UTILIZING QUALITATIVE MODELS TO PROVIDE TRANSPARENT DECISIONS FOR AUTONOMOUS VEHICLES

• US 20190322287A1
• Filed: 04/19/2019
• Published: 10/24/2019
• Est. Priority Date: 04/23/2018
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: ESCRIG-MONFERRER, Maria Teresa, KIM, Sang-Ik, MINARCIN, Monika
• Granted Patent: US 11,084,496 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2050/0031 Mathematical model of the vehicle
• CPC Class Codes: B60W 2400/00 Indexing codes relating to detected, measured or calculated conditions or factors
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/18109 Braking
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 50/06 Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
• 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: G06N 20/00 Machine learning

Abstract

A device receives quantitative data from sensors associated with an autonomous vehicle traveling on a road with other vehicles and from other sensors, and processes the quantitative data, with a first model, to determine distances between the autonomous vehicle and the other vehicles. The device processes the quantitative data, with a second model, to determine relative orientations between the autonomous vehicle and the other vehicles, and generates a conceptual neighborhood graph, based on a third model. The device identifies a subset of the conceptual neighborhood graph, and determines relative trajectories between the autonomous vehicle and the other vehicles based on the distances, the relative orientations, and the subset of the conceptual neighborhood graph. The device determines a decision for the autonomous vehicle based on the distances, the relative orientations, and the relative trajectories, and provides, to the autonomous vehicle, information instructing the autonomous vehicle to implement the decision.

Claims

1. A method, comprising:

receiving, by a device, quantitative data from sensors associated with an autonomous vehicle traveling on a road with other vehicles and from sensors associated with another source;

processing, by the device, the quantitative data, with a first qualitative model, to determine distances between the autonomous vehicle and the other vehicles;

processing, by the device, the quantitative data, with a second qualitative model, to determine relative orientations between the autonomous vehicle and the other vehicles;

generating, by the device, a conceptual neighborhood graph, based on a third qualitative model;

identifying, by the device, a subset of the conceptual neighborhood graph that includes information indicating potential collisions between the autonomous vehicle and the other vehicles;

determining, by the device, relative trajectories between the autonomous vehicle and the other vehicles based on the distances, the relative orientations, and the subset of the conceptual neighborhood graph;

determining, by the device, a decision for the autonomous vehicle based on the distances, the relative orientations, and the relative trajectories; and

providing, by the device and to the autonomous vehicle, information instructing the autonomous vehicle to implement the decision,

the autonomous vehicle to implement the decision based on the information instructing the autonomous vehicle to implement the decision.

2. The method of claim 1, further comprising:

storing information associated with the decision and historical decisions,

the historical decisions being previously determined by the device.

3. The method of claim 1, further comprising:

providing, for display, information associated with the decision and historical decisions,

the historical decisions being previously determined by the device.

4. The method of claim 1, wherein the decision includes one of:

stay in a lane at a constant speed,

accelerate,

decelerate,

overtake on the left,

overtake on the right, or

stop.

5. The method of claim 1, wherein, when the road is a highway, the decision includes one of:

stay in a second to the left lane of the highway at about a speed limit or a speed of traffic flow, when traffic density of the highway is low,

utilize a high occupancy vehicle (HOV) lane, when the highway includes a HOV lane and the autonomous vehicle includes two or more passengers, or

move to a less-dense lane of the highway, that is closer to or faster than the speed limit or the speed of the traffic flow, when the traffic density is medium or high.

6. The method of claim 1, further comprising:

determining whether a particular distance between the autonomous vehicle and one of the other vehicles satisfies a first threshold under normal road conditions;

or

determining whether the particular distance between the autonomous vehicle and the one of the other vehicles satisfies a second threshold under abnormal road conditions,

wherein the second threshold is greater than the first threshold.

7. The method of claim 1, wherein the third qualitative model includes a qualitative rectilinear projection calculus (QRPC) model.

8. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to;

receive quantitative data from sensors associated with an autonomous vehicle;

process the quantitative data, with a first qualitative model, to determine distances between the autonomous vehicle and other vehicles;

process the quantitative data, with a second qualitative model, to determine relative orientations between the autonomous vehicle and the other vehicles;

process the distances and the relative orientations, with a third qualitative model, to determine relative trajectories between the autonomous vehicle and the other vehicles;

determine a decision for the autonomous vehicle based on the distances, the relative orientations, and the relative trajectories; and

provide, to the autonomous vehicle, information instructing the autonomous vehicle to implement the decision,

the autonomous vehicle to implement the decision based on the information instructing the autonomous vehicle to implement the decision.

9. The device of claim 8, wherein the one or more processors are further to:

store information associated with the decision and historical decisions,

the historical decisions being previously determined by the device.

10. The device of claim 8, wherein the one or more processors are further to:

provide, for display, information associated with the decision and historical decisions,

the historical decisions being previously determined by the device.

11. The device of claim 8, wherein the one or more processors are further to:

determine whether a particular distance between the autonomous vehicle and one of the other vehicles satisfies a first threshold under normal road conditions;

or

determine whether the particular distance between the autonomous vehicle and the one of the other vehicles satisfies a second threshold under abnormal road conditions,

wherein the second threshold is greater than the first threshold.

12. The device of claim 8, wherein a particular relative orientation between the autonomous vehicle and one of the other vehicles includes one or more of:

behind the autonomous vehicle,

next to the autonomous vehicle,

forward of the autonomous vehicle,

left of the autonomous vehicle,

in front of the autonomous vehicle, or

right of the autonomous vehicle.

13. The device of claim 8, wherein the third qualitative model includes a qualitative rectilinear projection calculus (QRPC) model.

14. The device of claim 8, wherein the decision includes one of:

stay in a lane at a constant speed,

accelerate,

decelerate,

overtake on the left,

overtake on the right, or

stop.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

receive quantitative data from sensors associated with an autonomous vehicle traveling on a road with other vehicles;

process the quantitative data, with a first qualitative model, to determine distances between the autonomous vehicle and other vehicles;

process the quantitative data, with a second qualitative model, to determine relative orientations between the autonomous vehicle and the other vehicles;

process the distances and the relative orientations, with a third qualitative model, to determine relative trajectories between the autonomous vehicle and the other vehicles;

determine a reactive decision for the autonomous vehicle based on the distances, the relative orientations, and the relative trajectories,

the reactive decision to keep the autonomous vehicle safe;

determine a deliberative decision for the autonomous vehicle based on the distances, the relative orientations, and the relative trajectories,

the deliberative decision to cause the autonomous vehicle to choose a fastest lane to arrive at a destination; and

provide, to the autonomous vehicle, information instructing the autonomous vehicle to implement the reactive decision and the deliberative decision,

the autonomous vehicle to implement the reactive decision and the deliberative decision based on the information instructing the autonomous vehicle to implement the reactive decision and the deliberative decision.

16. The non-transitory computer-readable medium of claim 15, wherein the reactive decision includes one of:

stay in a lane at a constant speed,

accelerate,

decelerate,

overtake on the left,

overtake on the right, or

stop; and

wherein, when the road is a highway, the deliberative decision includes one of;

stay in a second to the left lane of the highway at about a speed limit or a speed of traffic flow, when traffic density of the highway is low,

utilize a high occupancy vehicle (HOV) lane, when the highway includes a HOV lane and the autonomous vehicle includes two or more passengers, or

move to a less-dense lane of the highway, that is closer to or faster than the speed limit or the speed of the traffic flow, when the traffic density is medium or high.

17. The non-transitory computer-readable medium of claim 15, wherein the reactive decision takes priority over the deliberative decision.

18. The non-transitory computer-readable medium of claim 15, wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

store information associated with the decision and historical decisions,

the historical decisions being previously determined.

19. The non-transitory computer-readable medium of claim 15, wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to;

provide, for display, information associated with the decision and historical decisions,

the historical decisions being previously determined.

20. The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the one or more processors to determine the relative trajectories between the autonomous vehicle and the other vehicles, cause the one or more processors to:

generate a conceptual neighborhood graph based on the third qualitative model;

identify a subset of the conceptual neighborhood graph that includes information indicating potential collisions between the autonomous vehicle and the other vehicles; and

determine the relative trajectories between the autonomous vehicle and the other vehicles based on the distances, the relative orientations, and the subset of the conceptual neighborhood graph.