Task-Level Decisions to Gait Level Control: A Hierarchical Policy Approach for Quadruped Navigation

TL;DR

This paper introduces a hierarchical control architecture for quadruped navigation that improves robustness and transferability by separating high-level decision-making from low-level gait control, enabling better adaptation and fault diagnosis.

Contribution

The paper proposes a novel hierarchical policy architecture with explicit interfaces for gait control and decision-making, enhancing robustness and adaptability in quadruped navigation.

Findings

Higher task success rates on mixed terrains

Improved robustness in out-of-distribution tests

Explicit interfaces facilitate tuning and diagnosis

Abstract

Real-world quadruped navigation is constrained by a scale mismatch between high-level navigation decisions and low-level gait execution, as well as by instabilities under out-of-distribution environmental changes. Such variations challenge sim-to-real transfer and can trigger falls when policies lack explicit interfaces for adaptation. In this paper, we present a hierarchical policy architecture for quadrupedal navigation, termed Task-level Decision to Gait Control (TDGC). A low-level policy, trained with reinforcement learning in simulation, delivers gait-conditioned locomotion and maps task requirements to a compact set of controllable behavior parameters, enabling robust mode generation and smooth switching. A high-level policy makes task-centric decisions from sparse semantic or geometric terrain cues and translates them into low-level targets, forming a traceable decision pipeline without dense maps or high-resolution terrain reconstruction. Different from end-to-end approaches, our architecture provides explicit interfaces for deployment-time tuning, fault diagnosis, and policy refinement. We introduce a structured curriculum with performance-driven progression that expands environmental difficulty and disturbance ranges. Experiments show higher task success rates on mixed terrains and out-of-distribution tests.