Vehicle trajectory prediction method based on game intention characteristics and data driving

• Main Authors: LIU XIULONG, QU WENYU, DU JINGSHUN, ZHANG CHAOKUN
• Format: Patent
• Language: Chinese; English
• Published: 15.10.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a vehicle trajectory prediction method based on game intention characteristics and data driving, and the method comprises the following steps: 1, carrying out the modeling of an interactive decision process based on the game of any vehicle pair with an interactive relationship, and obtaining a demonstration data set; performing imitation learning by adopting an intelligent agent according to the demonstration data set to obtain an intention feature matrix; fusing the intention feature matrix of the vehicle pair and the BEV feature matrix to obtain a time-space-game matrix; and step 2, performing data-driven trajectory prediction based on the space-time-game matrix obtained in the step 1 to obtain a future trajectory of each vehicle in the vehicle pair. The interaction modeling method based on the Stackelberg game is realized on the basis of the characteristic that interaction among all kinds of motion subjects must have the game property. The problem that a method based on the game the