Data driven rule books
The current disclosure provides techniques for using human driving behavior to assist in decision making of an autonomous vehicle as the autonomous vehicle encounters various scenarios on the road. For each scenario, a model may be generated based on human driving behavior that governs how an autonomous vehicle maneuvers in that scenario. As a result of using these models, reliability and safety of autonomous vehicle may be improved. In addition, because the model is programmed into the autonomous vehicle, the autonomous vehicle, in many instances, need not consume resources to implement complex calculations to determine driving behavior in real-time.
1. A computer-implemented method comprising:
determining, by at least one processor, driving behavior of a plurality of manually-operated vehicles, each manually-operated vehicle having engaged in traffic merging behavior at a corresponding uncontrolled traffic intersection;
determining, by the at least one processor, an autonomous vehicle driving model comprising a neural network, wherein data associated with manually-operated vehicles is input to the neural network in order to train the neural network to implement an autonomous vehicle driving behavior of an autonomous vehicle driving to merge with traffic at an uncontrolled traffic intersection; and
controlling, by the at least one processor, at least one control function of the autonomous vehicle according to the autonomous vehicle driving model.
2. The method of claim 1 , wherein determining the driving behavior of the plurality of manually-operated vehicles comprises sensing the driving behavior at or near one or more uncontrolled traffic intersections.
3. The method of claim 1 , wherein determining the driving behavior comprises:
identifying a vehicle that merged into a corresponding uncontrolled traffic intersection; and
determining (1) respective speeds of the plurality of manually-operated vehicles driving towards the corresponding uncontrolled traffic intersection, (2) a distance of each other vehicle of the plurality of manually-operated vehicles from the vehicle that merged and (3) a lane of each of the plurality of manually-operated vehicles.
4. The method of claim 1 , wherein determining the driving behavior comprises:
identifying vehicles that did not merge into the corresponding uncontrolled traffic intersection; and
for each vehicle of the vehicles that did not merge into the corresponding uncontrolled traffic intersection, determining respective speeds of the plurality of manually-operated vehicles in a vicinity of the each vehicle that were driving towards the corresponding uncontrolled traffic intersection, a distance of each other vehicle of the plurality of manually-operated vehicles from each vehicle that did not merge and a lane of each other vehicle of the plurality of manually-operated vehicles.
5. The method of claim 1 , wherein determining the driving behavior of the plurality of manually-operated vehicles comprises:
collecting data;
identifying a data set from the collected data; and
fitting the data set to a baseline model.
6. The method of claim 1 , wherein the driving behavior includes a velocity and a heading of each manually-operated vehicle.
7. The method of claim 1 , wherein the autonomous vehicle driving model maps, for a particular vehicle that was driving towards the uncontrolled traffic intersection, a speed of the plurality of manually-operated vehicles driving towards the uncontrolled traffic intersection, a distance of each other vehicle from the particular vehicle and a lane of each other vehicle.
8. The method of claim 1 , wherein determining the driving behavior comprises determining whether the plurality of manually-operated vehicles attempted to merge with traffic at the uncontrolled traffic intersection or did not attempt to merge with traffic at the uncontrolled traffic intersection.
9. A system, comprising:
at least one processor, and
at least one non-transitory storage media storing instructions that, when executed by the at least one processor, cause the at least one processor to:
determine driving behavior of a plurality of manually-operated vehicles, each manually-operated vehicle having engaged in traffic merging behavior at a corresponding uncontrolled traffic intersection;
determine an autonomous vehicle driving model comprising a neural network, wherein data associated with manually-operated vehicles is input to the neural network in order to train the neural network to implement an autonomous vehicle driving behavior of an autonomous vehicle driving to merge with traffic at an uncontrolled traffic intersection; and
control at least one control function of the autonomous vehicle according to the autonomous vehicle driving model.
10. The system of claim 9 , wherein a tracking system at or near one or more uncontrolled traffic intersections senses the driving behavior of the plurality of manually-operated vehicles.
11. The system of claim 9 , wherein determining the driving behavior comprises:
identifying a vehicle that merged into a corresponding uncontrolled traffic intersection; and
determining (1) respective speeds of the plurality of manually-operated vehicles driving towards the corresponding uncontrolled traffic intersection, (2) a distance of each other vehicle of the plurality of manually-operated vehicles from the vehicle that merged and (3) a lane of each of the plurality of manually-operated vehicles.
12. The system of claim 9 , wherein determining the driving behavior comprises:
identifying vehicles that did not merge into the corresponding uncontrolled traffic intersection; and
for each vehicle of the vehicles that did not merge into the corresponding uncontrolled traffic intersection, determining respective speeds of the plurality of manually-operated vehicles in a vicinity of the each vehicle that were driving towards the corresponding uncontrolled traffic intersection, a distance of each other vehicle of the plurality of manually-operated vehicles from each vehicle that did not merge and a lane of each other vehicle of the plurality of manually-operated vehicles.
13. The system of claim 9 , wherein determining the driving behavior of the plurality of manually-operated vehicles comprises:
collecting data;
identifying a data set from the collected data; and
fitting the data set to a baseline model.
14. The system of claim 9 , wherein the driving behavior includes a velocity and a heading of each manually-operated vehicle.
15. The system of claim 9 , wherein the autonomous vehicle driving model maps, for a particular vehicle that was driving towards the uncontrolled traffic intersection, a speed of the plurality of manually-operated vehicles driving towards the uncontrolled traffic intersection, a distance of each other vehicle from the particular vehicle and a lane of each other vehicle.
16. The system of claim 9 , wherein determining the driving behavior comprises determining whether the manually-operated vehicle attempted to merge with traffic at the uncontrolled traffic intersection or did not attempt to merge with traffic at the uncontrolled traffic intersection.
17. A non-transitory storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to:
determine driving behavior of a plurality of manually-operated vehicles, each manually-operated vehicle having engaged in traffic merging behavior at a corresponding uncontrolled traffic intersection;
determine an autonomous vehicle driving model comprising a neural network, wherein data associated with manually-operated vehicles is input to the neural network in order to train the neural network to implement an autonomous vehicle driving behavior of an autonomous vehicle driving to merge with traffic at an uncontrolled traffic intersection; and
control at least one control function of the autonomous vehicle according to the autonomous vehicle driving model.
18. The non-transitory storage medium of claim 17 , wherein determining the driving behavior of the plurality of manually-operated vehicles comprises sensing the driving behavior at or near one or more uncontrolled traffic intersections.