Identifying a route for an autonomous vehicle between an origin and destination location
Described herein are technologies relating to computing a likelihood of an operation-influencing event with respect to an autonomous vehicle at a geographic location. The likelihood of the operation-influencing event is computed based upon a prediction of a value that indicates whether, through a causal process, the operation-influencing event is expected to occur. The causal process is identified by means of a model, which relates spatiotemporal factors and the operation-influencing events.
1. An autonomous vehicle comprising:
a propulsion system; and
a computing system that is programmed to perform acts comprising:
receiving a request to navigate from an origin location of the autonomous vehicle to a destination location;
responsive to receiving the request, providing a value for a spatiotemporal factor to a mixed effects computer-implemented model, wherein the mixed effects computer-implemented model models the spatiotemporal factor as a random effect, and further wherein the value for the spatiotemporal factor is for a first intersection in a first potential route between the origin location and the destination location;
predicting a second value for the spatiotemporal factor for a second intersection in a second potential route between the origin location and the destination location, wherein the second value is computed based upon the value for the spatiotemporal factor at the first intersection, and further wherein kriging is employed to predict the second value;
receiving, from the mixed effects computer-implemented model, a first likelihood of occurrence of the operation-influencing event and a second likelihood of occurrence of the operation-influencing event, wherein the first likelihood of occurrence of the operation influencing event is for the first intersection and is based upon the value for the spatiotemporal factor at the first intersection, wherein the second likelihood of occurrence of the operation-influencing event is for the second intersection, and further wherein the second likelihood is computed based upon the second value for the spatiotemporal factor at the second intersection;
identifying a route between the origin location and the destination location based upon the first likelihood and the second likelihood; and
controlling the propulsion system based upon the identified route, wherein the autonomous vehicle travels from the origin location to the destination location along the identified route.
2. The autonomous vehicle of claim 1 , wherein the mixed effects model models a second spatiotemporal factor as a fixed effect.
3. The autonomous vehicle of claim 1 , wherein the second value is predicted based upon a distance between the first intersection and the second intersection.
4. The autonomous vehicle of claim 3 , wherein the distance is a Euclidean distance between the first intersection and the second intersection.
5. The autonomous vehicle of claim 3 , wherein the distance is a shortest distance along roadways between the first intersection and the second intersection.
6. The autonomous vehicle of claim 1 , wherein the value for the spatiotemporal factor is an estimated number of pedestrians at the intersection at a current point in time.
7. The autonomous vehicle of claim 1 , wherein the second value for the spatiotemporal factor for the second intersection is a probability that a human driver will take control of the autonomous vehicle when the autonomous vehicle is at the second intersection.
8. A method performed by a computing system of an autonomous vehicle, the method comprising:
receiving a request to navigate from an origin location of the autonomous vehicle to a destination location;
responsive to receiving the request, providing a value for a spatiotemporal factor to a mixed effects computer-implemented model, wherein the mixed effects computer-implemented model models the spatiotemporal factor as a random effect, and further wherein the value for the spatiotemporal factor is for a first intersection in a first potential route between the origin location and the destination location;
predicting a second value for the spatiotemporal factor for a second intersection in a second potential route between the origin location and the destination location, wherein the second value is computed based upon the value for the spatiotemporal factor at the first intersection, and further wherein kriging is employed to predict the second value;
receiving, from the mixed effects computer-implemented model, a first likelihood of occurrence of the operation-influencing event and a second likelihood of occurrence of the operation-influencing event, wherein the first likelihood of occurrence of the operation influencing event is for the first intersection and is based upon the value for the spatiotemporal factor at the first intersection, wherein the second likelihood of occurrence of the operation-influencing event is for the second intersection, and further wherein the second likelihood is computed based upon the second value for the spatiotemporal factor at the second intersection;
identifying a route between the origin location and the destination location based upon the first likelihood and the second likelihood; and
controlling a propulsion system of the autonomous vehicle based upon the identified route, wherein the autonomous vehicle travels from the origin location to the destination location along the identified route.
9. The method of claim 8 , wherein the mixed effects model models a second spatiotemporal factor as a fixed effect.
10. The method of claim 8 , wherein the second value is predicted based upon a distance between the first intersection and the second intersection.
11. The method of claim 10 , wherein the distance is a Euclidean distance between the first intersection and the second intersection.
12. The method of claim 10 , wherein the distance is a shortest distance along roadways between the first intersection and the second intersection.
13. The method of claim 8 , wherein the value for the spatiotemporal factor is an estimated number of bicyclists at the intersection at a current point in time.
14. The method of claim 8 , wherein the second value for the spatiotemporal factor for the second intersection is a probability that a human driver will take control of the autonomous vehicle when the autonomous vehicle is at the second intersection.
15. A computer-readable storage medium of an autonomous vehicle, where the computer-readable storage medium comprises instructions that, when executed by a processor, cause the processor to perform acts comprising:
receiving a request to navigate from an origin location of the autonomous vehicle to a destination location;
responsive to receiving the request, providing a value for a spatiotemporal factor to a mixed effects computer-implemented model, wherein the mixed effects computer-implemented model models the spatiotemporal factor as a random effect, and further wherein the value for the spatiotemporal factor is for a first intersection in a first potential route between the origin location and the destination location;
predicting a second value for the spatiotemporal factor for a second intersection in a second potential route between the origin location and the destination location, wherein the second value is computed based upon the value for the spatiotemporal factor at the first intersection, and further wherein kriging is employed to predict the second value;
receiving, from the mixed effects computer-implemented model, a first likelihood of occurrence of the operation-influencing event and a second likelihood of occurrence of the operation-influencing event, wherein the first likelihood of occurrence of the operation influencing event is for the first intersection and is based upon the value for the spatiotemporal factor at the first intersection, wherein the second likelihood of occurrence of the operation-influencing event is for the second intersection, and further wherein the second likelihood is computed based upon the second value for the spatiotemporal factor at the second intersection;
identifying a route between the origin location and the destination location based upon the first likelihood and the second likelihood; and
controlling a propulsion system of the autonomous vehicle based upon the identified route, wherein the autonomous vehicle travels from the origin location to the destination location along the identified route.
16. The computer-readable storage medium of claim 15 , wherein the mixed effects model models a second spatiotemporal factor as a fixed effect.
17. The computer-readable storage medium of claim 15 , wherein the second value is predicted based upon a distance between the first intersection and the second intersection.
18. The computer-readable storage medium of claim 17 , wherein the distance is a Euclidean distance between the first intersection and the second intersection.
19. The computer-readable storage medium of claim 17 , wherein the distance is a shortest distance along roadways between the first intersection and the second intersection.
20. The computer-readable storage medium of claim 15 , wherein the value for the spatiotemporal factor is an estimated number of pedestrians at the intersection at a current point in time.