Pushing Through Clutter With Movability Awareness of Blocking Obstacles

2025-02-27

AI Summary

This work addresses the challenge of autonomous robot navigation in environments with unknown, movable obstacles that obstruct planned paths. To overcome limitations of prior approaches—namely reliance on prior obstacle localization and binary movability assumptions—we propose a push-aware planning framework. Our method introduces, for the first time, a continuous movability model that quantifies obstacle displacement feasibility under contact. This is integrated with a semantic visibility graph (SVG) to enable movability-aware global topological planning. Locally, we generate dynamically feasible trajectories via model predictive path integral (MPPI) control coupled with contact force optimization, jointly optimizing motion and physical interaction within rigid-body physics simulation. Experiments demonstrate significant improvements in task success rate and reduced cumulative contact force, outperforming state-of-the-art methods based on binary movability classification.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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

Problem

• Enhancing path-planning with movability awareness
• Overcoming movable obstacle navigation challenges
• Integrating SVG-MPPI for efficient trajectory generation

Innovation

• Semantic Visibility Graph integration
• Model Predictive Path Integral approach
• Physics engine simulation interaction