Model Free Adaptive Control Algorithm based on ReOSELM for Autonomous Driving Vehicles

Different road conditions and dynamic environment bring significant challenges to the control system of autonomous driving vehicle (ADV). As is known, historical data collected from ADV contains valuable information about control systems, therefore, it is a promising thing to study adaptive control algorithms that have certain learning ability. In order to improve the control performance of ADV and the efficiency in data usage, in this paper, a model free adaptive control algorithm based on regularized online sequential extreme learning machine (ReOSELM) is introduced, it is difficult to analyze the algorithm based on neural network, and the system stability by improved update algorithm of ReOSELM is proved. Simulation results indicate that the proposed algorithm is effective in improving control precision when ADV is turning, and experimental results on an autonomous driving vehicle show that this algorithm is effective in real environment.