DUGM-R: Uncertainty-Aware Dynamic Grid Mapping and Risk-Triggered Recovery for Learned Local Navigation

2026-09-23

AI Summary

本文通过不确定性感知动态网格地图和风险触发恢复机制解决室内拥挤环境下学习局部导航的障碍物表示问题及碰撞倾向行为。

Abstract

Learned local navigation in crowded indoor environments is sensitive to how dynamic obstacle motion is represented, while collision-prone behaviour may persist after nominal policy training. We present a risk-aware reinforcement-learning framework that addresses these two issues through an uncertainty-aware Dynamic Uncertainty Grid Map (DUGM) and a modular post-training recovery mechanism. DUGM combines local occupancy, estimated obstacle motion, and motion-estimation uncertainty in a robot-centric representation. After the nominal policy is frozen, a finite-horizon Risk Value Function (RVF) is trained from nominal rollouts and used to trigger a dedicated recovery policy when continued nominal execution is predicted to be collision-prone. Experiments in a held-out NVIDIA Isaac Sim clinical-logistics benchmark show that uncertainty-aware dynamic representation improves nominal navigation over static and deterministic alternatives, while the recovery mechanism further mitigates residual collision-prone behaviour. The complete framework is also deployed directly on a TurtleBot3 without policy fine-tuning, retraining, or site-specific adaptation, retaining the performance trend observed in simulation. These results indicate that uncertainty-aware dynamic representation and post-training recovery provide complementary mechanisms for improving learned local navigation.

Problem

• uncertainty-aware
• dynamic obstacle motion
• collision-prone behaviour
• local navigation

Innovation

• Uncertainty-Aware Dynamic Uncertainty Grid Map (DUGM)
• Risk-Triggered Recovery
• Risk Value Function (RVF)