, though it is incremental as it builds on existing MCTS methods with a new scoring mechanism.
The paper tackles the tabletop tidying up problem by introducing a novel framework that uses a tidiness score-guided Monte Carlo tree search (TSMCTS) to find optimal arrangements without specifying explicit goals, and it presents a new dataset (TTU) for training and benchmarking, demonstrating successful application across various environments like coffee tables and office desks.
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.