Fuel-economy optimization for autonomous driving systems

1. A method comprising:

determining, by a processing device associated with an autonomous vehicle (AV), that an estimated arrival time of the AV arriving at a destination via a route exceeds a threshold arrival time of the AV arriving at the destination via the route;

increasing, by the processing device based on a correlation metric associated with a correlation between a fuel economy and a speed, a fuel-efficient speed value of a corresponding segment of the route to provide a speed profile reflecting the increased fuel-efficient speed value of the corresponding segment of the route; and

causing, by the processing device, the AV to travel along the route based on the speed profile.

2. The method of claim 1 further comprising:

determining, based on fuel economy data associated with the AV, a corresponding fuel-efficient speed value for each of a plurality of segments of the route; and

calculating, based on route data for the route of the AV and the corresponding fuel-efficient speed value for each of the plurality of segments of the route, the estimated arrival time of the AV arriving at the destination.

3. The method of claim 2 further comprising determining, based on regulatory speed limits and traffic data, a corresponding minimum threshold speed value and a corresponding maximum threshold speed value for each of the plurality of segments of the route, wherein the corresponding fuel-efficient speed value for one or more of the plurality of segments is further based on at least one of the corresponding minimum threshold speed value or the corresponding maximum threshold speed value.

4. The method of claim 2 , wherein the fuel economy data comprises:

a first fuel economy value associated with driving based on a first speed value; and

a second fuel economy value associated with driving based on a second speed value, wherein the fuel economy is based on the first fuel economy value and the second fuel economy value, and wherein the speed is based on the first speed value and the second speed value.

5. The method of claim 4 , wherein the first fuel economy value is further based on one or more of a first grade value, a first total AV mass value, or a first wind value.

6. The method of claim 2 further comprising:

determining, based on first sensor data associated with the AV driving at a first speed value, a first fuel economy value;

and

responsive to the first fuel economy value not being within a threshold range of fuel economy values associated with a plurality of AVs driving at the first speed value, providing an alert.

7. The method of claim 1 further comprising:

identifying, among a plurality of segments of the route, at least a subset of segments that each represent a candidate for speed increase; and

computing, for each segment in the at least a subset and based on fuel economy data, a corresponding correlation metric that indicates the correlation between the fuel economy and the speed for a respective segment in the at least a subset.

8. The method of claim 7 further comprising:

determining, based on regulatory speed limits and traffic data, a plurality of minimum threshold speed values and a plurality of maximum threshold speed values for the route; and

dividing, based on the plurality of minimum threshold speed values and the plurality of maximum threshold speed values, the route into the plurality of segments, wherein each of the plurality of segments has a corresponding minimum threshold speed value and a corresponding maximum threshold speed value that are substantially constant.

9. The method of claim 7 further comprising determining, based on regulatory speed limits and traffic data, a maximum threshold speed value for each of the plurality of segments, wherein a corresponding fuel-efficient speed value of each of the at least a subset of segments is below a corresponding maximum threshold speed value.

10. The method of claim 7 , wherein the corresponding segment from the at least a subset has the respective correlation metric that indicates least decrease in fuel economy compared to increase in speed.

11. The method of claim 1 further comprising:

determining, based on the speed profile, that a difference between a first fuel-efficient speed value of a first segment of the route and a second fuel-efficient speed value of a subsequent segment of the route exceeds a threshold speed difference value; and

adjusting the speed between the first segment and the subsequent segment in the speed profile to meet the threshold speed difference value.

12. A system comprising:

a memory device; and

a processing device, coupled to the memory device, wherein the processing device is to:

determine that an estimated arrival time of an autonomous vehicle (AV) arriving at a destination via a route exceeds a threshold arrival time of the AV arriving at the destination via the route;

increase, based on a correlation metric associated with a correlation between a fuel economy and a speed, a fuel-efficient speed value of a corresponding segment of the route to provide a speed profile reflecting the increased fuel-efficient speed value of the corresponding segment of the route; and

cause the AV is to travel along the route based on the speed profile.

13. The system of claim 12 , wherein the processing device is further to:

determine, based on fuel economy data associated with the AV, a corresponding fuel-efficient speed value for each of a plurality of segments of the route; and

calculate, based on route data for the route of the AV and the corresponding fuel-efficient speed value for each of the plurality of segments of the route, the estimated arrival time of the AV arriving at the destination.

14. The system of claim 12 , wherein the processing device is further to:

identify, among a plurality of segments of the route, at least a subset of segments that each represent a candidate for speed increase; and

compute, for each segment in the at least a subset and based on fuel economy data, a corresponding correlation metric that indicates the correlation between the fuel economy and the speed for a respective segment in the at least a subset.

15. The system of claim 14 , wherein the corresponding segment from the at least a subset has the respective correlation metric that indicates least decrease in fuel economy compared to increase in speed.

16. The system of claim 12 , wherein the processing device is further to:

determine, based on the speed profile, that a difference between a first fuel-efficient speed value of a first segment of the route and a second fuel-efficient speed value of a subsequent segment of the route exceeds a threshold speed difference value; and

adjust the speed between the first segment and the subsequent segment in the speed profile to meet the threshold speed difference value.

17. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processing device, cause the processing device to:

determine that an estimated arrival time of an autonomous vehicle (AV) arriving at a destination via a route exceeds a threshold arrival time of the AV arriving at the destination via the route;

increase, based on a correlation metric associated with a correlation between a fuel economy and a speed, a fuel-efficient speed value of a corresponding segment of the route to provide a speed profile reflecting the increased fuel-efficient speed value of the corresponding segment of the route; and

cause the AV is to travel along the route based on the speed profile.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the processing device is further to:

determine, based on fuel economy data associated with the AV, a corresponding fuel-efficient speed value for each of a plurality of segments of the route; and

calculate, based on route data for the route of the AV and the corresponding fuel-efficient speed value for each of the plurality of segments of the route, the estimated arrival time of the AV arriving at the destination.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the processing device is further to:

identify, among a plurality of segments of the route, at least a subset of segments that each represent a candidate for speed increase; and

compute, for each segment in the at least a subset and based on fuel economy data, a corresponding correlation metric that indicates the correlation between the fuel economy and the speed for a respective segment in the at least a subset.

20. The non-transitory computer-readable storage medium of claim 17 , wherein the processing device is further to:

determine, based on the speed profile, that a difference between a first fuel-efficient speed value of a first segment of the route and a second fuel-efficient speed value of a subsequent segment of the route exceeds a threshold speed difference value; and

adjust the speed between the first segment and the subsequent segment in the speed profile to meet the threshold speed difference value.