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.