CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped Robots

2026-10-07

AI Summary

This study addresses the low sampling efficiency and suboptimal path generation in 2D path planning for quadruped robots caused by the inability to distinguish obstacle heights. To overcome these limitations, we propose a planning framework that integrates perceptual estimation with height-adaptive collision detection. Specifically, the framework introduces a Channel Mamba-PointNet guidance mechanism that fuses RGB-based depth estimation with elevation maps to enable height-aware traversability assessment, thereby guiding Informed RRT* toward more efficient sampling. Experimental results demonstrate that the proposed method significantly reduces the number of explored nodes and shortens the path length by 16.3%. Furthermore, real-world terrain traversal capabilities are successfully validated on the Unitree Go2 quadruped platform.

Abstract

Quadruped robots can traverse low obstacles, but many 2D planning pipelines still model obstacles as binary occupied regions and rely on sampling-based search that can be inefficient under a limited budget. We propose a perception-assisted height-adaptive planning framework based on CMP-IRRT*, a Channel Mamba PointNet-guided Informed RRT* planner. Given a calibrated top-view RGB observation, the perception module estimates obstacle regions and converts depth predictions into a ground-relative height map. The planner then performs height-conditioned collision checking, treating high obstacles as blocked while allowing low obstacles to be traversed, and uses the CMP guide to bias sampling toward promising regions while retaining standard free-space and informed sampling fallbacks. Experiments on 2D planning benchmarks show that CMP-IRRT* reduces explored nodes and iterations compared with classical and neural-guided baselines, and a controlled ablation supports the contribution of the Mamba-based guide. In constructed traversability-aware scenarios, the proposed planner reduces path length by up to 16.3% when low obstacles are traversable, and a Unitree Go2 demonstration further shows executable bypassing and traversal behaviors. Our code is publicly available at https://github.com/MingfanZhao/height-adaptive-planner.

Problem

• quadruped robots
• path planning
• obstacle traversability
• height-adaptive
• sampling-based search

Innovation

• Height-adaptive planning
• Mamba-guided sampling
• Perception-assisted navigation
• Informed RRT*
• Quadruped traversability