Approach for consolidating observed vehicle trajectories into a single representative trajectory

• US 8,825,265 B1
• Filed: 03/16/2012
• Issued: 09/02/2014
• Est. Priority Date: 03/16/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Zhu, Jiajun
• Primary Examiner(s): To, Tuan C.
• Assistant Examiner(s): Hilgendorf, Dale W
• Application Number:
  US13/422,688
• Time in Patent Office: 900 Days
• Field of Search: 701/1, 701/2, 701/23, 701/27, 701/28, 701/41, 701/48, 701/3, 701/4, 701/5, 701/6, 701/7, 701/11, 701/14, 701/15, 701/16, 701/17, 701/18, 701/24, 701/25, 701/26
• US Class Current: 701/26
• 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 2050/048 displaying data transmitted between vehicles, e.g. for platooning, control of inter-vehicle distance
• CPC Class Codes: B60W 2554/408 Traffic behavior, e.g. swarm
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 40/072 Curvature of the road
• 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: B62D 1/00 Steering controls, i.e. means for initiating a change of direction of the vehicle
• CPC Class Codes: B62D 15/00 Steering not otherwise provided for
• 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 15/0255 Automatic changing of lane, e.g. for passing another vehicle
• CPC Class Codes: B62D 15/026 combined with automatic distance control, i.e. electronic tow bar
• CPC Class Codes: B62D 6/00 Arrangements for automatically controlling steering depending on driving conditions sensed and responded to, e.g. control circuits means for initiating a change in direction B62D1/00; steering valves B62D5/06; combined with means for inclining the vehicle body or wheels on bends B62D9/00
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01S 13/865 Combination of radar systems with lidar systems
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 15/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S15/46
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• CPC Class Codes: G01S 17/88 : Lidar systems specially adapted for specific applications
• CPC Class Codes: G01S 2013/9325 : for inter-vehicle distance regulation, e.g. navigating in platoons
• CPC Class Codes: G01S 2205/002 : for traffic control, mobile tracking, guidance, surveillance or anti-collision
• CPC Class Codes: G05D 1/00 : Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots drive control systems specially adapted for autonomous road vehicles B60W60/00
• 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
• CPC Class Codes: G05D 1/0212 : with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G05D 1/0214 : in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0223 : involving speed control of the vehicle vehicle fittings for automatically controlling, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator B60K31/00
• CPC Class Codes: G05D 1/0246 : using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0287 : involving a plurality of land vehicles, e.g. fleet or convoy travelling traffic control systems for road vehicles G08G1/00, particularly anticollision systems G08G1/16
• CPC Class Codes: G05D 1/0293 : Convoy travelling
• CPC Class Codes: G08G 1/096725 : where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/20 : Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
• CPC Class Codes: G08G 1/22 : Platooning, i.e. convoy of communicating vehicles

Abstract

A method and apparatus is provided for controlling the operation of an autonomous vehicle. According to one aspect, the autonomous vehicle may track the trajectories of other vehicles on a road. Based on the other vehicle'"'"'s trajectories, the autonomous vehicle may generate a pool of combined trajectories. Subsequently, the autonomous vehicle may select one of the combined trajectories as a representative trajectory. The representative trajectory may be used to change at least one of the speed or direction of the autonomous vehicle.

Claims

1. A method comprising:

tracking a plurality of road vehicles to obtain a plurality of observed trajectories, each one of the plurality of observed trajectories including locations passed by a given road vehicle from the plurality of road vehicles;

generating, by a processor, a plurality of trajectories, each one of the plurality of generated trajectories being generated using a different observed trajectory as a base, and each one of the plurality of generated trajectories being generated by;

(i) selecting one of the plurality of observed trajectories as the base;

(ii) combining the selected observed trajectory with remaining ones in the plurality of observed trajectories to generate a resultant set of locations; and

(iii) combining the resultant set of locations with all observed trajectories in the plurality;

selecting a first generated trajectory from the plurality of generated trajectories; and

changing at least one of a speed of the given road vehicle and a direction of the given road vehicle based on the selected first generated trajectory.

