Attention Based Vehicle Trajectory Prediction

• Published in: IEEE transactions on intelligent vehicles Vol. 6; no. 1; pp. 175 - 185
• Main Authors: Messaoud, Kaouther, Yahiaoui, Itheri, Verroust-Blondet, Anne, Nashashibi, Fawzi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Autonomous cars; Computer Science; Computer Vision and Pattern Recognition; Hidden Markov models; multi-head attention; multi-modality; Predictive models; Reaction time; recurrent networks; Road transportation; Task analysis; Trajectory; Trajectory analysis; Trajectory planning; Trajectory prediction; Vehicle dynamics; Vehicles; vehicles interactions; Recurrent networks; Trajectory prediction; Vehicles interactions; Multi-modality; Multi-head attention
• ISSN: 2379-8858; 2379-8904
• DOI: 10.1109/TIV.2020.2991952

Self-driving vehicles need to continuously analyse the driving scene, understand the behavior of other road users and predict their future trajectories in order to plan a safe motion and reduce their reaction time. Motivated by this idea, this paper addresses the problem of vehicle trajectory prediction over an extended horizon. On highways, human drivers continuously adapt their speed and paths according to the behavior of their neighboring vehicles. Therefore, vehicles' trajectories are very correlated and considering vehicle interactions makes motion prediction possible even before the start of a clear maneuver pattern. To this end, we introduce and analyze trajectory prediction methods based on how they model the vehicles interactions. Inspired by human reasoning, we use an attention mechanism that explicitly highlights the importance of neighboring vehicles with respect to their future states. We go beyond pairwise vehicle interactions and model higher order interactions. Moreover, the existence of different goals and driving behaviors induces multiple potential futures. We exploit a combination of global and partial attention paid to surrounding vehicles to generate different possible trajectory. Experiments on highway datasets show that the proposed model outperforms the state-of-the-art performances.