Real-Time Multi-Level Terrain-Aware Path Planning for Ground Mobile Robots in Large-Scale Rough Terrains
Yuxiang Li, Kun Chen, Yifei Wang, Weifan Zhang, Jiancheng Wang, Haoyao Chen, Yunhui Liu
AI summary
Problem
Traditional hierarchical path planners struggle with the high-dimensional workspaces of complex robot configurations and lack detailed terrain awareness, leading to safety hazards and poor real-time performance in large-scale rough terrains.
Approach
The framework uses an implicit volumetric map to efficiently compute terrain metrics for global pathfinding, while a local layer applies an iterative geometric evaluation to accurately estimate configuration stability and ensure kinematic feasibility.
Key results
- Implicit map enables large-scale terrain accuracy
- Terrain metrics pipeline assesses traversal risk
- Iterative geometric stability estimation outperforms baselines
- Higher success rates in simulations and real-world tests
Why it matters
Provides a modular, real-time navigation solution critical for autonomous ground robots operating in disaster zones, exploration sites, and other large-scale unstructured environments.
Abstract
Autonomous ground mobile robots rely on their configuration characteristics to prevent tip-overs and collisions, ensuring safe navigation in complex environments. However, complex configurations with specially designed links and joints produce a higher-dimensional workspace and bring significant challenges for path planning, especially in large-scale rough terrains. To address this, we propose a real-time multi-level terrain-aware path planning framework that integrates different levels of terrain awareness into the global and local layers. An implicit map representation is introduced at the global layer to enable efficient terrain analysis and path planning, while an iterative geometric evaluation is designed at the local layer to estimate configuration stability and improve path smoothness. By sharing the global layer information with the local layer, the framework enhances path planning efficiency and adaptability in complex environments. Its modular design supports diverse robot configurations and pathfinding algorithms, enabling effective autonomous navigation in large-scale 3D terrains with online or offline maps. Simulations and real-world experiments demon- strated that our approach outperforms state-of-the-arts across diverse environments, including uneven terrains, multi-layered structures, and complex debris fields. The results highlighted that our approach provides faster and safer path planning, more accurate and robust configuration-stability estimation, and higher success rates in traversing complex 3D environments.