US 12,441,307 B2
Obstruction detection system
James Lucas, Wilmerding, PA (US); Brad Von Tersch, Wilmerding, PA (US); and Mike Kirchner, Wilmerding, PA (US)
Assigned to Xorail, Inc.
Filed by Xorail, Inc., Berwick, PA (US)
Filed on Aug. 17, 2022, as Appl. No. 17/890,192.
Application 17/890,192 is a continuation in part of application No. 16/733,465, filed on Jan. 3, 2020, granted, now 11,468,766.
Prior Publication US 2022/0398924 A1, Dec. 15, 2022
Int. Cl. B60W 30/095 (2012.01); B60W 30/08 (2012.01); B60W 30/09 (2012.01); B60W 60/00 (2020.01); G06N 20/00 (2019.01); G06V 20/54 (2022.01); G08G 1/052 (2006.01); G08G 1/056 (2006.01); G08G 1/0967 (2006.01); G08G 1/16 (2006.01)
CPC B60W 30/0956 (2013.01) [B60W 30/08 (2013.01); B60W 30/09 (2013.01); B60W 30/095 (2013.01); B60W 30/0953 (2013.01); B60W 60/0027 (2020.02); G06V 20/54 (2022.01); G08G 1/052 (2013.01); G08G 1/056 (2013.01); G08G 1/096725 (2013.01); G08G 1/096783 (2013.01); G08G 1/164 (2013.01); G08G 1/166 (2013.01); G06N 20/00 (2019.01); G06V 2201/08 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
receiving sensor output indicative of one or more of a location, a heading, or a moving speed of one or more of a first vehicle or a second vehicle;
predicting a collision between the first vehicle and the second vehicle at an intersection between two or more routes based on the sensor output that is received by calculating a likelihood of collision using an artificial intelligence or machine learning model;
communicating a signal to the one or more of the first vehicle or the second vehicle to change movement of the one or more of the first vehicle or the second vehicle, based on hierarchically-ranked alert levels corresponding to hierarchically ranked remedial activities, responsive to the collision that is predicted;
receiving an input of a result of changing the movement of the one or more of the first vehicle or the second vehicle that indicates whether a desirable outcome is achieved or not, wherein the desirable outcome comprises that the collision does not actually occur; and
updating the artificial intelligence or machine learning model based on the input.