Pushing Through Clutter With Movability Awareness of Blocking Obstacles

TL;DR

This paper introduces a movability-aware planning framework for navigation among movable obstacles, combining semantic visibility graphs and predictive path sampling to improve success rates and reduce contact forces in obstacle manipulation tasks.

Contribution

It presents a novel SVG-MPPI framework that integrates semantic visibility and physics-based simulation for enhanced movability-aware navigation planning.

Findings

Outperforms existing binary movability methods in success rate

Reduces cumulative contact forces during obstacle interaction

Demonstrates effectiveness in both qualitative and quantitative tests

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