Trajectory tracking is a key technology for precisely controlling autonomous vehicles. In this paper, we propose a trajectory-tracking method based on model predictive control. Instead of using the forward Euler integration method, the backward Euler integration method is used to establish the predictive model. To meet the real-time requirement, a constraint is imposed on the control law and the warm-start technique is employed. The MPC-based controller is proved to be stable. The simulation results demonstrate that, at the cost of no or a little increase in computational time, the tracking performance of the controller is much better than that of controllers using the forward Euler method. The maximum lateral errors are reduced by 69.09%, 47.89% and 78.66%. The real-time performance of the MPC controller is good. The calculation time is below 0.0203 s, which is shorter than the control period.

Vehicle dynamic parameters are of vital importance to establish feasible vehicle models which are used to provide active controls and automated driving control. However, most vehicle dynamics parameters are difficult to obtain directly. In this paper, a new method, which requires only conventional sensors, is proposed to estimate vehicle dynamic parameters. The influence of vehicle dynamic parameters on vehicle dynamics often involves coupling. To solve the problem of coupling, a two-stage estimation method, consisting of multiple-models and the Unscented Kalman Filter, is proposed in this paper. During the first stage, the longitudinal vehicle dynamics model is used. Through vehicle acceleration/deceleration, this model can be used to estimate the distance between the vehicle centroid and vehicle front, the height of vehicle centroid and tire longitudinal stiffness. The estimated parameter can be used in the second stage. During the second stage, a single-track with roll dynamics vehicle model is adopted. By making vehicle continuous steering, this vehicle model can be used to estimate tire cornering stiffness, the vehicle moment of inertia around the yaw axis and the moment of inertia around the longitudinal axis. The simulation results show that the proposed method is effective and vehicle dynamic parameters can be well estimated.

Autonomous driving is a popular and promising field in artificial intelligence. Rapid decision of the next action according to the latest few actions and status, such as acceleration, brake, and steering angle, is a major concern for autonomous driving. There are some learning methods, such as reinforcement learning which automatically learns the decision. However, it usually requires large volume of samples. In this paper, to reduce the sample size, we exploit the deep Gaussian process, where a regression model is trained on small sample datasets and captures the most significant features correctly. Besides, to realize the real-time and close-loop control, we combine the feedback control into the process. Experimental results on the Torcs simulation engine illustrate smooth driving on virtual road which can be achieved. Compared with the amount of training data in deep reinforcement learning, our method uses only 0.34% of its size and obtains similar simulation results. It may be useful for real road tests in the future.

The coordinated control of a blended braking system is always a difficult task. In particular, blended braking control becomes more challenging when the braking actuator has an input time-delay and some states of the braking system cannot be measured. In order to improve the tracking performance, a coordinated control system was designed based on the input time-delay and state observation for a blended braking system comprising a motor braking system and friction braking system. The coordinated control consists of three parts: Sliding mode control, a multi-input single-output observer, and time-delay estimation-based Smith Predictor control. The sliding mode control is used to calculate the total command braking torque according to the desired braking performance and vehicle states. The multi-input single-output observer is used to simultaneously estimate the input time-delay and output braking torque of the friction braking system. With time-delay estimation-based Smith Predictor control, the friction braking system is able to effectively track the command braking torque of the friction braking system. The tracking of command braking torque is realized through the coordinated control of the motor braking system and friction braking system. In order to validate the effectiveness of the proposed approach, numerical simulations on a quarter-vehicle braking model were performed.