Robot-Body-Aware Traversal Risk Graph Planning for Wheeled-Legged Robots in Complex Terrain

2026-08-17

AI Summary

This study addresses support loss and collision risks in wheeled-legged robot navigation caused by neglecting body pose. We propose RB-TRG, a novel planning framework introducing a body-centric traversability risk graph that upgrades traditional node neighborhoods into perception-aware risk transition models incorporating heading and turning dynamics. By employing oriented rectangular footprint sampling and yaw scanning to quantify support stability and roll disturbances, the method optimizes A* search costs using upper-tail features. Real-world experiments demonstrate an end-to-end success rate improvement from 51.5% to 68.5%. Recognized with the ICRA 2026 Best Autonomy and Mobility Award, this work significantly enhances safe navigation capabilities for legged systems in unstructured environments.

Abstract

Traversal Risk Graphs (TRGs) provide a compact, terrain-aware representation for global navigation, but native TRG costs are computed over circular node neighborhoods and edge-aligned terrain regions rather than the robot's oriented body footprint. For wheeled-legged robots, this abstraction can miss partial support loss and body-terrain interference, especially during turns. We present Robot-Body-Aware TRG planning (RB-TRG), which builds on the sparse TRG representation and lifts edge-wise terrain-risk search to heading- and turn-aware body-risk transitions. An oriented rectangular footprint is sampled along graph edges and yaw sweeps to measure longitudinal support variation, lateral inclination, terrain interference, and exposure to untrusted map regions. Mean-and-upper-tail features are incorporated into transition costs, whose accumulated value is minimized by A* over ordered node-pair states, preserving TRG construction and its planning interface. We evaluate RB-TRG in a same-graph study on four scanned terrain environments and in paired closed-loop MuJoCo trials. RB-TRG reduces the three core geometric body-placement metrics and increases end-to-end success from 51.5% to 68.5%, while increasing mean path length by 2.3%. A Go2-W deployment further demonstrates RB-TRG with a full LiDAR navigation stack, which received the Best Autonomy and Best Mobility awards at the IEEE ICRA 2026 Legged Robot Challenges. The code for RB-TRG is released at https://github.com/ZhiqiaoGuo/RB-TRG.

Problem

• Traversal Risk Graphs
• Wheeled-Legged Robots
• Robot Body Awareness
• Terrain Interference
• Global Navigation

Innovation

• Robot-Body-Aware TRG
• Wheeled-Legged Robots
• Traversal Risk Graphs
• Heading-Aware Body-Risk Transitions
• Oriented Rectangular Footprint Sampling