Methods and systems for determining instructions for pulling over an autonomous vehicle

• US 9,523,984 B1
• Filed: 07/12/2013
• Issued: 12/20/2016
• Est. Priority Date: 07/12/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Herbach, Joshua Seth, Fairfield, Nathaniel
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US13/940,429
• Time in Patent Office: 1,257 Days
• Field of Search: 701/23, 701/28, 701400-541, 340988-996
• US Class Current: 1/1
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2555/00 Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 2720/103 Speed profile
• CPC Class Codes: B60W 2720/106 Longitudinal acceleration
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/18009 related to particular drive situations
• CPC Class Codes: B60W 30/181 Preparing for stopping
• CPC Class Codes: B60W 50/0225 Failure correction strategy
• CPC Class Codes: B60W 60/0015 specially adapted for safety
• CPC Class Codes: B62D 15/025 Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation B62D1/28 takes precedence
• CPC Class Codes: B62D 15/0265 Automatic obstacle avoidance by steering
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00

Abstract

Methods and systems for determining instructions for pulling over an autonomous vehicle are described. An example method may involve identifying a region of a road ahead of the autonomous vehicle based on lane boundaries of the road, one or more road boundaries indicating an edge of the road, and a size of the autonomous vehicle. The method may also involve determining a braking profile for reducing the speed of the autonomous vehicle based on the region and a speed of the autonomous vehicle. The method may also involve determining, based on the braking profile, a trajectory such that the autonomous vehicle will travel within the region while reducing the speed of the autonomous vehicle. The method may further involve determining instructions for pulling over and stopping the autonomous vehicle in the region in accordance with the determined trajectory and storing the instructions in a memory accessible by a computing device.

Claims

1. A method performed by a computing system configured to control an autonomous vehicle, the method comprising:

receiving, by at least one processor of the computing system, and from one or more sensors in communication with the computing system, sensor data indicative of lane boundaries of a region of a road of travel ahead of the autonomous vehicle and one or more road boundaries indicating an edge of the road in the region;

based on the sensor data and further based on a size of the autonomous vehicle, the at least one processor;

(i) determining a distance between the autonomous vehicle and the lane boundaries of the road, (ii) determining a distance between the autonomous vehicle and the one or more road boundaries, (iii) comparing the determined distances to a predetermined threshold distance and to the size of the autonomous vehicle, and (iv) based on the determined distances satisfying the predetermined threshold, selecting the region to be a region in which to pull over and stop the autonomous vehicle;

based on a speed of the autonomous vehicle and based on the region, determining, by the at least one processor, a braking profile for reducing the speed of the autonomous vehicle while travelling within the region;

based on the braking profile, determining, by the at least one processor, a trajectory the autonomous vehicle navigates within the region while reducing the speed of the autonomous vehicle in accordance with the braking profile;

the at least one processor continuously determining up-to-date instructions to cause the autonomous vehicle to pull over and stop during travel as an environment of the autonomous vehicle changes and storing the up-to-date instructions in a memory of the computing system accessible by the at least one processor; and

based on the stored up-to-date instructions, the computing system causing the autonomous vehicle to pull over and stop in the region while navigating along the trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile.

2. The method of claim 1, wherein determining the braking profile comprises:

determining a plurality of phases including a first phase, a second phase following the first phase, and a third phase following the second phase, determining, for each phase of the plurality of phases, a respective rate at which to reduce the speed of the autonomous vehicle while travelling within the region, and determining respective lateral displacements the autonomous vehicle navigates within the region during the plurality of phases, wherein the lateral displacement of the autonomous vehicle during the second phase is at least equal to the lateral displacement of the autonomous vehicle during the first phase and the lateral displacement of the autonomous vehicle during the third phase, and wherein the respective rate of the third phase is greater than the respective rates of the first phase and the second phase.

3. The method of claim 2, wherein at least one phase of the plurality of phases is based on at least a portion of unobstructed drivable space within the region, and wherein the respective rates include respective rates at which to reduce the speed of the autonomous vehicle while travelling within the portion of unobstructed drivable space.

4. The method of claim 1, further comprising:

continuously determining, by the at least one processor, as the environment of the autonomous vehicle changes, up-to-date default instructions for maintaining a current trajectory of the autonomous vehicle and maintaining the speed of the autonomous vehicle so as to not pull over and stop the autonomous vehicle; and

the at least one processor storing the up-to-date default instructions in the memory accessible by the at least one processor.

5. The method of claim 1, further comprising:

receiving, at the at least one processor, information indicative of a failure of one or more systems of the autonomous vehicle; and

in response to receiving the information indicative of the failure of the one or more systems of the autonomous vehicle, and based on the stored up-to-date instructions, the at least one processor causing the autonomous vehicle to pull over and stop in the region while navigating along the trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile.

