US 11,772,640 B2
Systems and methods for vehicular collision detection based on multi-dimensional collision models
Boyu Wang, Menlo Park, CA (US); Sujoy Bhattacharjee, San Jose, CA (US); Naveed Farooqui, Sunnyvale, CA (US); and Nick G. Suizo, San Jose, CA (US)
Assigned to Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed by Verizon Patent and Licensing Inc., Basking Ridge, NJ (US)
Filed on Apr. 2, 2021, as Appl. No. 17/221,135.
Prior Publication US 2022/0314971 A1, Oct. 6, 2022
Int. Cl. B60W 30/09 (2012.01); B60W 30/16 (2020.01); B60W 40/04 (2006.01); B60W 50/14 (2020.01); G06F 18/2411 (2023.01); G06F 18/23213 (2023.01)
CPC B60W 30/09 (2013.01) [B60W 30/16 (2013.01); B60W 40/04 (2013.01); B60W 50/14 (2013.01); G06F 18/23213 (2023.01); G06F 18/2411 (2023.01); B60W 2050/143 (2013.01); B60W 2050/146 (2013.01); B60W 2554/406 (2020.02); B60W 2554/4049 (2020.02); B60W 2554/80 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A device, comprising:
one or more processors configured to:
identify a plurality of data sets that are each associated with a plurality of dimensions, wherein each dimension of the plurality of dimensions is based on a particular factor indicating relationship data between multiple objects;
perform an anomaly detection technique on the plurality of data sets to identify a subset of the plurality of data sets that are rare data sets with respect to the plurality of data sets;
determine a rarity threshold curve, associated with the plurality of dimensions, based on identifying the subset of the plurality of data sets, wherein the rarity threshold curve separates the rare data sets from data sets, of the plurality of data sets, that are not rare:
receive a particular data set indicating particular relationship data between a particular vehicle and a particular object detected by one or more sensors associated with the particular vehicle;
compare the particular data set, associated with the particular vehicle and the particular object, with the rarity threshold curve;
determine, based on the comparison, whether the particular data set associated with the particular vehicle and the particular object is a rare data set;
when the particular data set associated with the particular vehicle and the particular object is not a rare data set, refrain from causing the particular vehicle to perform a collision prevention measure; and
when the particular data set associated with the particular vehicle and the particular object is a rare data set, cause the particular vehicle to perform the collision prevention measure.