HiPAN: Hierarchical Posture-Adaptive Navigation for Quadruped Robots in Unstructured 3D Environments

TL;DR

HiPAN is a hierarchical framework enabling quadruped robots to navigate complex 3D environments effectively by combining strategic planning, posture adaptation, and curriculum learning, all operating directly on onboard depth images.

Contribution

The paper introduces HiPAN, a novel hierarchical navigation framework with posture adaptation and curriculum learning, improving success rates and efficiency in unstructured 3D environments.

Findings

HiPAN outperforms classical reactive planners and end-to-end baselines in simulation.

Real-world experiments demonstrate HiPAN's applicability across diverse environments.

Path-Guided Curriculum Learning extends navigation horizon effectively.

Abstract

Navigating quadruped robots in unstructured 3D environments poses significant challenges, requiring goal-directed motion, effective exploration to escape from local minima, and posture adaptation to traverse narrow, height-constrained spaces. Conventional approaches employ a sequential mapping-planning pipeline but suffer from accumulated perception errors and high computational overhead, restricting their applicability on resource-constrained platforms. To address these challenges, we propose Hierarchical Posture-Adaptive Navigation (HiPAN), a framework that operates directly on onboard depth images at deployment. HiPAN adopts a hierarchical design: a high-level policy generates strategic navigation commands (planar velocity and body posture), which are executed by a low-level, posture-adaptive locomotion controller. To mitigate myopic behaviors and facilitate long-horizon navigation, we introduce Path-Guided Curriculum Learning, which progressively extends the navigation horizon from reactive obstacle avoidance to strategic navigation. In simulation, HiPAN achieves higher navigation success rates and greater path efficiency than classical reactive planners and end-to-end baselines, while real-world experiments further validate its applicability across diverse, unstructured 3D environments.