Determining car positions

1. A method for determining car positions, the method comprising:

receiving, at an edge device, position data from a mobile device associated with a legacy car, the position data comprising global position information for the legacy car;

receiving, at the edge device, sensor data from a sensor-rich car, the sensor data comprising position information, visual information, and distance information about one or more observed cars in the vicinity of the sensor-rich car;

determining, by the edge device, an updated position for the legacy car based on a combination of the position data from the mobile device and the sensor data from the sensor-rich car; and

providing, by the edge device, the updated position for the legacy car to one or more of the legacy car and the sensor-rich car.

2. The method of claim 1 , wherein determining the updated position for the legacy car comprises:

generating a visual fingerprint for one or more of the observed cars based on the sensor data; and

correlating visual fingerprints of the observed legacy cars with car information about the legacy car, wherein car information comprises one or more of car make, model, color, position, and year of manufacture.

3. The method of claim 2 , wherein determining the updated position of the legacy car includes:

determining, for one or more of the observed cars, a set of constraints; and

determining, for one or more of the observed cars, a respective position of the observed car based on the set of constraints.

4. The method of claim 3 , wherein determining the updated position of the legacy car includes:

determining the updated position of the legacy car by minimizing a sum of distances from the geometric median of the determined positions from each of the set of observed cars and the visual fingerprint of the legacy car.

5. The method of claim 3 , wherein at least one of the constraints in the set of constraints is based upon information about a road associated with the sensor-rich car.

6. The method of claim 3 , wherein at least one of the constraints in the set of constraints is based upon information about a distance and an angle of the sensor-rich car relative to a second sensor-rich car, wherein the second sensor-rich car is one of the observed cars, and

wherein the method further comprises:

determining, for the sensor-rich car, a next move of the sensor-rich car based on the set of constraints, the updated position of the legacy car, and the position of one or more of the observed cars; and

providing, to the sensor-rich car, an indication of the next move.

7. The method of claim 1 , further comprising:

receiving, responsive to providing the updated position of the legacy car, car dynamics information of the legacy car;

determining a new updated position based on the received information about the car dynamics of the legacy car; and

providing the new updated position.

8. A non-transitory machine-readable storage medium comprising instructions executable by a physical processor of a computing device for determining car positions, the machine-readable storage medium comprising:

instructions to receive position data from a mobile device associated with a legacy car, the position data comprising global position information for a legacy car;

instructions to receive sensor data from a sensor-rich car, the sensor data comprising position information, visual information, and distance information about one or more observed cars in the vicinity of the sensor-rich car;

instructions to correlate car information about legacy car with the sensor data;

instructions to determine an updated position for the legacy car based on the correlation; and

instructions to provide the updated position for the legacy car.

9. The non-transitory machine-readable storage medium of claim 8 ,

wherein the instructions to correlate car information about the legacy car comprise:

instructions to generate a visual fingerprint for one or more of the observed cars based on the sensor data; and

instructions to correlate a visual fingerprint of the legacy car with the visual fingerprints of the other observed cars.

10. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions to determine the updated position for the legacy car comprise:

instructions to determine, for each of the observed cars, a set of constraints; and

instructions to determine, for each of the observed cars, a respective position of the observed car based on the set of constraints.

11. The non-transitory machine-readable storage medium of claim 10 , wherein the instructions to determine the updated position for the legacy car comprise:

instructions to determine the updated position of the legacy car by minimizing a sum of distances from the geometric median of the determined positions from each of the set of observed cars and the visual fingerprint of the legacy car.

12. The non-transitory machine-readable storage medium of claim 10 ,

wherein the set of constraints include information about a road associated with the sensor-rich car.

13. The non-transitory machine-readable storage medium of claim 10 ,

wherein at least one of the constraints in the set of constraints is based upon information about a distance and an angle of the sensor-rich car relative to a second sensor-rich car, wherein the second sensor-rich car is one of the observed cars, and

wherein the instructions further comprise: instructions to determine, for the sensor-rich car, a next move of the sensor-rich car based on the set of constraints, the updated position of the legacy car, and the position of one or more of the observed cars; and

instructions to provide, to the sensor-rich car, an indication of the next move.

14. The non-transitory machine-readable storage medium of claim 8 , further comprising:

instructions to, responsive to providing the updated position of the legacy car, receive car dynamics information of the legacy car;

instructions to determine a new updated position based on the received information about the car dynamics of the legacy car; and

instructions to provide the new updated position.

15. A system for determining car positions, the system comprising:

a physical processor that implements machine readable instructions that cause the system to:

receive information from a mobile device associated with a legacy car, the information comprising position data of the legacy car and information about a make and model of the legacy car;

receive, from a sensor-rich car, a set of sensor data about a set of observed cars in the vicinity of the sensor-rich car, the set of sensor data comprising a set of position data for the set of observed cars, and a set of visual data of the set of observed cars, wherein the set of observed cars includes the legacy car and the sensor-rich car;

correlate information about the legacy car with the set of sensor data, the set of position data, and the set of visual data;

determine an updated position for the legacy car based on the correlation; and

provide, to the mobile device, the updated position for the legacy car.

16. The system of claim 15 , wherein the physical processor implements machine readable instructions to cause the system to:

determine a visual fingerprint of one or more observed cars of the set of observed cars based on the set of sensor data;

determine, for each of the set of sensor-rich cars and the legacy car, a set of constraints; and

instructions to determine, for each of the set of observed cars, a respective position of the observed car based on the set of constraints and a corresponding visual fingerprint.

17. The system of claim 16 , wherein the physical processor implements machine readable instructions to cause the system to determine the updated position for the legacy car by:

determining the updated position of the legacy car by minimizing a sum of distances from the geometric median of the determined positions from each of the set of observed cars and the visual fingerprint of the legacy car.

18. The system of claim 16 , wherein at least one of the constraints in the set of constraints is based upon information about a road associated with the sensor-rich car, and

wherein the physical processor implements machine readable instructions to cause the system to:

provide, to the sensor-rich car, the updated position of the legacy car, and information about a position of one or more observed cars of the set of observed cars.

19. The system of claim 16 , wherein at least one of the constraints in the set of constraints is based upon information about a distance and an angle of the sensor-rich cars relative to a second sensor-rich car of the set of observed cars, and

wherein the physical processor implements machine readable instructions to cause the system to:

determine, for the sensor-rich car, a next move of the sensor-rich car based on the set of constraints, the updated position of the legacy car, and the positions of the set of observed cars updated position of the legacy cars, and the position of one or more of the set of sensor-rich cars; and

provide, to the sensor-rich car, an indication of the next move.

20. The system of claim 15 , wherein the physical processor implements machine readable instructions to cause the system to:

responsive to providing the updated position of the legacy car, receive, from the mobile device, car dynamics information of the legacy car;

determine a new updated position based on the received information about the car dynamics of the legacy car; and

provide the new updated position to the mobile device.