Task-Level Decisions to Gait Level Control: A Hierarchical Policy Approach for Quadruped Navigation
This work solves navigation challenges for quadruped robots, particularly in real-world environments with terrain variations, though it appears incremental as it builds on hierarchical and reinforcement learning methods.
The paper tackles the problem of quadruped navigation by addressing the scale mismatch between high-level decisions and low-level gait execution, resulting in higher task success rates on mixed terrains and out-of-distribution tests.
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.