US 12,444,203 B2
Apparatus and methods for detecting trailer sway
Jeremy Michael Young, Chicago, IL (US); Jerome Beaurepaire, Nantes (FR); and Leon Stenneth, Chicago, IL (US)
Assigned to HERE GLOBAL B.V., Eindhoven (NL)
Filed by HERE GLOBAL B.V., Eindhoven (NL)
Filed on Feb. 15, 2022, as Appl. No. 17/672,271.
Prior Publication US 2023/0260288 A1, Aug. 17, 2023
Int. Cl. G06V 20/56 (2022.01); G01S 17/88 (2006.01); G06T 7/70 (2017.01); G06V 10/764 (2022.01); G07C 5/00 (2006.01); G07C 5/02 (2006.01); G08B 5/22 (2006.01)
CPC G06V 20/56 (2022.01) [G01S 17/88 (2013.01); G06T 7/70 (2017.01); G06V 10/764 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30252 (2013.01); G07C 5/008 (2013.01); G07C 5/02 (2013.01); G08B 5/22 (2013.01)] 17 Claims
OG exemplary drawing
 
1. An apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to:
receive sensor data;
based on the sensor data, determine a pitch angle of a trailer, wherein the pitch angle is defined by an angle at which a direction and a horizontal plane intersects, wherein the trailer extends along the direction, and wherein the horizontal plane is a plane that is parallel to a surface of a ground local to the trailer or is a plane that is perpendicular to an axis stretching from the center of the earth to the trailer;
based on the pitch angle, determine a confidence of trailer sway occurring;
receive first attribute data associated with a first location in which the trailer is positioned;
input the first attribute data to a machine learning model;
based on an output of the machine learning model as a function of the first attribute data, determine the confidence, wherein the machine learning model is trained based on historical data of one or more past events in which one or more vehicles towing one or more other trailers was swaying, the historical data including second attribute data associated with one or more second locations of the one or more past events; and
responsive to the confidence exceeding a threshold, generate a warning signal indicating potential trailer sway.