Speed planning for autonomous vehicles

• US 10,640,111 B1
• Filed: 09/07/2016
• Issued: 05/05/2020
• Est. Priority Date: 09/07/2016
• Status: Active Grant

• Current Assignee: Waymo LLC (Alphabet Inc.)
• Original Assignee: Waymo LLC (Alphabet Inc.)
• Inventors: Gutmann, Jens-Steffen Ralf, Furman, Vadim, Kunz, Tobias
• Primary Examiner(s): Merlino, David P.
• Application Number:
  US15/258,324
• Time in Patent Office: 1,336 Days
• Field of Search: None
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2554/4042 Longitudinal speed
• CPC Class Codes: B60W 2554/4044 Direction of movement, e.g. backwards
• CPC Class Codes: B60W 2554/4045 Intention, e.g. lane change or imminent movement
• CPC Class Codes: B60W 2555/60 Traffic rules, e.g. speed limits or right of way
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 30/143 Speed control B60W30/16 takes precedence
• CPC Class Codes: B60W 30/18145 Cornering
• CPC Class Codes: B60W 30/18159 Traversing an intersection
• CPC Class Codes: B60W 60/0011 involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
• CPC Class Codes: B60W 60/0013 specially adapted for occupant comfort
• CPC Class Codes: B60W 60/0015 specially adapted for safety
• CPC Class Codes: B60W 60/0027 using trajectory prediction for other traffic participants

Abstract

Aspects of the disclosure relate to identifying and adjusting speed plans for controlling a vehicle in an autonomous driving mode. In one example, an initial speed plan for controlling speed of the vehicle for a first predetermined period of time corresponding to an amount of time along a route of the vehicle is identified. Data identifying an object and characteristics of that object is received from a perception system of the vehicle. A trajectory for the object that will intersect with the route at an intersection point at particular point in time is predicted using the data. A set of constraints is generated based on at least the trajectory. The speed plan is adjusted in order to satisfy the set of constraints for a second predetermined period of time corresponding to the amount of time. The vehicle is maneuvered in the autonomous driving mode according to the adjusted speed plan.

Claims

1. A method of maneuvering a vehicle in an autonomous driving mode, the method comprising:

identifying, by one or more processors, an initial speed plan for controlling speed of the vehicle for a first predetermined period of time corresponding to an amount of time along a route of the vehicle, the initial speed plan corresponding to a selected speed of the vehicle defined at least in part by a legal speed limit on the speed of the vehicle for a roadway on which the vehicle is currently located;

receiving, by the one or more processors, from a perception system of the vehicle, data identifying an object and characteristics of that object;

predicting, by the one or more processors, a trajectory for the object that will intersect with the route at an intersection point at a particular point in time using the data;

generating, by the one or more processors, a set of constraints including a first constraint based on at least the trajectory and a second constraint based on expected comfort of at least one of a passenger within the vehicle or a person associated with the object;

determining whether the first and second constraints can both be satisfied during a second predetermined period of time corresponding to the amount of time;

upon determining that both of the first and second constraints can be satisfied;

adjusting, by the one or more processors, the initial speed plan in order to satisfy the first and second constraints for a second predetermined period of time corresponding to the amount of time;

maneuvering, by the one or more processors, the vehicle in the autonomous driving mode according to the adjusted initial speed plan; and

upon determining that the first and second constraints cannot both be satisfied;

comparing an expected result if the vehicle were to return to the selected speed with an expected result if the vehicle were to come to a complete stop.

2. The method of claim 1, wherein the initial speed plan corresponds to a previously adjusted initial speed plan such that the initial speed plan is adjusted as an iterative process.

3. The method of claim 1, wherein a constraint of the set of constraints includes constraint that the vehicle should not be within a predetermined distance of the intersection point at the particular point in time.

4. The method of claim 1, further comprising determining a status of a traffic signal, and wherein generating a constraint of the set of constraints is based on the determined status.

5. The method of claim 1, further comprising:

receiving from the perception system of the vehicle, second data identifying a second object and characteristics of the second object including a speed of the second object, wherein the second object corresponds to a road user;

predicting a second trajectory of the second object that indicates that the vehicle will pass the second object; and

wherein the set of constraints includes a constraint that limits the speed of the vehicle relative to the speed of the second object when the vehicle passes the second object.

6. The method of claim 1, further comprising receiving from the perception system of the vehicle, second data identifying a second object and characteristics of the second object including a signal of the second object, wherein the second object corresponds to a road user, and wherein generating the set of constraints includes generating a first constraint of the set of constraints based on the signal of the second object.

