VEHICLE SPEED PROFILE PREDICTION USING NEURAL NETWORKS

• US 20150344036A1
• Filed: 05/30/2014
• Published: 12/03/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company), Board of Regents of the University of Michigan (University of Michigan)
• Original Assignee: Board of Regents of the University of Michigan (University of Michigan)
• Inventors: KRISTINSSON, Johannes Geir, PHILLIPS, Anthony Mark, KUANG, Ming Lang, MCGEE, Ryan Abraham, WANG, Wenduo, PARK, Jungme, MURPHEY, Yi, FANG, Chen
• Granted Patent: US 9,663,111 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 10/06 including control of combustion engines
• CPC Class Codes: B60W 10/08 including control of electric propulsion units, e.g. motors or generators
• CPC Class Codes: B60W 20/12 using control strategies taking into account route information estimation or calculation of non-directly measurable driving parameters B60W40/00
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2720/103 Speed profile
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 40/06 Road conditions
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: Y02T 10/62 Hybrid vehicles

Abstract

A vehicle includes a powertrain having an electric machine and an engine. The vehicle also includes a controller programmed to operate the powertrain according to a predicted vehicle speed profile for a predetermined route segmented according to a group of driving zone types, wherein each driving zone type is associated with a different characteristic speed profile shape and vehicle location. The controller is further programmed to update the predicted speed profile for a those segments showing deviation in response to deviation between the predicted speed profile and a measured speed profile.

Claims

1. A vehicle comprising:

a powertrain including an electric machine and an engine; and

a controller programmed to for each of a plurality of segments defining a route (i) operate the powertrain according to a predicted vehicle speed profile for the segment associated with one of a group of driving zone types each defining a different characteristic speed profile and vehicle location, and (ii) in response to deviation between the predicted speed profile and a measured speed profile, update the predicted speed profile associated with the driving zone type.

2. The vehicle of claim 1 wherein the controller further comprises at least one neural network processor programmed to partition the route into segments according to driving zone type.

3. The vehicle of claim 1 wherein the controller further comprises at least one neural network processor programmed to generate the predicted vehicle speed profiles based on data corresponding to historical driving patterns.

4. The vehicle of claim 3 wherein the at least one neural network processor further comprises a plurality of neural network processors each programmed to generate one of the predicted speed profiles.

5. The vehicle of claim 1 wherein the group of driving zone types includes a free flow traffic area, a stop sign traffic area, a traffic light traffic area, a turn traffic area, a freeway entrance ramp area, a freeway exit ramp area, or an inter-freeway ramp area.

6. A method of operating a vehicle comprising:

classifying, based on historical driving data, each of a series of segments of a predetermined route into one of a group of driving zone types;

generating a predicted speed profile for each segment using a processor corresponding to a particular one of the driving zone types; and

updating the predicted speed profile for each segment having a deviation between a measured speed profile and the predicted speed profile.

7. The method of claim 6 wherein the generating is based on a unique set of input parameters corresponding to each driving zone type.

8. The method of claim 6 wherein the generating is based on historical driving data, geographical information, and traffic pattern data.

9. The method of claim 6 wherein the generating is based on dynamic traffic information received from an external source.

10. The method of claim 6 wherein the group of driving zone types includes a free flow traffic area, a stop sign traffic area, a traffic light traffic area, a turn traffic area, a freeway entrance ramp area, a freeway exit ramp area, or an inter-freeway ramp area.

11. A vehicle comprising:

a powertrain; and

a controller having a neural network assigned to a driving zone type and programmed to operate the powertrain along a route segment defined by the driving zone type according to a predicted speed profile associated with the driving zone type, and update the predicted speed profile for use in subsequent trips along the route segment based on a measured deviation from the predicted speed profile.

12. The vehicle of claim 11 wherein another neural network is programmed to classify each of a series of segments of a route into one of a plurality of driving zone types.

13. The vehicle of claim 12 wherein each of the series of segments of the route is classified based on a speed profile shape that is characteristic of a single driving zone type.

14. The vehicle of claim 12 wherein the plurality of driving zone types includes a free flow traffic area, a stop sign traffic area, a traffic light traffic area, a turn traffic area, a freeway entrance ramp area, a freeway exit ramp area, or an inter-freeway ramp area.

15. The vehicle of claim 11 wherein the neural network is programmed to generate the predicted speed profile based on data corresponding to historical driving patterns.

16. The vehicle of claim 11 wherein the powertrain includes an electric machine and an engine, each capable of selectively providing output torque to propel the vehicle.