US 11,673,550 B2
Agent prioritization for autonomous vehicles
Kai Ding, Santa Clara, CA (US); Khaled Refaat, Mountain View, CA (US); and Stephane Ross, San Jose, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on May 14, 2021, as Appl. No. 17/320,727.
Application 17/320,727 is a continuation of application No. 16/264,136, filed on Jan. 31, 2019, granted, now 11,034,348.
Application 16/264,136 is a continuation in part of application No. 16/198,130, filed on Nov. 21, 2018, granted, now 11,048,253.
Application 16/198,130 is a continuation in part of application No. 16/196,769, filed on Nov. 20, 2018, granted, now 10,739,777, issued on Aug. 11, 2020.
Prior Publication US 2021/0269023 A1, Sep. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. B60W 30/095 (2012.01); G05D 1/02 (2020.01); G05D 1/00 (2006.01)
CPC B60W 30/0956 (2013.01) [G05D 1/0088 (2013.01); G05D 1/0214 (2013.01); G05D 2201/0213 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by one or more data processing apparatus, the method comprising:
generating, using an importance scoring model and for each of a plurality of agents currently located at respective locations in an environment in a vicinity of a vehicle, a respective importance score for the agent that characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle;
selecting, for one or more of the agents, a respective prediction model for use in generating data characterizing the agent based on the importance score for the agent, comprising:
identifying a proper subset of the plurality of agents as high-priority agents based on their respective importance scores, comprising:
identifying one or more agents of the plurality of agents as having highest importance scores from among the plurality of agents;
designating the one or more agents identified as having the highest importance scores from among the plurality of agents as being high-priority agents;
selecting, for only those agents of the plurality of agents that are identified as high-priority agents based on their respective importance scores, a first prediction model for use in generating data characterizing the agent; and
generating, for each of the high-priority agents, data characterizing the agent using the first prediction model selected for the agent; and
providing the data characterizing the high-priority agents generated using the first prediction model to the planning system of the vehicle to generate the planning decisions which plan the future trajectory of the vehicle.