Reinforcement Learning-Based Control of Single-Track Two-Wheeled Robots in Narrow Terrain

The single-track two-wheeled (STTW) robot has the advantages of small size and flexibility, and it is suitable for traveling in narrow terrains of mountains and jungles. In this article, a reinforcement learning control method for STTW robots is proposed for driving fast in narrow terrain with limited visibility and line-of-sight occlusions. The proposed control scheme integrates path planning, trajectory tracking, and balancing control in a single framework. Based on this method, the state, action, and reward function are defined for narrow terrain passing tasks. At the same time, we design the actor network and the critic network structures and use the twin delayed deep deterministic policy gradient (TD3) to train these neural networks to construct a controller. Next, a simulation platform is formulated to test the performances of the proposed control method. The simulation results show that the obtained controller allows the STTW robot to effectively pass the training terrain, as well as the four test terrains. In addition, this article conducts a simulation comparison to prove the advantages of the integrated framework over traditional methods and the effectiveness of the reward function.