Navigation Among Movable Obstacles (NAMO) poses a challenge for traditional path-planning methods when obstacles block the path, requiring push actions to reach the goal. We propose a framework that enables movability-aware planning to overcome this challenge without relying on explicit obstacle placement. Our framework integrates a global Semantic Visibility Graph and a local Model Predictive Path Integral (SVG-MPPI) approach to efficiently sample rollouts, taking into account the continuous range of obstacle movability. A physics engine is adopted to simulate the interaction result of the rollouts with the environment, and generate trajectories that minimize contact force. In qualitative and quantitative experiments, SVG-MPPI outperforms the existing paradigm that uses only binary movability for planning, achieving higher success rates with reduced cumulative contact forces. Our code is available at: https://github.com/tud-amr/SVG-MPPI
@article{arxiv.2502.20106,
title = {Pushing Through Clutter With Movability Awareness of Blocking Obstacles},
author = {Joris J. Weeda and Saray Bakker and Gang Chen and Javier Alonso-Mora},
journal= {arXiv preprint arXiv:2502.20106},
year = {2025}
}
Comments
7 pages (6+1), 5 images, 1 table, preprint version of accepted paper at ICRA 2025