Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Taegeun, Hwang, Jiwoo, Jeong, Jeil, Yoon, Minsung, Yoon, Sung-Eui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912438072377344
author Yang, Taegeun
Hwang, Jiwoo
Jeong, Jeil
Yoon, Minsung
Yoon, Sung-Eui
author_facet Yang, Taegeun
Hwang, Jiwoo
Jeong, Jeil
Yoon, Minsung
Yoon, Sung-Eui
contents We propose a hierarchical reinforcement learning (HRL) framework for efficient Navigation Among Movable Obstacles (NAMO) using a mobile manipulator. Our approach combines interaction-based obstacle property estimation with structured pushing strategies, facilitating the dynamic manipulation of unforeseen obstacles while adhering to a pre-planned global path. The high-level policy generates pushing commands that consider environmental constraints and path-tracking objectives, while the low-level policy precisely and stably executes these commands through coordinated whole-body movements. Comprehensive simulation-based experiments demonstrate improvements in performing NAMO tasks, including higher success rates, shortened traversed path length, and reduced goal-reaching times, compared to baselines. Additionally, ablation studies assess the efficacy of each component, while a qualitative analysis further validates the accuracy and reliability of the real-time obstacle property estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15380
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning
Yang, Taegeun
Hwang, Jiwoo
Jeong, Jeil
Yoon, Minsung
Yoon, Sung-Eui
Robotics
We propose a hierarchical reinforcement learning (HRL) framework for efficient Navigation Among Movable Obstacles (NAMO) using a mobile manipulator. Our approach combines interaction-based obstacle property estimation with structured pushing strategies, facilitating the dynamic manipulation of unforeseen obstacles while adhering to a pre-planned global path. The high-level policy generates pushing commands that consider environmental constraints and path-tracking objectives, while the low-level policy precisely and stably executes these commands through coordinated whole-body movements. Comprehensive simulation-based experiments demonstrate improvements in performing NAMO tasks, including higher success rates, shortened traversed path length, and reduced goal-reaching times, compared to baselines. Additionally, ablation studies assess the efficacy of each component, while a qualitative analysis further validates the accuracy and reliability of the real-time obstacle property estimation.
title Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning
topic Robotics
url https://arxiv.org/abs/2506.15380