LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Haonan, Gao, Kai, Boyalakuntla, Kowndinya, Lee, Alex, Huang, Baichuan, Kumar, Harish Udhaya, Yu, Jinjin, Boularias, Abdeslam
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917795947610112
author Chang, Haonan
Gao, Kai
Boyalakuntla, Kowndinya
Lee, Alex
Huang, Baichuan
Kumar, Harish Udhaya
Yu, Jinjin
Boularias, Abdeslam
author_facet Chang, Haonan
Gao, Kai
Boyalakuntla, Kowndinya
Lee, Alex
Huang, Baichuan
Kumar, Harish Udhaya
Yu, Jinjin
Boularias, Abdeslam
contents We introduce a novel approach to the executable semantic object rearrangement problem. In this challenge, a robot seeks to create an actionable plan that rearranges objects within a scene according to a pattern dictated by a natural language description. Unlike existing methods such as StructFormer and StructDiffusion, which tackle the issue in two steps by first generating poses and then leveraging a task planner for action plan formulation, our method concurrently addresses pose generation and action planning. We achieve this integration using a Language-Guided Monte-Carlo Tree Search (LGMCTS). Quantitative evaluations are provided on two simulation datasets, and complemented by qualitative tests with a real robot.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15821
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement
Chang, Haonan
Gao, Kai
Boyalakuntla, Kowndinya
Lee, Alex
Huang, Baichuan
Kumar, Harish Udhaya
Yu, Jinjin
Boularias, Abdeslam
Robotics
We introduce a novel approach to the executable semantic object rearrangement problem. In this challenge, a robot seeks to create an actionable plan that rearranges objects within a scene according to a pattern dictated by a natural language description. Unlike existing methods such as StructFormer and StructDiffusion, which tackle the issue in two steps by first generating poses and then leveraging a task planner for action plan formulation, our method concurrently addresses pose generation and action planning. We achieve this integration using a Language-Guided Monte-Carlo Tree Search (LGMCTS). Quantitative evaluations are provided on two simulation datasets, and complemented by qualitative tests with a real robot.
title LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement
topic Robotics
url https://arxiv.org/abs/2309.15821