US 12,228,926 B1
System and method for predicting behaviors of detected objects through environment representation
Jiajun Zhu, Palo Alto, CA (US); and David I. Ferguson, San Francisco, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Feb. 15, 2022, as Appl. No. 17/672,166.
Application 17/672,166 is a continuation of application No. 16/737,318, filed on Jan. 8, 2020, granted, now 11,287,820.
Application 16/737,318 is a continuation of application No. 15/670,128, filed on Aug. 7, 2017, granted, now 10,564,639, issued on Feb. 18, 2020.
Application 15/670,128 is a continuation of application No. 15/161,556, filed on May 23, 2016, granted, now 9,766,626, issued on Sep. 19, 2017.
Application 15/161,556 is a continuation of application No. 13/366,828, filed on Feb. 6, 2012, granted, now 9,381,916, issued on Jul. 5, 2016.
This patent is subject to a terminal disclaimer.
Int. Cl. G05D 1/00 (2024.01); B60W 30/095 (2012.01); G01S 13/86 (2006.01); G01S 13/931 (2020.01); G01S 17/931 (2020.01); G05D 1/02 (2020.01); G08G 1/16 (2006.01); G01S 15/931 (2020.01); G08G 1/0967 (2006.01)
CPC G05D 1/0088 (2013.01) [B60W 30/0956 (2013.01); G01S 13/862 (2013.01); G01S 13/865 (2013.01); G01S 13/867 (2013.01); G01S 13/931 (2013.01); G01S 17/931 (2020.01); G05D 1/0248 (2013.01); G05D 1/0257 (2013.01); G08G 1/166 (2013.01); G01S 2013/932 (2020.01); G01S 2013/9322 (2020.01); G01S 2013/93271 (2020.01); G01S 2013/93272 (2020.01); G01S 2013/93273 (2020.01); G01S 2013/93274 (2020.01); G01S 15/931 (2013.01); G08G 1/096791 (2013.01); G08G 1/16 (2013.01)] 23 Claims
OG exemplary drawing
 
11. A system for controlling a vehicle in an autonomous driving mode, the system comprising:
one or more sensor devices mounted on the vehicle;
and
one or more processors configured to:
receive sensor data generated by the one or more sensor devices, the sensor data corresponding to a set of objects detected by the one or more sensor devices in an external environment of the vehicle;
access data containing a plurality of object classifications and behavior information;
determine a classification of each object in the set of objects detected by the one or more sensor devices based on the accessed data;
for each object in the set of objects, predict at least one future action of the object based on:
a likely behavior of the object according to the behavior information,
a current trajectory of the object with respect to map information, and
the classification of the object determined based on the accessed data; and
control the vehicle in the autonomous driving mode based on the predicted at least one future action of each object in the set of objects.