Agent trajectory prediction using target locations

Patent metadata

Field	Value
Publication number	US-12365361-B2
Application number	US-202418423136-A
Country	US
Kind code	B2
Filing date	Jan 25, 2024
Priority date	Jul 28, 2020
Publication date	Jul 22, 2025
Grant date	Jul 22, 2025

Abstract

A system obtains scene context data characterizing the environment. The scene context data includes data that characterizes a trajectory of an agent in a vicinity of a vehicle up to a current time point. The system identifies a plurality of initial target locations, and generates, for each of a plurality of target locations that each corresponds to one of the initial target locations, a respective predicted likelihood score that represents a likelihood that the target location will be an intended final location for a future trajectory of the agent. For each target location in a first subset of the target locations, the system generates a predicted future trajectory for the agent given that the target location is the intended final location for the future trajectory. The system further selects, as likely future trajectories of the agent, one or more of the predicted future trajectories.

First claim

What is claim is:

1. A method performed by one or more computers, the method comprising:
obtaining scene context data characterizing an environment, the scene context data comprising data that characterizes a trajectory of an agent in a vicinity of a vehicle in an environment up to a current time point;
processing the scene context data using a context encoding neural network to generate an encoded representation of the scene context data;
identifying a plurality of initial target locations in the environment;
for each of a plurality of target locations that each corresponds to one of the initial target locations, using a target prediction neural network to process (i) the encoded representation generated by the context encoding neural network and (ii) data specifying the respective initial target location corresponding to the respective target location to generate a target prediction output that specifies a respective predicted likelihood score that represents a likelihood that the target location will be an intended final location for a future trajectory of the agent starting from the current time point;
selecting a first subset of the target locations based on the respective predicted likelihood scores of the target locations;
for each target location in the first subset of the target locations, generating a predicted future trajectory for the agent that is a prediction of the future trajectory of the agent given that the target location is the intended final location for the future trajectory;
selecting, as likely future trajectories of the agent starting from the current time point, one or more of the predicted future trajectories; and
controlling the vehicle using the one or more selected predicted future trajectories.

2. The method of claim 1 , wherein the scene context data further comprises data that characterizes respective trajectories of one or more other agents in the environment up to the current time point.

3. The method of claim 1 , wherein selecting the first subset of the target locations comprises selecting a threshold number of target locations having the highest respective predicted likelihood scores.

4. The method of claim 1 , wherein identifying the plurality of initial target locations in the environment comprises:
dividing a region of the environment that is in a vicinity of the agent into a grid having a plurality of grid points; and
selecting at least some of the grid points in the grid as initial target locations.

5. The method of claim 1 , wherein identifying the plurality of initial target locations in the environment comprises:
obtaining road graph data identifying lanes on one or more roads in the environment; and
sampling, as initial target locations, points from the identified lanes.

6. The method of claim 5 , wherein sampling points from the identified lanes comprises:
for each identified lane, sampling points on a lane center line of the identified lane.

7. The method of claim 1 , wherein generating the predicted future trajectory for the agent that is a prediction of the future trajectory of the agent given that the target location is the intended final location for the future trajectory comprises:
processing (i) the encoded representation and data specifying the (ii) target location using a motion estimation neural network to generate the predicted future trajectory.

8. The method of claim 7 , wherein the target prediction neural network and the motion estimation neural network have been jointly trained.

9. The method of claim 7 , wherein selecting, as likely future trajectories of the agent starting from the current time point, one or more of the predicted future trajectories comprises:
generating a respective refined score for each of the predicted future trajectories that represents a likelihood that the predicted future trajectory will be the future trajectory of the agent after the current time point given the scene context data; and
selecting one or more of the predicted future trajectories based on the refined scores.

10. The method of claim 9 , wherein generating a respective refined score for each of the predicted future trajectories that represents a likelihood that the predicted future trajectory will be the future trajectory of the agent after the current time point given the scene context data comprises:
processing (i) the encoded representation and (ii) the predicted future trajectory using a trajectory scoring neural network to generate the respective refined score for the predicted future trajectory.

11. The method of claim 10 , wherein the target prediction neural network, the motion estimation neural network, and the trajectory scoring neural network have been jointly trained end-to-end.

12. The method of claim 10 , wherein selecting one or more of the predicted future trajectories comprises:
ordering the predicted future trajectories according to the respective refined scores; and
for each predicted future trajectory starting from a first predicted future trajectory in the order and until a specified number of trajectories have been selected:
determining whether the predicted future trajectory is more than a threshold distance from all trajectories that have already been selected according to a distance metric; and
selecting the predicted future trajectory only if the predicted trajectory is more than a threshold distance from all trajectories that have already been selected according to a distance metric.

13. The method of claim 1 , wherein the target prediction output further comprises data defining an offset for the corresponding initial target location, and wherein the target location is a location that is generated by applying the offset to coordinates of the initial target location.

14. The method of claim 13 , wherein the data defining the offset comprises, for each coordinate of the initial target location, parameters of respective probability distributions over offsets for the coordinate, and wherein the method further comprises generating the offset by sampling from the respective probability distributions.

15. The method of claim 13 , wherein the data defining the offset comprises, for each coordinate of the initial target location, a respective offset for the coordinate.

16. A system comprising:
one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
obtaining scene context data characterizing an environment, the scene context data comprising data that characterizes a trajectory of an agent in a vicinity of a vehicle in an environment up to a current time point;
processing the scene context data using a context encoding neural network to generate an encoded representation of the scene context data;
identifying a plurality of initial target locations in the environment;
for each of a plurality of target locations that each corresponds to one of the initial target locations, using a target prediction neural network to process (i) the encoded representation generated by the context encoding neural network and (ii) data specifying the respective initial target location corresponding to the respective target location to generate a target prediction output that specifies a respective predicted likelihood score that represents a likelihood that the target location will be an intended final location for a future trajectory of the agent starting from the current time point;
selecting a first subset of the target locations based on the respective predicted likelihood scores

Assignees

• Waymo Llc

Inventors

• Zhao Hang
• Gao Jiyang
• Sun Chen
• Shen Yi
• Chai Yuning
• Schmid Cordelia Luise
• Li Congcong
• Sapp Benjamin
• Anguelov Dragomir
• Lan Tian
• Shen Yue

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/02

  Neural networks · CPC title

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W2554/4049

  Relationship among other objects, e.g. converging dynamic objects · CPC title