US 12,352,579 B1
Localization performance metric
Guillermo Duenas Arana, San Francisco, CA (US); Nathaniel Jon Kaiser, Boston, MA (US); and Brice Rebsamen, San Jose, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Jul. 27, 2022, as Appl. No. 17/875,090.
Int. Cl. G01C 21/28 (2006.01); B60W 60/00 (2020.01); G08G 1/127 (2006.01)
CPC G01C 21/28 (2013.01) [B60W 60/001 (2020.02); G08G 1/127 (2013.01); B60W 2756/10 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving sensor data comprising first sensor data from a first sensor associated with an autonomous vehicle and second sensor data associated with a second sensor associated with the autonomous vehicle;
inputting the sensor data into a localization system associated with the autonomous vehicle by fusing the first sensor data and the second sensor data in part to determine localization data and auxiliary localization data, the auxiliary localization data comprising at least one of variance data, a latent parameter, or residual data;
inputting the auxiliary localization data into a machine learned model;
receiving, from the machine learned model, a metric associated with a performance of the localization system associated with the autonomous vehicle; and
performing, based at least in part on the metric, an action associated with the autonomous vehicle, the action comprising adjusting at least one of a braking force of the autonomous vehicle, a braking distance of the autonomous vehicle, or a maximum speed of the autonomous vehicle; and
controlling the autonomous vehicle based at least in part on the action.