Smart vehicle

• US 9,711,050 B2
• Filed: 06/05/2015
• Issued: 07/18/2017
• Est. Priority Date: 06/05/2015
• Status: Active Grant

• Current Assignee: Aurora Operations Incorporated (Aurora Innovation, Inc.)
• Original Assignee: Bao Tran
• Inventors: Ansari, Arafat M. A.
• Primary Examiner(s): Shaawat, Mussa A
• Assistant Examiner(s): KERRIGAN, MICHAEL V
• Application Number:
  US14/732,555
• Publication Number:
  US 20160358477A1
• Time in Patent Office: 774 Days
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2556/20 Data confidence level
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 60/0027 using trajectory prediction for other traffic participants
• CPC Class Codes: B60W 60/0059 Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: G08G 1/162 event-triggered
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection
• CPC Class Codes: G08G 1/22 Platooning, i.e. convoy of communicating vehicles
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Abstract

A smart vehicle can be operated by generating a 3D model of a sensor'"'"'s field of view; receiving information from neighboring vehicles to compensate for blindspots in the sensor'"'"'s field of view and in a driver'"'"'s field of view; receiving traffic information, weather information; adjusting one or more characteristics of the plurality of 3D models based on the received traffic and weather information and blindspot information; aggregating the plurality of 3D models to generate a comprehensive 3D model; and combining the comprehensive 3D model with detailed map information; and using the combined comprehensive 3D model with detailed map information to maneuver the vehicle.

Claims

1. A method to follow a lane of a road with a smart vehicle, comprising:

creating with a processor a 3D model having x, y, and z coordinates of the road comprising the lane, a nearby vehicle, and the smart vehicle;

obtaining lane information that provides an estimated location of the lane;

controlling the smart vehicle based on the obtained lane information

estimating a path of each neighboring vehicle and updating the 3D model of the road, the smart vehicle and the nearby vehicle; and

when the lane information becomes unavailable or unreliable, controlling the smart vehicle to maintain a relative position of the smart vehicle using the 3D model of the road and the nearby vehicle based on one or more estimated paths until the lane information becomes available or reliable again.

2. The method of claim 1, wherein the lane information is based on at least one of a lane marking on the road, a geographic location of the vehicle, and a predetermined map of the road.

3. The method of claim 1, wherein determining that the lane information has become unavailable or unreliable comprises detecting that a confidence of the lane information is less than a predetermined threshold.

4. The method of claim 1, wherein determining that the lane information has become unavailable or unreliable comprises detecting that a confidence of the lane information is less than a predetermined threshold for at least a predetermined amount of time.

5. The method of claim 1, further comprising:

periodically obtaining updated lane information;

determining that the updated lane information has become reliable; and

in response to determining that the updated lane information has become reliable, ceasing to control the vehicle based on the estimated paths of the 3D model and using reliable lane information instead.

6. The method of claim 5, wherein determining that the updated lane information has become reliable comprises detecting that a confidence of the updated lane information is greater than a predetermined threshold.

7. The method of claim 1, further comprising using radio triangulation, laser ranging or camera estimation to monitor a speed of the neighboring vehicle;

and modifying a speed of the vehicle to be less than the speed of the neighboring vehicle.

8. The method of claim 1, wherein extrapolating the trajectory comprises extrapolating the path of each neighboring vehicle with a constant curvature.

9. The method of claim 1, further comprising:

identifying vehicles traveling to a common destination for a predetermined period;

organizing the vehicles into a flock; and

forming a flock with neighboring vehicles by applying a flocking behavior for each vehicle using a separation rule to avoid crowding vehicular neighbors, an alignment rule to steer towards average heading of vehicular neighbors, and a cohesion rule to maintain proximity to an average position of vehicular neighbors.

10. The method of claim 1, comprising communicating with neighboring vehicles to determine a relative position of the vehicle to neighboring vehicles.

11. The method of claim 10, comprising performing lane identification using flock information and maintaining a predetermined spacing between vehicles based on a plurality of predetermined flock behavior rules.

12. The method of claim 10, comprising flocking the vehicles over a plurality of lanes.

13. The method of claim 10, comprising maintaining two separate flocks of vehicles in opposite directions.

14. The method of claim 10, wherein the common destination comprises a segment of a vehicle'"'"'s final destination.

15. The method of claim 1, where vehicles traveling a same route is determined using a vehicle to vehicle communication protocol for identifying peers based upon encoded signals during peer discovery in a peer to peer network.

16. The method of claim 1, wherein the protocol is compatible with WiFi, cellular, or Proximity Services via LTE Device Broadcast.

17. The method of claim 1, comprising direct signaling that partitions a time-frequency resource into a number of segments can be utilized to communicate an identifier within a peer discovery interval.

18. The method of claim 1, wherein vehicles that share same driving segments broadcast expressions indicating their path(s), comprising detecting vehicles in the same segment as part of the proximity services for capturing and sharing crowd-sourced navigation data.

19. The method of claim 1, comprising capturing crowd-sourced information relating to:

closing of a lane;

predicting an avoidance maneuver;

predicting a congestion with respect to a segment of the route of the at least one vehicle; and

predicting traffic light patterns.

20. The method of claim 1, comprising determining an obstacle in the lane and changing the vehicle'"'"'s path to avoid the obstacle, wherein the obstacle comprises rocks, a lane closure, an inoperative vehicle, or a vehicle in an accident.