Isaac Gym

Diagram: a navigation policy sends a bounded velocity command to a locomotion policy, which also reads terrain height samples and drives the robot's joints.

Hierarchical reinforcement learning for quadruped navigation

Two reinforcement-learning policies, one for navigation and one for locomotion, joined by a bounded velocity command. Simulation research presented at ICRoM 2025; thesis in progress.

Original paper figure showing the obstacle map, the quadruped at an intermediate position and its complete simulated navigation trajectory.

Hierarchical Deep Reinforcement Learning for Quadruped Navigation over Complex Terrains

A two-policy framework for quadruped navigation over uneven terrain, evaluated in Isaac Gym. Read the research summary, explore the original figures and download the ICRoM 2025 paper.