Human-like Behavior Decision Making Method for Intelligent Vehicle Considering Driver Characteristics

Abstract

Aiming at improving the human-like degree of in-telligent vehicle behavioral decision making, this paper proposes a human-like behavior decision-making method for intelligent vehicle considering driver characteristics. The indexes reflecting driver characteristics can be extracted and analyzed by bench experiment. Then combine the k-means clustering algorithm and BP neural network algorithm to identify drivers' characteristics. For different driver characteristics, lane change probabilities are calculated through average speed efficient, average time efficient and road length efficient. When lane change expectations are generated, keep, slow down or appropriate lane change gaps are determined. Simulation results show that this method can effectively classify driver characteristics and make human-like behavior decisions.