Perception-based speed limit estimation and learning

• US 9,747,506 B2
• Filed: 10/21/2015
• Issued: 08/29/2017
• Est. Priority Date: 10/21/2015
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Mullen, Jonathan Thomas
• Primary Examiner(s): COUSO, JOSE L
• Application Number:
  US14/919,540
• Publication Number:
  US 20170116485A1
• Time in Patent Office: 678 Days
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/052 with provision for determining speed or overspeed speed measuring in general G01P
• CPC Class Codes: G08G 1/09623 Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle G08G1/0967 takes precedence
• CPC Class Codes: G08G 1/09626 where the origin of the information is within the own vehicle, e.g. a local storage device, digital map
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/09675 where a selection from the received information takes place in the vehicle
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element
• CPC Class Codes: G08G 1/096791 where the origin of the information is another vehicle

Abstract

Systems, methods, and devices for estimating a speed limit are disclosed herein. A system for estimating a speed limit includes one or more perception sensors, an attribute component, an estimator component, and a notification component. The one or more perception sensors are configured to generate perception data about a region near a vehicle. The attribute component is configured to detect one or more environmental attributes based on the perception data. The estimator component is configured to determine an estimated speed limit based on the environmental attributes. The notification component is configured to provide the estimated speed limit to an automated driving system or driver assistance system of the vehicle.

Claims

1. A system comprising:

one or more perception sensors configured to generate perception data about a region near a vehicle;

an attribute component configured to detect one or more environmental attributes based on the perception data;

an estimator component configured to determine an estimated legal speed limit based on the environmental attributes, wherein the estimator component determines the estimated legal speed limit based on environmental attributes comprising one or more of a size of a shoulder of a road, a number of lanes on a road, a presence of houses, a presence of buildings, a presence of parked cars, a presence of a concrete medium, a lane marking, a curb, a rumble strip, a lane width, and a road curvature; and

a notification component configured to provide the estimated legal speed limit to an automated driving system or driver assistance system of the vehicle.

2. The system of claim 1, wherein the one or more environmental attributes comprise one or more physical attributes or features of a road, structure, or object in the region near the vehicle.

3. The system of claim 1, wherein the attribute component detects the one or more environmental attributes comprising one or more of:

the size of the shoulder of the road, the number of lanes on the road, the presence of houses, the presence of buildings, the presence of parked cars, the presence of the concrete medium, the lane marking, the curb, the rumble strip, the lane width, and the road curvature.

4. The system of claim 1, wherein the estimator component is configured to determine the estimated legal speed limit based on an estimation model, wherein the estimation model associates at least one of the one or more environmental attributes with a legal speed limit or an indication to adjust a legal speed limit.

5. The system of claim 1, wherein the one or more perception sensors comprise a camera and wherein the attribute component is configured to process an image from the camera to determine the one or more environmental attributes.

6. The system of claim 1, further comprising an arbitrated speed component configured to determine a high-confidence legal speed limit.

7. The system of claim 6, further comprising a learning component configured to update an estimation model to update an association between the one or more environmental attributes and an estimated legal speed limit based on the high-confidence legal speed limit.

8. The system of claim 6, wherein the arbitrated speed limit component determines the high-confidence legal speed limit based on data provided by a third party.

9. The system of claim 6, wherein the data provided by a third party comprises a road sign detected by the one or more sensors, map data stored by the system, a vehicle-to-vehicle communication, an infrastructure-to-vehicle communication, and data received via a mobile network.

10. A method for machine learning of legal speed limits, the method comprising:

receiving perception data from one or more perception sensors;

receiving an indication of an arbitrated legal speed limit for a location corresponding to the perception data;

identifying one or more environmental attributes based on the perception data, wherein the one or more environmental attributes comprise one or more of a size of a shoulder of a road, a number of lanes on a road, a presence of houses, a presence of buildings, a presence of parked cars, a presence of a concrete medium, a lane marking, a curb, a rumble strip, a lane width, and a road curvature; and

associating the one or more environmental attributes with a value of the arbitrated legal speed limit within an estimation model.

11. The method of claim 10, wherein the location corresponding to the perception data comprises a first location, wherein the method further comprises:

receiving perception data for a second location; and

determining an estimated legal speed limit for the second location based on the estimation model.

12. The method of claim 10, wherein the one or more perception sensors comprise a camera and the perception data comprises an image capture by the camera, wherein identifying the one or more environmental attributes comprises processing the image to determine the one or more environmental attributes.

13. The method of claim 10, wherein the arbitrated legal speed limit is received in data provided by a third party.

14. The method of claim 13, wherein the data provided by a third party comprises a road sign detected by the one or more sensors, map data stored by the system, a vehicle-to-vehicle communication, an infrastructure-to-vehicle communication, and data received via a mobile network.

15. Non-transitory computer readable storage media storing instructions that, when executed by one or more processors, cause the processors to:

process perception data to detect one or more environmental attributes of an area near a vehicle based on the perception data;

estimate a legal speed limit for the area near the vehicle based on the environmental attributes, wherein estimating the legal speed limit comprises estimating based on environmental attributes comprising one or more of a size of a shoulder of a road, a number of lanes on a road, a presence of houses, a presence of buildings, a presence of parked cars, a presence of a concrete medium, a lane marking, a curb, a rumble strip, a lane width, and a road curvature; and

notify an automated driving system or driver of the vehicle of the estimated legal speed limit.

16. The computer readable storage media of claim 15, wherein the instructions further cause the processor to determine that one or more of:

an arbitrated legal speed limit has not been determined for at least a threshold time or distance; and

an arbitrated legal speed limit has not been determined for a current road or region of the current road.

17. The computer readable storage media of claim 15, wherein the one or more environmental attributes comprise one or more physical attributes or features of a road, structure, or object in the region near the vehicle.

18. The computer readable storage media of claim 15, wherein the perception data comprise an image from a camera and wherein processing the perception data comprise processing an image from the camera to determine the one or more environmental attributes.

19. The computer readable storage media of claim 15, wherein the instructions further cause the processor to determine a high-confidence legal speed limit for the area and to update an estimation model to update an association between the one or more environmental attributes and an estimated legal speed limit based on the high-confidence legal speed limit.