CPC G06N 20/00 (2019.01) [G08G 5/0095 (2013.01)] | 20 Claims |
1. A method for updating a vehicle interaction machine learning model, the method comprising:
obtaining trajectory information indicating trajectories of a plurality of vehicles over a set period of time;
analyzing the trajectory information to determine whether a trajectory, among the trajectories within the set period of time, is a new trajectory type;
analyzing the trajectory information to determine whether the trajectory is a member of a new interaction, wherein an interaction is a trajectory, among the trajectories within the set period of time, of a first vehicle of the plurality of vehicles within a threshold distance of a trajectory, among the trajectories within the set period of time, of a second vehicle of the plurality of vehicles, and wherein the interaction includes combinations of vehicles that were not operating at the same time, but that would have been within a threshold distance of each other if the respective vehicles had been operating at the same time;
in response to determining the trajectory is a new trajectory type or the trajectory is a member of a new interaction, updating training data for the vehicle interaction machine learning model with the new trajectory type or the new interaction; and
training the vehicle interaction machine learning model based on the updated training data including the new trajectory type or the new interaction.
|