Search Results

For high levels autonomous driving functions, the Decision Layer often takes on more responsibility due to the requirement of facing more diverse and even rare conditions. It is very difficult to accurately find a safe and efficient lane change timing when autonomous vehicles encounter complex traffic flow and need to change lanes. The traditional method based on rules and experiences has the limitation that it is difficult to be taken into account all possible conditions. Therefore, this paper designs a lane-changing decision algorithm based on data-driven and machine learning, and uses the DQN (Deep Q Network) algorithm in Reinforcement Learning to determine the appropriate lane-changing timing and target lane. Firstly, the scene characteristics of the highway are analyzed, the input and output of the decision-making model are designated and the data from the Perception Layer are processed.

For the DCC (Dynamic Chassis Control) system, in addition to the requirement of ride and comfort, it is also necessary to consider the requirement of handling and stability, and these two requirements are often not met at the same time. This poses a great challenge to the design of the controller, especially in the face of complex working conditions. In order to solve this problem, this paper proposes a comprehensive DCC controller that considers road roughness class recognition. Firstly, a quarter vehicle model is established, the road surface roughness is calculated from the vertical acceleration of the wheels measured by the sensors. Then we calculate the autocorrelation function and the Fourier transform to estimate the PSD (Power Spectral Density) to get the road roughness class. Then control algorithms are designed for the vertical motion control, roll control and pitch control.

Autonomous vehicle performance is increasingly highlighted in many highway driving scenarios, which leads to more priorities to vehicle stability as well as tracking accuracy. In this paper, a nonlinear model predictive controller for autonomous vehicle trajectory tracking is designed and verified through a real-time simulation bench of a virtual test track. The dynamic stability constraints of nonlinear model predictive control (NLMPC) are obtained by a novel quadrilateral stability region criterion instead of the conventional phase plane method using the double-line region. First, a typical lane change scene of overtaking is selected and a new composited trajectory model is proposed as a reference path that combines smoothness of sine wave and comfort of linear functional path. Reference lateral velocity, azimuth angle, yaw rate, and front wheel steering angle are subsequently taken into account.

In order to improve the robustness and stability of autonomous vehicle at high speed, a path tracking approach which combines front steering and differential braking is investigated in this paper. A bicycle model with 3-DOFs is established and a linear time-varying predictive model using front steering as its control input can be derived. Based on model predictive theory, the path tracking issue using linear time-varying model predictive control can be transformed into an online quadratic programming problem with constraints. The expected front steering angle can be obtained from online moving optimization. Then the direct yawing control is adopted to treat two types of differential braking control. The first one investigates steady-state gain of yaw rate in linear 2-DOFs vehicle model, and designs a stable differential braking controller which is based on reference yaw rate.