Abstract: Example embodiments relate to techniques for adjusting vehicle behavior based on estimated unintentional lateral movements. A computing system may receive sensor data representing a truck's environment as the truck pulls a trailer and navigates above a threshold speed on a freeway or another type of road. The computing system may use the sensor data to detect another truck navigating in an adjacent lane and at a speed that indicates an increased likelihood of a pass maneuver occurring between the trucks. Responsive to determining the increased likelihood of the pass maneuver occurring between the vehicles, the computing system may estimate an unintentional lateral movement for the pass maneuver based on parameters that can include the truck's speed, the size of the other truck's trailer, and a wind condition of the environment. The computing system can subsequently control the truck based on estimated unintentional lateral movement for the pass maneuver.

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: 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: Example embodiments relate to techniques for adjusting vehicle behavior based on estimated unintentional lateral movements. A computing system may receive sensor data representing a truck's environment as the truck pulls a trailer and navigates above a threshold speed on a freeway or another type of road. The computing system may use the sensor data to detect another truck navigating in an adjacent lane and at a speed that indicates an increased likelihood of a pass maneuver occurring between the trucks. Responsive to determining the increased likelihood of the pass maneuver occurring between the vehicles, the computing system may estimate an unintentional lateral movement for the pass maneuver based on parameters that can include the truck's speed, the size of the other truck's trailer, and a wind condition of the environment. The computing system can subsequently control the truck based on estimated unintentional lateral movement for the pass maneuver.

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.