In order to enhance the trajectory tracking accuracy of distributed-driven intelligent vehicles, this paper formulates the tasks of torque output control for longitudinal dynamics and steering angle output control for lateral dynamics as Markov decision processes. To dissect the requirements of action output continuity for longitudinal and lateral control, this paper adopts the deep deterministic policy gradient algorithm (DDPG) for longitudinal velocity control and the deep Q-network algorithm (DQN) for lateral motion control. Multi-agent reinforcement learning methods are applied to the task of trajectory tracking in distributed-driven vehicle autonomous driving. By contrasting with two classical trajectory tracking control methods, the proposed approach in this paper is validated to exhibit superior trajectory tracking performance, ensuring that both longitudinal velocity deviation and lateral position deviation of the vehicle remain at lower levels. Compared with classical control methods, the maximum lateral position deviation is improved by up to 90.5% and the maximum longitudinal velocity deviation is improved by up to 97%. Furthermore, it demonstrates excellent generalization and high computational efficiency, and the running time can be reduced by up to 93.7%.

Speed information is crucial for controlling distributed electric-drive loaders, especially for driving and operation. Due to complex working conditions, the wheels of the loader often experience different conditions, leading to inaccurate speed estimation. To solve this, this paper proposes a multi-sensor fusion speed estimation method based on a Finite State Machine (FSM). The method uses the FSM to identify the wheel states and adaptively switches between the weighted average method and integration method to estimate the vehicle’s speed accurately. When all wheels are slipping, the acceleration integration method is used, starting from the latest trustworthy speed estimate. When the wheels are not slipping, the speed is estimated using the weighted average of the trustworthy wheels. Additionally, the method addresses the relative motion between the front and rear vehicle bodies caused by articulated steering by using an articulated steering projection method to ensure accurate wheel state estimation from IMU signals. Simulation and hardware-in-the-loop experiments show that the proposed method can accurately estimate vehicle speed under various road conditions. Specifically, under low-adhesion road conditions with all four wheels in a slipping state, it improves speed estimation accuracy by over 75% compared to traditional methods such as simple averaging, selective averaging, and pure integration.