Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Yoonwoo, Arora, Raghav, Martín-Martín, Roberto, Stone, Peter, Abbatematteo, Ben, Sung, Yoonchang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911489768554496
author Kim, Yoonwoo
Arora, Raghav
Martín-Martín, Roberto
Stone, Peter
Abbatematteo, Ben
Sung, Yoonchang
author_facet Kim, Yoonwoo
Arora, Raghav
Martín-Martín, Roberto
Stone, Peter
Abbatematteo, Ben
Sung, Yoonchang
contents Robot planning in partially observable environments, where not all objects are known or visible, is a challenging problem, as it requires reasoning under uncertainty through partially observable Markov decision processes. During the execution of a computed plan, a robot may unexpectedly observe task-irrelevant objects, which are typically ignored by naive planners. In this work, we propose incorporating two types of common-sense knowledge: (1) certain objects are more likely to be found in specific locations; and (2) similar objects are likely to be co-located, while dissimilar objects are less likely to be found together. Manually engineering such knowledge is complex, so we explore leveraging the powerful common-sense reasoning capabilities of large language models (LLMs). Our planning and execution framework, CoCo-TAMP, introduces a hierarchical state estimation that uses LLM-guided information to shape the belief over task-relevant objects, enabling efficient solutions to long-horizon task and motion planning problems. In experiments, CoCo-TAMP achieves an average reduction of 62.7% in planning and execution time in simulation, and 72.6% in real-world demonstrations, compared to a baseline that does not incorporate either type of common-sense knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03704
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
Kim, Yoonwoo
Arora, Raghav
Martín-Martín, Roberto
Stone, Peter
Abbatematteo, Ben
Sung, Yoonchang
Robotics
Artificial Intelligence
Robot planning in partially observable environments, where not all objects are known or visible, is a challenging problem, as it requires reasoning under uncertainty through partially observable Markov decision processes. During the execution of a computed plan, a robot may unexpectedly observe task-irrelevant objects, which are typically ignored by naive planners. In this work, we propose incorporating two types of common-sense knowledge: (1) certain objects are more likely to be found in specific locations; and (2) similar objects are likely to be co-located, while dissimilar objects are less likely to be found together. Manually engineering such knowledge is complex, so we explore leveraging the powerful common-sense reasoning capabilities of large language models (LLMs). Our planning and execution framework, CoCo-TAMP, introduces a hierarchical state estimation that uses LLM-guided information to shape the belief over task-relevant objects, enabling efficient solutions to long-horizon task and motion planning problems. In experiments, CoCo-TAMP achieves an average reduction of 62.7% in planning and execution time in simulation, and 72.6% in real-world demonstrations, compared to a baseline that does not incorporate either type of common-sense knowledge.
title Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2603.03704