Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 43 references that are in the map. First posted on arXiv 18 Jun 2025.
Builds on
15 of 43 references.
References · 15
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2018On Evaluation of Embodied Navigation Agentscited by 547
- 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
- 2022Rapid Locomotion via Reinforcement Learningcited by 168
- 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 141
- 2019DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactionscited by 63
- 2019HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulatorscited by 55
- 2020ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulationcited by 49
- 2024Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robotscited by 48
- 2021Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigationcited by 22
- 2021Pushing it out of the Way: Interactive Visual Navigationcited by 16
- 2019Let's Push Things Forward: A Survey on Robot Pushingcited by 14
3 more
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning
- 2024Combining Planning and Diffusion for Mobility with Unknown Dynamics
- 2025Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors
- 2025Interactive Navigation for Legged Manipulators with Learned Arm-Pushing Controller
- 2025Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation
- 2026DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects ↗
- 2024Predictive Reachability for Embodiment Selection in Mobile Manipulation Behaviors
- 2025Push Smarter, Not Harder: Hierarchical RL-Diffusion Policy for Efficient Nonprehensile Manipulation