Method and apparatus for fuel consumption prediction and cost estimation via crowd sensing in vehicle navigation system

Patent metadata

Field	Value
Publication number	US-9970780-B2
Application number	US-201615352011-A
Country	US
Kind code	B2
Filing date	Nov 15, 2016
Priority date	Nov 19, 2015
Publication date	May 15, 2018
Grant date	May 15, 2018

Abstract

A system and method for providing navigation routing options to a vehicle driver, including estimated fuel consumption and fuel cost. A server collects data from a large number of road vehicles driving different routes, where the data includes road grade, average speed, stop/start and acceleration/deceleration info and vehicle specifications, and the data is collected via a telematics or other wireless system. The server also receives map data, point of interest data and real-time traffic data from their respective providers. When a driver of a road vehicle requests navigation routing from a start point to a destination, the server provides multiple routing options including not only distance and time for each routing option, but also fuel consumption and cost. The estimated fuel consumption is computed using models based on the crowd-sensed data from the other vehicles driving the routes, where the models include a physics-based model and a machine learning model.

First claim

What is claimed is:

1. A method for providing estimated fuel consumption for a driving route in a vehicle navigation system, said method comprising:
providing vehicle operational data from a plurality of road vehicles to a server computer, where the vehicle operational data is collected by sensors on the road vehicles and provided wirelessly to the server computer, and the vehicle operational data includes data characterizing each of the road vehicles driving over one or more road segments including fuel consumption for each of the road vehicles for each of the road segments;
creating one or more fuel consumption models on the server computer, where the one or more fuel consumption models compute fuel consumption for each of the road vehicles for each of the road segments based on the vehicle operational data, properties of road segments, and behavior characteristics of drivers;
requesting navigation instructions from a start point to a destination by an occupant of a host vehicle using a navigation system in the host vehicle;
determining one or more driving routes from the start point to the destination;
computing an estimated fuel consumption and a fuel cost for the host vehicle to drive each of the one or more driving routes, using the one or more fuel consumption models; and
displaying the one or more driving routes, with the fuel consumption and the fuel cost for each of the one or more driving routes on the navigation system.

2. The method of claim 1 wherein the vehicle operational data includes vehicle and engine model, road grade, traffic flow speed, individual vehicle acceleration/braking patterns, individual vehicle deviation from average traffic speed, and idling caused by stop signs, traffic lights and congestion.

3. The method of claim 2 wherein the vehicle operational data also includes elevation and outside air temperature.

4. The method of claim 1 wherein the one or more fuel consumption models include a vehicle kinematic physics-based model which simulates vehicle forces and motions in order to compute fuel consumption for a road segment.

5. The method of claim 4 wherein the vehicle kinematic physics-based model includes, for each road segment, a vehicle dynamic profile which simulates vehicle motion as a function of time for the road segment, an engine speed profile computed based on the vehicle dynamic profile, and an engine torque profile computed based on the vehicle dynamic profile and forces affecting the vehicle, and estimates fuel consumption for the road segment by computing a time integral of the engine speed profile and the engine torque profile.

6. The method of claim 1 wherein the one or more fuel consumption models include a machine learning model which correlates the vehicle operational data to fuel consumption for each of the road segments.

7. The method of claim 6 wherein the machine learning model is a neural network model, and the neural network model includes a training mode in which it is calibrated using the vehicle operational data and the fuel consumption data from the plurality of road vehicles, and a testing mode in which it predicts fuel consumption for the host vehicle.

8. The method of claim 6 wherein the machine learning model is a statistical learning model, and the statistical learning model includes a training mode in which it is calibrated using the vehicle operational data and the fuel consumption data from the plurality of road vehicles, and a testing mode in which it predicts fuel consumption for the host vehicle.

9. The method of claim 1 wherein computing an estimated fuel consumption and a fuel cost is performed by the server computer, and the estimated fuel consumption and the fuel cost are downloaded to the navigation system in the host vehicle.

10. The method of claim 1 wherein computing an estimated fuel consumption and a fuel cost is performed by the navigation system in the host vehicle, using the one or more fuel consumption models downloaded from the server computer to the navigation system.

11. The method of claim 1 further comprising receiving map data, point of interest (POI) data and real-time traffic data from supplemental data providers, by the server computer, incorporating the map data and the real-time traffic data into the fuel consumption models, and incorporating the POI data into the driving route and fuel cost displayed on the navigation system.

12. The method of claim 11 further comprising providing updated data to the supplemental data providers by the server computer.

13. A method for providing estimated fuel consumption for a driving route in a vehicle navigation system, said method comprising:
providing vehicle operational data from a plurality of road vehicles to a server computer, where the vehicle operational data is collected by sensors on the road vehicles and provided wirelessly to the server computer, and the vehicle operational data includes data characterizing each of the road vehicles driving over one or more road segments including fuel consumption for each of the road vehicles for each of the road segments, where the vehicle operational data includes vehicle and engine model, road grade, traffic flow speed, individual vehicle acceleration/braking patterns, individual vehicle deviation from average traffic speed, idling caused by stop signs, traffic lights and congestion, elevation and outside air temperature;
receiving map data, point of interest (POI) data and real-time traffic data from supplemental data providers, by the server computer;
creating a plurality of fuel consumption models on the server computer, where the fuel consumption models compute fuel consumption for each of the road vehicles for each of the road segments based on the vehicle operational data, properties of road segments, behavior characteristics of drivers and the data from the supplemental data providers, and where the fuel consumption models include a vehicle kinematic physics-based model which simulates vehicle forces and motions in order to compute fuel consumption for a road segment and a machine learning model which correlates the vehicle operational data to fuel consumption for each of the road segments;
requesting navigation instructions from a start point to a destination by an occupant of a host vehicle using a navigation system in the host vehicle;
determining one or more driving routes from the start point to the destination;
computing an estimated fuel consumption and a fuel cost for the host vehicle to drive each of the one or more driving route using the plurality of fuel consumption models; and
displaying the one or more driving routes, with the fuel consumption, the fuel cost and POI data for each of the one or more driving routes on the navigation system.

14. A system for providing estimated fuel consumption for a driving route in a vehicle navigation system, said system comprising:
a server computer including a processor and a memory, said server computer being configured to receive operational data from a plurality of vehicles being driven over a plurality of road segments, and further configured to compute one or more fuel consumption models which calculate fuel consumption for each of the vehicles driving each of the road segments based on the operational data, properties of road segments, and behavior characteristics of drivers; and
a navigation system in a host vehicle, said navigation system being configured to wirelessly communicate with the server computer,
where an occupant of the host vehicle uses the navigation system to make a request for navigation instructions from a start point to a destination, one or more navigation routing

Assignees

• Gm Global Tech Operations Llc

Inventors

• Bai Fan
• Bojanowski David E
• Grimm Donald K
• Wagner Michael
• Tsimhoni Omer

Classifications

• G08G1/0141

  for traffic information dissemination · CPC title

• G08G1/09685

  where the complete route is computed only once and not updated · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G01C21/3697 Primary

  Output of additional, non-guidance related information, e.g. low fuel level (G01C21/3679 takes precedence) · CPC title

• G08G1/0129

  for creating historical data or processing based on historical data · CPC title