Control of rough terrain vehicles using deep reinforcement learning

TL;DR

This paper demonstrates that deep reinforcement learning can effectively control a complex forestry vehicle in rough terrain, outperforming traditional methods by enabling safe, efficient, and adaptable navigation in challenging environments.

Contribution

It introduces a novel deep reinforcement learning controller for a large articulated forestry vehicle, capable of handling complex dynamics and high-dimensional sensory data in rough terrains.

Findings

Successfully controlled a 16-tonne forestry vehicle in simulated rough terrains.

Handled obstacles, slopes up to 27°, and natural terrains with limited wheel slip.

Showed potential of deep RL to surpass traditional control methods in complex vehicle navigation.

Abstract

We explore the potential to control terrain vehicles using deep reinforcement in scenarios where human operators and traditional control methods are inadequate. This letter presents a controller that perceives, plans, and successfully controls a 16-tonne forestry vehicle with two frame articulation joints, six wheels, and their actively articulated suspensions to traverse rough terrain. The carefully shaped reward signal promotes safe, environmental, and efficient driving, which leads to the emergence of unprecedented driving skills. We test learned skills in a virtual environment, including terrains reconstructed from high-density laser scans of forest sites. The controller displays the ability to handle obstructing obstacles, slopes up to 27$^\circ$, and a variety of natural terrains, all with limited wheel slip, smooth, and upright traversal with intelligent use of the active suspensions. The results confirm that deep reinforcement learning has the potential to enhance control of vehicles with complex dynamics and high-dimensional observation data compared to human operators or traditional control methods, especially in rough terrain.