Collision mitigated braking for autonomous vehicles

• US 9,862,364 B2
• Filed: 12/04/2015
• Issued: 01/09/2018
• Est. Priority Date: 12/04/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Waymo LLC (Alphabet Inc.)
• Inventors: Fairfield, Nathaniel
• Primary Examiner(s): Khatib, Rami
• Assistant Examiner(s): BOOMER, JEFFREY C
• Application Number:
  US14/959,067
• Publication Number:
  US 20170158175A1
• Time in Patent Office: 767 Days
• CPC Class Codes: B60T 2201/024 Collision mitigation systems
• CPC Class Codes: B60T 2210/36 Global Positioning System [GPS]
• CPC Class Codes: B60T 7/12 for automatic initiation; for initiation not subject to will of driver or passenger limiting speed of vehicles other than rail vehicles B60K31/00
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60T 8/17558 specially adapted for collision avoidance or collision mitigation road vehicle drive control systems for collision avoidance otherwise than by controlling a particular sub-unit B60W30/09
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2554/806 Relative heading
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 60/00276 for two or more other traffic participants
• CPC Class Codes: G05D 1/0055 with safety arrangements
• CPC Class Codes: G05D 1/0077 using redundant signals or controls
• 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

Aspects of the disclosure involve a collision mitigated braking system employed in vehicles operating in a self-driving (autonomous) mode. Collision mitigated braking provides redundancy to the vehicle'"'"'s main driving system in emergency situations. The collision mitigated braking system is configured to cause the vehicle to come to a stop when an imminent collision is perceived and the main driving system has not initiated a braking maneuver. A perception component employs information received from vehicle sensors, analyzing the sensor data to identify nearby objects of interest that are determined to be in the vehicle'"'"'s path or that could otherwise collide with the vehicle. A control component evaluates the objects of interest to determine whether immediate braking is required. If this is the case and the main driving system has not begun to brake, the control component causes the vehicle to perform immediate braking to avoid a possible collision.

Claims

1. A computer-implemented method for collision mitigated braking in a vehicle operating in an autonomous mode, the method comprising:

receiving, by one or more processors of one or more computing devices, heading and location information of one or more objects located externally to the vehicle from one or more sensors of the vehicle;

analyzing, by the one or more processors, the received heading and location information to filter selected ones of the objects that may collide with the vehicle in accordance with a predetermined false positive collision rate;

evaluating, by the one or more processors, the filtered selected objects to determine whether immediate braking is required to avoid a collision with any of the filtered selected objects;

determining that a main driving system of the vehicle for the autonomous mode has not initiated braking during the autonomous mode; and

in response to the evaluation and the determination, sending a signal from the one or more processors to a deceleration system of the vehicle to initiate immediate braking and thereby causing the deceleration system to brake;

wherein filtering the selected objects includes applying a padded polygon to different objects detected by the one or more sensors to identify whether there is a potential for collision with the different detected objects, and a size and shape of each padded polygon is based on one or more factors selected from the group consisting of;

a buffer braking distance from the front bumper of the vehicle to a respective object;

a sweep volume of the front bumper; and

the vehicle'"'"'s predicted path from a current time to a future time.

2. The method of claim 1, wherein the analyzing comprises independently evaluating the received heading and location information from laser and radar sensors of the vehicle.

3. The method of claim 1, wherein evaluating the selected objects includes evaluating a stopping distance model to calculate a distance to stop based upon the current movement of the vehicle, a model of the braking system, and a maximum braking amount.

4. The method of claim 1, wherein evaluating the selected objects includes predicting a future position of the vehicle at one or more points in time, in accordance with a primary path and speed plan obtained from a planning component of the main driving system.

5. The method of claim 1, wherein the signal sent to the braking system of the vehicle to initiate immediate braking causes the braking system to bring the vehicle to a complete stop.

6. The method of claim 1, wherein the signal sent to the braking system of the vehicle to initiate immediate braking causes the braking system to slow the vehicle according to a minimal braking threshold.

7. The method of claim 6, wherein slowing the vehicle is performed until there is no longer a danger of imminent collision.

8. A vehicle control system for a vehicle, the vehicle control system comprising one or more computing devices configured to:

receive heading and location information of one or more objects located externally to the vehicle from one or more sensors of the vehicle;

analyze the received heading and location information to filter selected ones of the objects that may collide with the vehicle in accordance with a predetermined false positive collision rate;

evaluate the filtered selected objects to determine whether immediate braking is required to avoid a collision with any of the filtered selected objects; and

determine that a main driving system of the vehicle for the autonomous mode has not initiated braking during an autonomous driving mode; and

in response to the evaluation and the determination, send a signal to initiate immediate braking of the vehicle to a deceleration system of the vehicle and thereby causing the deceleration system to brake;

wherein the one or more computing devices are configured to filter the selected objects by applying a padded polygon to different objects detected by the one or more sensors to identify whether there is a potential for collision with the different detected objects, and a size and shape of each padded polygon is based on one or more factors selected from the group consisting of;

a buffer braking distance from the front bumper of the vehicle to a respective object;

a sweep volume of the front bumper; and

the vehicle'"'"'s predicted path from a current time to a future time.

9. The system of claim 8, wherein evaluation of the selected objects by the system includes the one or more computing devices being configured to predict a future position of the vehicle at one or more points in time, in accordance with a primary path and speed plan obtained from a planning component of the main driving system.

10. The system of claim 8, wherein the signal sent to the braking system of the vehicle to initiate immediate braking causes the braking system to bring the vehicle to a complete stop.

11. The system of claim 8, wherein the signal sent to the braking system of the vehicle to initiate immediate braking causes the braking system to slow the vehicle according to a minimal braking threshold.

12. The system of claim 11, wherein slowing the vehicle is performed until there is no longer a danger of imminent collision.

13. 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 for collision mitigated braking in a vehicle operating in an autonomous mode, the method comprising:

receiving heading and location information of one or more objects located externally to the vehicle from one or more sensors of the vehicle;

analyzing the received heading and location information to filter selected ones of the objects that may collide with the vehicle in accordance with a predetermined false positive collision rate;

evaluating the filtered selected objects to determine whether immediate braking is required to avoid a collision with any of the filtered selected objects; and

determining that a main driving system of the vehicle for the autonomous mode has not initiated braking during the autonomous mode; and

in response to the evaluation and the determination, sending a signal from the one or more processors to a deceleration system of the vehicle to initiate immediate braking and thereby causing the deceleration system to brake;

wherein filtering the selected objects includes applying a padded polygon to different objects detected by the one or more sensors to identify whether there is a potential for collision with the different detected objects, and a size and shape of each padded polygon is based on one or more factors selected from the group consisting of;

a buffer braking distance from the front bumper of the vehicle to a respective object;

a sweep volume of the front bumper; and

the vehicle'"'"'s predicted path from a current time to a future time.

14. The non-transitory computer-readable medium of claim 13, wherein the analyzing comprises independently evaluating the received heading and location information from laser and radar sensors of the vehicle.

15. The non-transitory computer-readable medium of claim 13, wherein evaluating the selected objects includes evaluating a stopping distance model to calculate a distance to stop based upon the current movement of the vehicle, a model of the braking system, and a maximum braking amount.