US 12,145,627 B2
System and method for predicting the trajectory of a vehicle
David Gonzalez Bautista, Saint Cyr l'ecole (FR); Vicente Milanes, Boulogne-Billancourt (FR); and Francisco Martin Navas Matos, Paris (FR)
Assigned to AMPERE S.A.S., Boulogne-Billancourt (FR)
Appl. No. 17/784,531
Filed by RENAULT S.A.S., Boulogne-Billancourt (FR)
PCT Filed Dec. 10, 2020, PCT No. PCT/EP2020/085633
§ 371(c)(1), (2) Date Jun. 10, 2022,
PCT Pub. No. WO2021/116345, PCT Pub. Date Jun. 17, 2021.
Claims priority of application No. 1914342 (FR), filed on Dec. 13, 2019.
Prior Publication US 2023/0015485 A1, Jan. 19, 2023
Int. Cl. B60W 60/00 (2020.01); B60W 30/18 (2012.01); B60W 40/105 (2012.01)
CPC B60W 60/0027 (2020.02) [B60W 30/18163 (2013.01); B60W 40/105 (2013.01); B60W 2554/4041 (2020.02); B60W 2554/4046 (2020.02)] 7 Claims
OG exemplary drawing
 
1. A method for predicting a trajectory of an ego vehicle travelling in a main lane, the method comprising:
determining a lane change by the ego vehicle from the main lane to an adjacent lane according to an estimate of the dynamic behavior of a group of vehicles travelling in the adjacent lane, said group of vehicles comprising at least one main vehicle located near the ego vehicle and a secondary vehicle located behind said ego vehicle;
gathering position, orientation, and speed information of the ego vehicle and of the vehicles of the group of vehicles; and
establishing a dynamic model per pair of consecutive vehicles travelling in the adjacent lane according to the gathered information,
wherein the dynamic model per pair of consecutive vehicles is acquired by determining a second-order transfer function corresponding to the behavior of the ego vehicle relative to each pair of considered consecutive vehicles using an autoregressive exogenous computation model, with the behavior of the ego vehicle depending on its longitudinal model and on its longitudinal controller.