7. The method of claim 6, further comprising, adjusting the adjusted initial speed plan to generate a speed plan based on the first constraint where the signal does not persist while the speed plan is being generated, and wherein the signal is a hand signal and the second object is a bicyclist.

8. The method of claim 1, wherein a constraint of the set of constraints is selected from a group consisting of:

a constraint that includes a deceleration limit corresponding to a mechanical limit of deceleration for the vehicle;

a constraint that includes a deceleration limit for the vehicle corresponding to a level of deceleration less than a recommended deceleration level to safely operate the vehicle;

a constraint that includes a headway distance limit between the vehicle and the object corresponding to a distance greater than a recommended headway distance to safely operate the vehicle; and

a constraint that includes a lateral gap distance limit between the vehicle and the object corresponding to a lateral gap distance greater than a recommended lateral gap distance to safely operate the vehicle.

9. The method of claim 1 wherein the speed of the vehicle remains constant during the initial speed plan.

10. The method of claim 1, wherein generating the second constraint based on the expected comfort includes determining an expected jerk value associated with the vehicle during the second period of time.

11. A system for maneuvering a vehicle in autonomous driving mode, the system comprising one or more processors configured to:

identify an initial speed plan for controlling speed of the vehicle for a first predetermined period of time corresponding to an amount of time along a route of the vehicle, the initial speed plan corresponding to a selected speed of the vehicle defined at least in part by a legal speed limit on the speed of the vehicle for a roadway on which the vehicle is currently located;

receive from a perception system of the vehicle, data identifying an object and characteristics of that object;

predict a trajectory for the object that will intersect with the route at an intersection point at a particular point in time using the data;

generate a set of constraints including a first constraint based on at least the trajectory and a second constraint based on expected comfort of at least one of a passenger within the vehicle or a person associated with the object;

determine whether the first and second constraints can both be satisfied during a second predetermined period of time corresponding to the amount of time;

upon determining that both of the first and second constraints can be satisfied;

adjust the initial speed plan in order to satisfy the set of constraints for a second predetermined period of time corresponding to the amount of time;

maneuvering the vehicle in the autonomous driving mode according to the adjusted initial speed plan; and

upon determining that the first and second constraints cannot both be satisfied;

compare an expected result if the vehicle were to return to the selected speed with an expected result if the vehicle were to come to a complete stop.

12. The system of claim 11, wherein the initial speed plan corresponds to a previously adjusted initial speed plan such that the initial speed plan is adjusted as an iterative process.

13. The system of claim 11, wherein a constraint of the set of constraints is selected from a group consisting of:

a constraint that includes constraint that the vehicle should not be within a predetermined distance of the intersection point at the particular point in time;

a constraint that includes a deceleration limit for the vehicle corresponding to a level of deceleration less than a recommended deceleration level to safely operate the vehicle;

a constraint that includes a headway distance limit between the vehicle and the object corresponding to a distance greater than a recommended headway distance to safely operate the vehicle; and

a constraint that includes a lateral gap distance limit between the vehicle and the object corresponding to a lateral gap distance greater than a recommend lateral gap distance to safely operate the vehicle.

14. The system of claim 11, wherein the one or more processors are further configured to determine a status of a traffic signal, and generating a constraint of the set of constraints is based on the status.

15. The system of claim 11, wherein the speed of the vehicle remains constant during the initial speed plan.

16. A non-transitory computer readable medium on which instructions are stored, the instructions when executed by one or more processors, cause the one or more processors to perform a method of controlling a vehicle in an autonomous driving mode, the method comprising:

identifying an initial speed plan for controlling speed of the vehicle for a first predetermined period of time corresponding to an amount of time along a route of the vehicle, the initial speed plan corresponding to a selected speed of the vehicle defined at least in part by a legal speed limit on the speed of the vehicle for a roadway on which the vehicle is currently located;

receiving from a perception system of the vehicle, data identifying an object and characteristics of that object;

determining whether the first and second constraints can both be satisfied during a second predetermined period of time corresponding to the amount of time;

upon determining that both of the first and second constraints can be satisfied;

predicting a trajectory for the object that will intersect with the route at an intersection point at a particular point in time using the data;

generating a set of constraints including a first constraint based on at least the trajectory and a second constraint based on expected comfort of at least one of a passenger within the vehicle or a person associated with the object;

adjusting the initial speed plan in order to satisfy the set of constraints for a second predetermined period of time corresponding to the amount of time;

maneuvering the vehicle according to the adjusted initial speed plan; and

upon determining that the first and second constraints cannot both be satisfied;

comparing an expected result if the vehicle were to return to the selected speed with an expected result if the vehicle were to come to a complete stop.