6. The method of claim 1, wherein the stored up-to-date instructions include instructions to adjust a steering angle of the autonomous vehicle so as to navigate the determined trajectory.

7. The method of claim 1,

wherein determining the distance between the autonomous vehicle and the lane boundaries of the road and determining the distance between the autonomous vehicle and the one or more road boundaries comprises:

determining a location of (i) a rightmost lane in the region, (ii) a rightmost boundary of the rightmost lane in the region, and (iii) a rightmost edge of the road in the region, and

based on the determined locations, determining (i) a lateral distance from a center of the rightmost lane to the rightmost boundary of the rightmost lane and (ii) a lateral distance from the center of the rightmost lane to the rightmost edge of the road,

wherein comparing the determined distances to the predetermined threshold distance and to the size of the autonomous vehicle comprises making a determination of whether the lateral distance from the center of the rightmost lane to the rightmost boundary of the rightmost lane plus a width of the autonomous vehicle plus the predetermined threshold distance is less than the lateral distance from the center of the rightmost lane to the rightmost edge of the road, and

wherein selecting the region to be the region in which to pull over and stop the autonomous vehicle comprises selecting the region to be the region in which to pull over and stop the autonomous vehicle in response to the determination being that the lateral distance from the center of the rightmost lane to the rightmost boundary of the rightmost lane plus the width of the autonomous vehicle plus the predetermined threshold distance is less than the lateral distance from the center of the rightmost lane to the rightmost edge of the road.

8. The method of claim 1, further comprising:

before comparing the determined distances to the predetermined threshold distance and to the size of the autonomous vehicle, the at least one processor;

receiving sensor data that indicates a speed limit of the road; and

adjusting the predetermined threshold distance based on the sensor data that indicates the speed limit of the road,

wherein comparing the determined distances to the predetermined threshold distance and to the size of the autonomous vehicle comprises comparing the determined distances to the adjusted predetermined threshold distance and to the size of the autonomous vehicle.

9. The method of claim 1, further comprising:

before comparing the determined distances to the predetermined threshold distance and to the size of the autonomous vehicle, the at least one processor;

based on predetermined map data of the road stored in the memory accessible by the at least one processor, determining a width of the road in the region; and

adjusting the predetermined threshold distance based on the width of the road in the region,

wherein comparing the determined distances to the predetermined threshold distance and to the size of the autonomous vehicle comprises comparing the determined distances to the adjusted predetermined threshold distance and to the size of the autonomous vehicle.

10. A non-transitory computer readable medium having stored thereon instructions that, upon execution by a computing device configured to control an autonomous vehicle, cause the computing device to perform functions comprising:

while the autonomous vehicle is travelling on a road along a trajectory at a speed and while an environment of the autonomous vehicle changes, continuously (i) determining up-to-date instructions to cause the autonomous vehicle to pull over and stop during travel and (ii) storing the up-to-date instructions in a memory accessible by the computing device, wherein determining and storing the up-to-date instructions comprises;

selecting a suitable region of the road ahead of an autonomous vehicle to be an up-to-date region in which to pull over and stop the autonomous vehicle while avoiding obstacles in the up-to-date region,

based on the speed of the autonomous vehicle and based on the up-to-date region, determining a braking profile corresponding to the up-to-date region, the braking profile being for reducing the speed of the autonomous vehicle while travelling within the up-to-date region, and

based on the braking profile, (i) determining the up-to-date instructions for causing the autonomous vehicle to pull over and stop in the up-to-date region while navigating along an adjusted trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile corresponding to the up-to-date region, and (ii) storing the up-to-date instructions in a memory accessible by the computing device; and

based on the stored up-to-date instructions, causing the autonomous vehicle to pull over and stop in the up-to-date region while navigating along the adjusted trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile corresponding to the up-to-date region.

11. The non-transitory computer readable medium of claim 10, the functions further comprising determining the predetermined threshold distance based on one or more of:

a type of the road boundaries, a width of the road, and a speed limit of the road.

12. The non-transitory computer readable medium of claim 10, wherein the sensor data further indicates one or more objects ahead of the autonomous vehicle on the road, and wherein determining the braking profile comprises determining the first rate, the second rate, and the third rate based on the one or more objects such that the autonomous vehicle will avoid the one or more objects within the region while reducing the speed of the autonomous vehicle in accordance with the braking profile.

13. The non-transitory computer readable medium of claim 12, wherein determining the trajectory comprises determining a trajectory the autonomous vehicle navigates within the region while avoiding the one or more objects within the region and while reducing the speed of the autonomous vehicle in accordance with the braking profile.

