Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension
Researchers have developed a novel control system for a planetary rover named ERNEST, which features an actively articulated suspension. This system utilizes a single neural network controller trained via reinforcement learning in a high-fidelity simulation environment. The controller is designed to adapt to various terrains without explicit classification, consolidating learning from specialized agents into one unified network. Experimental results show the system successfully navigating challenging terrains like rock fields and sandy slopes, demonstrating improved efficiency and capability over passive suspension systems. AI
IMPACT Demonstrates advanced AI control for robotic navigation in complex, unstructured environments.