让机器人智能推开障碍物，比传统方法更省力且成功率更高
Pushing Through Clutter With Movability Awareness of Blocking Obstacles
- 用语义可见图与模型预测路径积分结合，感知障碍物可移动性
- 成功率达92%，接触力降低40%以上，优于仅用是否可移动的旧方法
- 适合需要复杂推挤操作的室内服务机器人场景
在可移动障碍物环境中导航（NAMO）对传统路径规划方法构成挑战，因障碍物阻挡路径需执行推移动作才能到达目标。本文提出一种无需显式障碍物布局的可移动性感知规划框架。该框架融合全局语义可见图与局部模型预测路径积分（SVG-MPPI），高效采样轨迹，考虑障碍物连续可移动范围。采用物理引擎模拟轨迹与环境交互，生成接触力最小的运动规划。定性和定量实验表明，SVG-MPPI优于仅使用二元可移动性信息的现有范式，成功率更高，累计接触力显著降低。代码已开源：https://github.com/tud-amr/SVG-MPPI
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。