14. The non-transitory computer readable medium of claim 12, wherein the one or more objects include one or more of a traffic cone, a road boundary barrier, and another vehicle.

15. A system comprising:

at least one processor; and

a memory having stored thereon instructions that, upon execution by the at least one processor, cause the system to perform functions comprising;

receiving, from one or more sensors coupled to the autonomous vehicle, sensor data indicative of lane boundaries of a region of a road of travel ahead of the autonomous vehicle and one or more road boundaries indicating an edge of the road in the region;

based on the sensor data and further based on a size of the autonomous vehicle;

(i) determining a distance between the autonomous vehicle and the lane boundaries of the road, (ii) determining a distance between the autonomous vehicle and the one or more road boundaries, (iii) comparing the determined distances to a predetermined threshold distance and to the size of the autonomous vehicle, and (iv) based on the determined distances satisfying the predetermined threshold, selecting the region to be a region in which to pull over and stop the autonomous vehicle;

based on a speed of the autonomous vehicle and based on the region, determining a braking profile for reducing the speed of the autonomous vehicle while travelling within the region;

based on the braking profile, determining a trajectory the autonomous vehicle navigates within the region while reducing the speed of the autonomous vehicle in accordance with the braking profile;

determining instructions for causing the autonomous vehicle to pull over and stop in the region while navigating along the trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile;

continuously determining up-to-date instructions to cause the autonomous vehicle to pull over and stop during travel as an environment of the autonomous vehicle changes and storing the up-to-date instructions in the memory accessible and executable by the at least one processor; and

based on the stored up-to-date instructions, causing the autonomous vehicle to pull over and stop in the region while navigating along the trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile.

16. The system of claim 15, the functions further comprising:

referring to predetermined map data of the road stored in the memory,

wherein the predetermined map data includes information indicating at least a portion of the lane boundaries of the road and at least a portion of the one or more road boundaries, and

wherein determining the distances, comparing the determined distances, and selecting the region in which to pull over and stop the autonomous vehicle are based on the predetermined map data of the road.

17. The system of claim 15, wherein the predetermined map data further includes information indicating a type of lanes of the road, a type of the road boundaries, road intersections ahead of the autonomous vehicle, and one or more obstacles ahead of the autonomous vehicle.

18. The system of claim 15, the functions further comprising:

as the environment of the autonomous vehicle changes, continuously determining up-to-date default instructions for maintaining a current trajectory of the autonomous vehicle and maintaining the speed of the autonomous vehicle so as to not pull over and stop the autonomous vehicle; and

storing the up-to-date default instructions in the memory accessible and executable by the at least one processor.

19. The system of claim 15, the functions further comprising:

receiving information indicative of a failure of one or more systems of the autonomous vehicle; and

in response to receiving the information indicative of the failure of the one or more systems of the autonomous vehicle, and based on the stored up-to-date instructions, the at least one processor causing the autonomous vehicle to pull over and stop in the region while navigating along the trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile.

20. The system of claim 15, wherein the braking profile comprises a plurality of phases including respective rates at which to reduce the speed of the autonomous vehicle while travelling within the region, and

wherein the braking profile includes a piecewise linear function associated with the plurality of phases and representative of the respective rates.

21. A method performed by a computing system configured to control an autonomous vehicle, the method comprising:

while the autonomous vehicle is travelling on a road along a trajectory at a speed and while an environment of the autonomous vehicle changes, at least one processor of the computing system continuously (i) determining up-to-date instructions to cause the autonomous vehicle to pull over and stop during travel and (ii) storing the up-to-date instructions in a memory of the computing system accessible by the at least one processor, wherein determining and storing the up-to-date instructions comprises;

the at least one processor selecting a suitable region of the road ahead of an autonomous vehicle to be an up-to-date region in which to pull over and stop the autonomous vehicle while avoiding obstacles in the up-to-date region;

based on the speed of the autonomous vehicle and based on the up-to-date region, the at least one processor determining a braking profile corresponding to the up-to-date region, the braking profile being for reducing the speed of the autonomous vehicle while travelling within the up-to-date region;

based on the braking profile, the at least one processor (i) determining the up-to-date instructions for causing the autonomous vehicle to pull over and stop in the up-to-date region while navigating along an adjusted trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile corresponding to the up-to-date region, and (ii) storing the up-to-date instructions in a memory of the computing system accessible by the at least one processor; and

based on the stored up-to-date instructions, the computing system causing the autonomous vehicle to pull over and stop in the up-to-date region while navigating along the adjusted trajectory and reducing the speed of the autonomous vehicle in accordance with the braking profile corresponding to the up-to-date region.