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

2025/06/18 by T. Yang, Yang, Taegeun, Jiwoo Hwang +6
Computer Science · #FOS: Computer and information sciences #Robotic Path Planning Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2506.15380

openalex publication_date 2025/06/18 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing
• Rapid Locomotion via Reinforcement Learning
• Pushing it out of the Way: Interactive Visual Navigation
• Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation
• Affordance-Based Mobile Robot Navigation Among Movable Obstacles
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators
• DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions
• On Evaluation of Embodied Navigation Agents
• Proximal Policy Optimization Algorithms
• Preparing for the Unknown: Learning a Universal Policy with Online System Identification
• Manipulator Inverse Kinematic Solutions Based on Vector Formulations and Damped Least-Squares Methods

Related

• HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators
• Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors
• Obstacle-aware Waypoint Generation for Long-range Guidance of Deep-Reinforcement-Learning-based Navigation Approaches
• Interactive Navigation for Legged Manipulators with Learned Arm-Pushing Controller
• Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning