US 12,405,382 B1
Particulate matter-occluded object probability map for sensor returns
Samantha Marie Ting, Redwood City, CA (US); Venkata Subrahmanyam Chandra Sekhar Chebiyyam, San Francisco, CA (US); and Shaminda Subasingha, San Ramon, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Dec. 17, 2021, as Appl. No. 17/555,365.
Int. Cl. G01S 17/931 (2020.01); G01B 11/22 (2006.01); G01S 7/481 (2006.01); G01S 17/89 (2020.01); G05B 13/02 (2006.01); B60W 30/09 (2012.01)
CPC G01S 17/931 (2020.01) [G01B 11/22 (2013.01); G01S 7/4814 (2013.01); G01S 17/89 (2013.01); G05B 13/0265 (2013.01); B60W 30/09 (2013.01); B60W 2420/408 (2024.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving sensor data associated with an environment;
receiving or determining an indication that a portion of the sensor data is associated with particulate matter, wherein the portion comprises a set of returns;
providing the set of returns as an input to a machine-learned (ML) model;
receiving, from the ML model, an output representing:
a first likelihood that there is a first object with equal to or more than a first reflectivity at equal to or more than a first distance beyond the particulate matter, and
a second likelihood that there is a second object with equal to or more than a second reflectivity at equal to or more than a second distance beyond the particulate matter; and
controlling a vehicle based at least in part on the first likelihood and the second likelihood.