2. The method of claim 1, wherein combining the selected observed trajectory comprises identifying, for each location in the selected observed trajectory, locations in remaining ones of the plurality of observed trajectories that are within a predetermined distance from the location in the selected observed trajectory.

3. The method of claim 1, wherein the plurality of generated trajectories is generated using an expectation-maximization (EM) process.

4. The method of claim 1, wherein the first generated trajectory is selected based on a characteristic of a curvature of the first generated trajectory.

5. The method of claim 1, wherein the first generated trajectory is selected based on a discontinuity in the first generated trajectory.

6. The method of claim 1, wherein the first generated trajectory is selected based on a characteristic of a distribution of locations in the first generated trajectory.

7. The method of claim 1, further comprising:

determining a current location of the given road vehicle; and

wherein the first generated trajectory is selected based on a distance between the current location and a location that is part of the first generated trajectory.

8. A method comprising:

determining a plurality of observed trajectories of road vehicles that are travelling on the same road as a first vehicle;

determining a first location by combining locations found in two or more observed trajectories from the plurality of observed trajectories;

selecting a second location that is part of an observed trajectory from the plurality of observed trajectories;

calculating, by a processor, a third location based on the first location and the second location, the third location being located between the first location and the second location; and

controlling, by the processor, the operation of the first vehicle based on the third location.

9. The method of claim 8, wherein the second location is selected based on a distance to the first location.

10. The method of claim 8, wherein controlling the operation of the first vehicle includes changing at least one of a speed of the first vehicle and a direction of the first vehicle based on the third location.

11. The method of claim 8, wherein the third location is used in controlling the operation of the first vehicle only when it is determined by the processor that the third location is within a predetermined distance from the first location.

12. The method of claim 8, wherein:

the first location and the second location are calculated during different iterations of a process for generating the third location, the process being executed by the processor; and

the third location is used in controlling the operation of the first vehicle only when it is determined by the processor that a predetermined number of iterations of the process have been completed.

13. The method of claim 8, wherein:

the first location is part of a first generated trajectory;

the third location is part of a third generated trajectory; and

the third location is used in controlling the operation of the first vehicle only when the third trajectory satisfies a criterion for similarity in shape to the first trajectory.

14. The method of claim 11, further comprising:

identifying a constraint for at least one of a shape of the first observed trajectory, and a quality of information used as a basis for determining the first observed trajectory;

determining a characteristic of the first trajectory, the characteristic concerning at least one of the shape of the first observed trajectory, and quality of information used as a basis for determining the first observed trajectory; and

determining, based on the determined characteristic, an extent to which the first trajectory meets the constraint;

wherein the third location is also calculated based on the extent to which the first trajectory meets the constraint.

15. An apparatus comprising:

a processor configured to;

track a plurality of road vehicles to obtain a plurality of observed trajectories, wherein each observed trajectory is associated with a tracked vehicle and each of the observed trajectories correspond to a plurality of locations;

execute a process including an initial iteration that is executed first and a final iteration that is executed last, wherein;

(i) the initial iteration generates a resultant set of locations based on the plurality of locations from the observed trajectories, and

(ii) each subsequent iteration after the initial iteration generates another resultant set of locations based on the resultant set of locations that is generated during a preceding iteration, and

change at least one of a speed of a following vehicle and a direction of the following vehicle based on one or more locations that are part of the another resultant set generated by the final iteration.

16. The apparatus of claim 15, wherein the process implements an expectation-maximization (EM) process.

17. The apparatus of claim 15, wherein a number of times the processor performs a subsequent iteration in the process depends on a rule specifying a maximum number of iterations.

18. The apparatus of claim 15, wherein a number of times the processor performs a subsequent iteration in the process depends on a comparison between locations in the another resultant set generated by the final iteration and locations in a resultant set generated by an iteration preceding the final iteration.

19. The apparatus of claim 15, wherein the another resultant set of locations generated by the final iteration is based on the resultant set of locations generated during an iteration immediately preceding the final iteration.