Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension

arXiv:2606.0679010.9
Originality Incremental advance
AI Analysis

For planetary exploration rovers, this work demonstrates a unified controller that handles heterogeneous terrains without explicit classification, achieving zero-shot transfer to physical hardware.

ERNEST, a planetary rover with actively articulated suspension, uses a single neural network controller trained via reinforcement learning to autonomously traverse challenging terrains. On a 20° sandy slope, it reduces cost of transport by 37% on dry sand and outperforms passive suspension on wet sand where passive gets immobilized.

This paper presents ERNEST, a four-wheeled planetary rover concept equipped with a two-degree-of-freedom Active Gimbal Suspension that combines yaw and roll actuation to enable wheel reconfiguration, steering, and active load redistribution. A single neural network controller, trained to track a desired path across challenging terrain, fully unlocks the capabilities of this actuated suspension system for autonomous obstacle negotiation. A reinforcement learning framework is developed using the high-fidelity DARTS simulation engine, which combines rigid-contact dynamics and Bekker-Wong terramechanics, enabling the emergence of locomotion strategies adapted to loose-soil conditions. To obtain a single unified controller across heterogeneous terrains, a policy consolidation strategy merges the experience of terrain-specialized agents into one neural network, eliminating the need for explicit terrain classification and controller switching. The resulting controller operates on a combination of proprioceptive and exteroceptive feedback, including sparse stereo-derived terrain elevation, chassis attitude, joint states, and force-torque measurements. Zero-shot transfer to the physical rover is achieved through domain randomization, sensor noise injection, and model-to-real system identification. Experimental results demonstrate autonomous traversal of rock fields, a bump trap, a wheel-high step, sand ripples, and sandy slopes. On a 20° sandy slope, the learned controller reduces the cost of transport by 37% on dry sand despite the additional actuation, and achieves superior performance on wet sand where the passive suspension becomes completely immobilized.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes