Abstract: Example embodiments relate to a method for cut-in identification and classification. An example embodiment includes a obtaining operational data about one or more vehicles; based on the operational data, identifying the presence of one or more cut-ins within the operational data; extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data; and, based on the extracted cut-in data, training a model for controlling an autonomous vehicle. Identifying the presence of a given cut-in includes: determining that at least one vertex of a bounding box surrounding a vehicle was located more than a threshold distance within a lane being navigated by a given vehicle; and determining that the ability of the given vehicle to maintain its course and speed was impeded by the presence of the particular additional vehicle within the lane.

Abstract: A sensor assembly contains at least first and second sensors configured to perform imaging from a portion of a vehicle, each sensor having a respective field of view (FOV) based on an imaging direction of the sensor, each sensor having an FOV origin. The sensor assembly is configured to be disposed at the portion of the vehicle such that (i) the first and second sensors' FOV origins are each outboard from the vehicle, (ii) the first and second sensors' imaging directions are each within 90 degrees in yaw of being parallel to the backward direction of the vehicle, (iii) the first sensor's imaging direction is closer in yaw than the second sensor's imaging direction to being parallel to the backward direction of the vehicle, and (iv) the first sensor's FOV origin is more outboard from the vehicle than the second sensor's FOV origin.

Abstract: Example embodiments relate to a method for cut-in identification and classification. An example embodiment includes a obtaining operational data about one or more vehicles; based on the operational data, identifying the presence of one or more cut-ins within the operational data; extracting, from the operational data, cut-in data that depicts one or more of the cut-ins identified within the operational data; and, based on the extracted cut-in data, training a model for controlling an autonomous vehicle. Identifying the presence of a given cut-in includes: determining that at least one vertex of a bounding box surrounding a vehicle was located more than a threshold distance within a lane being navigated by a given vehicle; and determining that the ability of the given vehicle to maintain its course and speed was impeded by the presence of the particular additional vehicle within the lane.