Planning with dynamic state a trajectory of an autonomous vehicle

Patent metadata

Field	Value
Publication number	US-12060083-B2
Application number	US-202117239155-A
Country	US
Kind code	B2
Filing date	Apr 23, 2021
Priority date	Apr 23, 2021
Publication date	Aug 13, 2024
Grant date	Aug 13, 2024

Abstract

This disclosure describes an autonomous vehicle configured to obtain sensor data associated with objects proximate a projected route of the autonomous vehicle, determine static constraints that limit a trajectory of the autonomous vehicle along the projected route based on non-temporal risks associated with a first subset of the f objects, predict a position and speed of the autonomous vehicle as a function of time along the projected route based on the static constraints, identify temporal risks associated with a second subset of the objects based on the predicted position and speed of the autonomous vehicle, determine dynamic constraints that further limit the trajectory of the autonomous vehicle along the projected route to help the autonomous vehicle avoid the temporal risks associated with the second subset of the objects, and adjust the trajectory of the autonomous vehicle in accordance with the static constraints and the dynamic constraints.

First claim

What is claimed is:

1. A system, comprising:
at least one processor, and
at least one memory storing instructions thereon that, when executed by the at least one processor, cause the at least one processor to:
obtain sensor data associated with a plurality of objects proximate a projected route of an autonomous vehicle;
determine static constraints that limit a trajectory of the autonomous vehicle along the projected route, the static constraints comprising one or more objects of the plurality of objects not predicted to change status as the autonomous vehicle traverses the projected route;
predict a position and speed of the autonomous vehicle along the projected route over time;
identify one or more dynamic objects, the one or more dynamic objects comprising one or more objects of the plurality of objects predicted to change status as the autonomous vehicle traverses the projected route;
determine one or more zones of temporal risk posed by the one or more dynamic objects, wherein to determine a first zone of temporal risk of the one or more zones of temporal risk posed by a first dynamic object of the one or more dynamic objects, the instructions cause the at least one processor to:
determine, using a machine-learning model, a predicted status of the first dynamic object over time, wherein the machine-learning model is trained using historical data,
determine a confidence level of the predicted status, wherein the confidence level is based at least in part on data collected about the first dynamic object and an estimated time to the first dynamic object, and
determine, based on the predicted status and the confidence level of the predicted status, a spatial region around the first dynamic object in which an unsafe event is predicted to occur if the autonomous vehicle enters the spatial region;

determine, based on the predicted position and speed of the autonomous vehicle and the one or more zones of temporal risk, an acceleration profile for the autonomous vehicle;
update the trajectory of the autonomous vehicle along the projected route based on the static constraints and the acceleration profile; and
navigate the autonomous vehicle based on the updated trajectory.

2. The system of claim 1 , wherein the first dynamic object is a pedestrian in a crosswalk.

3. The system of claim 1 , wherein the instructions further cause the at least one processor to update the trajectory after one or more zones of temporal risk are detected to be a threshold distance away from the projected route.

4. The system of claim 2 , wherein a size of the first zone of temporal risk is determined based on a size of the crosswalk.

5. The system of claim 1 , wherein the first dynamic object is a traffic light and the first zone of temporal risk associated with the traffic light extends across a majority of a traffic intersection associated with the traffic light.

6. The system of claim 5 , wherein the instructions further cause the at least one processor to, in response to the traffic light turning yellow, determine an acceleration profile allowing the autonomous vehicle to enter the traffic intersection prior to the traffic light turning red.

7. The system of claim 6 , wherein the historical data comprises an average amount of time for the traffic light to turn from yellow to red.

8. The system of claim 1 , wherein to predict a position and speed of the autonomous vehicle along the projected route over time, the instructions further causc the at least one processor to determine a maximum possible speed profile for the autonomous vehicle.

9. The system of claim 1 , wherein the plurality of objects proximate the projected route comprises one or more objects trailing the autonomous vehicle and wherein the acceleration profile comprises a maximum deceleration limit based upon the one or more objects trailing the autonomous vehicle at less than a threshold distance.

10. The system of claim 1 , wherein the instructions further cause the at least one processor to:
determine a type of each object of the plurality of objects proximate the projected route; and
prioritize avoidance of zones of temporal risk associated with a first type of object over avoidance of zones of temporal risk associated with a second type of object based on the first type of object and the second type of object.

11. The system of claim 1 , wherein the instructions further cause the at least one processor to determine a second zone of temporal risk associated with the first dynamic object of the one or more dynamic objects in response to a detected change in status of the first dynamic object.

12. The system of claim 1 , wherein the first dynamic object is a pedestrian crossing a street outside of a crosswalk.

13. The system of claim 1 , wherein the instructions further cause the at least one processor to activate an emergency collision avoidance system in response to a determination that sensor data from a sensor of the autonomous vehicle indicates an imminent collision.

14. The system of claim 1 , wherein the acceleration profile is a first acceleration profile and the updated trajectory is a first updated trajectory, wherein the instructions further cause the at least one processor to:
determine a second zone of temporal risk associated with the first dynamic object of the one or more dynamic objects in response to a determination that a status of the first dynamic object is different than a predicted status of the first dynamic object;
determine a second acceleration profile for the autonomous vehicle based at least in part on the second zone of temporal risk,
determine a second updated trajectory of the autonomous vehicle based at least in part on the second acceleration profile; and
navigate the autonomous vehicle in accordance with the second updated trajectory.

15. The system of claim 14 , wherein the instructions further cause the at least one processor to:
determine that a vehicle on a crossing road is likely to enter an intersection at a same time as the autonomous vehicle;
determine that the autonomous vehicle is too close to the intersection to stop in time to avoid entering the intersection; and
accelerate the autonomous vehicle as it approaches the intersection and maintaining a higher speed than predicted through the intersection to avoid a collision with the vehicle on the crossing road.

16. The system of claim 1 , wherein status comprises one of a location or state of an object.

17. The system of claim 1 , wherein the unsafe event comprises a collision.

18. The system of claim 1 , wherein the unsafe event comprises navigating the autonomous vehicle through a red light.

19. The system of claim 1 , wherein the instructions further cause the at least one processor to:
determine speed constraints, the speed constraints comprising at least one of a posted speed limit, a posted recommended speed, or a maximum speed of the autonomous vehicle; and
predict a position and speed of the autonomous vehicle along the projected route over time based at least in part on the speed constraints and the static constraints.

20. The system of claim 19 , wherein the instructions cause the autonomous vehicle to violate a speed constraint only when required to avoid an unsafe event.

21. The system of claim 1 , wherein the instructions further cause the at least one processor to:
determine acceleration constraints, the acceleration constraints comprising at least one of an acceleration limit designed to prevent damage to a power train

Assignees

• Motional Ad Llc

Inventors

• Pendleton Scott Drew
• Andersen Hans

Classifications

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W2554/80

  Spatial relation or speed relative to objects · CPC title

• B60W2554/4029

  Pedestrians · CPC title

• B60W2554/408

  Traffic behavior, e.g. swarm · CPC title

• B60W60/0016 Primary

  of the vehicle or its occupants · CPC title