US 12,311,927 B1
Collision monitoring using statistic models
Andrew Scott Crego, Foster City, CA (US); Ali Ghasemzadehkhoshgroudi, Foster City, CA (US); Sai Anurag Modalavalasa, Foster City, CA (US); Andreas Christian Reschka, Foster City, CA (US); Siavosh Rezvan Behbahani, Redwood City, CA (US); and Lingqiao Qin, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on May 22, 2023, as Appl. No. 18/200,493.
Application 18/200,493 is a continuation of application No. 16/682,971, filed on Nov. 13, 2019, granted, now 11,697,412.
Int. Cl. B60W 30/095 (2012.01); B60W 30/09 (2012.01); B60W 40/04 (2006.01); G06V 20/58 (2022.01)
CPC B60W 30/0956 (2013.01) [B60W 30/09 (2013.01); B60W 40/04 (2013.01); G06V 20/584 (2022.01); B60W 2554/80 (2020.02); B60W 2555/20 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving sensor data from a sensor associated with a vehicle;
determining, based at least in part on the sensor data, a vehicle estimated location;
determining, based at least in part on the sensor data, an object estimated location associated with an object;
obtaining, based at least in part on the object estimated location, an uncertainty model associated with the object estimated location from a plurality of uncertainty models, the plurality of uncertainty models being associated with at least one of a same prediction model or a same perception model;
determining, based at least in part on the object estimated location and the uncertainty model associated with the object estimated location, an uncertainty distribution associated with the object estimated location; and
causing the vehicle to perform an action based at least in part on the vehicle estimated location and the uncertainty distribution associated with the object estimated location.