# US 11,906,315 B2 · Electric vehicle trip energy prediction based on baseline and dynamic driver models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,906,315 B2
- Document ID: US11906315B2
- Status: Granted
- Kind: B2
- Application number: 17/562,171
- Filed: 2021-12-27
- Published: 2023-06-29
- Granted: 2024-02-20
- Earliest claimed: 2021-12-27
- Assignees: GM Global Technology Operations LLC
- Applicants: GM Global Technology Operations LLC
- Inventors: Yue-Yun Wang; Dongxu Li; Brandon D. Mazzara; Jonathan Wilson; Chen-Fang Chang; Chunhao J. Lee
- Web page: https://patentgrep.com/patent/US11906315B2

## CPC

- B60L 58/14: Preventing excessive discharging
- G01C 21/3469: {Fuel consumption; Energy use; Emission aspects}
- B60L 58/16: responding to battery ageing, e.g. to the number of charging cycles or the state of health [SoH]
- B60W 40/00: Estimation or calculation of {non-directly measurable} driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, {e.g. by using mathematical models}
- B60L 2240/12: Speed
- B60L 2240/14: Acceleration
- B60L 2240/64: Road conditions
- B60L 2240/66: Ambient conditions
- B60L 2240/68: Traffic data
- B60L 2240/70: Interactions with external data bases, e.g. traffic centres
- B60L 2260/44: by parameter estimation
- B60L 2260/52: drive range estimation, e.g. of estimation of available travel distance
- B60L 2260/54: Energy consumption estimation
- B60L: PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES (arrangements or mounting of electrical propulsion units or of plural diverse prime-movers for mutual or common propulsion in vehicles B60K1/00, B60K6/20; arrangements or mounting of electrical gearing in vehicles B60K17/12, B60K17/14; preventing wheel slip by reducing power in rail vehicles B61C15/08; dynamo-electric machines H02K; control or regulation of electric motors H02P); SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES (electric coupling devices combined with mechanical couplings of vehicles B60D1/64; electric heating for vehicles B60H1/00); ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL (control or regulation of electric motors H02P); MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT

## Abstract

A trip energy estimation system includes a memory and a control module. The memory stores average traffic speed, average traffic acceleration, driver speed, and driver acceleration data. The control module executes an algorithm to estimate an amount of energy for an electric vehicle to travel between two locations. The algorithm includes: determining, based on the average traffic speed data and the average traffic acceleration data, a baseline amount of energy for the electric vehicle to travel between the two locations; determining, based on the driver speed data and the driver acceleration data, a dynamic amount of energy corresponding to at least one of stop and go events, over speeding, or under speeding; and determining a total amount of energy based on the baseline amount of energy and the dynamic amount of energy. The control module, based on the total amount of energy, performs an operation including indicating a trip estimate.

## Claims

### Claim 1

A trip energy estimation system comprising:
a memory configured to store average traffic speed data, average traffic acceleration data, driver speed data, and driver acceleration data, wherein the driver speed data and the driver acceleration data are historical data specific to a particular driver; and
a control module configured to execute an algorithm to estimate an amount of energy for an electric vehicle to travel from a first location to a second location, the algorithm comprising
determining, based on the average traffic speed data and the average traffic acceleration data, a baseline amount of energy for the electric vehicle to travel from the first location to the second location,
determining, based on the driver speed data and the driver acceleration data, a dynamic amount of energy based on (i) stop and go events, (ii) over speeding, and (iii) under speeding, wherein the dynamic amount of energy is based on historical over speeding and under speeding behavior of the particular driver as compared to average traffic speed and average traffic acceleration rates, and
determining a total amount of energy based on the baseline amount of energy and the dynamic amount of energy,
wherein the control module is configured
based on the total amount of energy, to perform operations including indicating a trip estimate, and
to perform the operations to minimize energy usage and extend at least one of drive time and distance traveled, the operations including i) limiting an acceleration rate of the electric vehicle, ii) selecting which electrical load requests to satisfy, and iii) enabling selected electronic devices of the electric vehicle corresponding to the selected electrical load requests to satisfy.

### Claim 2 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module is configured to determine the dynamic amount of energy for the stop and go events, over speeding and under speeding.

### Claim 3 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module, in determining the dynamic amount of energy for the stop and go events:
projects path information onto a plot of average traffic speed;
determines, based on the projection, how many stop and go events occur along a route from the first location to the second location;
sums up energy associated with decelerating and accelerating associated with each of the stop and go events to provide a sum; and
determines the dynamic amount of energy based on the sum.

### Claim 4 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module, in determining the dynamic amount of energy for at least one of the over speeding or the under speeding:
determines differences between the average traffic speed data and the driver speed data;
determines, based on the differences, percentage increases or percentage decreases in the dynamic amount of energy; and
determines the dynamic amount of energy based on the percentage increases or percentage decreases.

### Claim 5 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module, in determining the dynamic amount of energy:
projects path information onto a plot of average traffic speed;
determines, based on the projection, a number of stop and go events;
sums up the energy associated with decelerating and accelerating associated with each of the stop and go events to provide a sum;
determines differences between the average traffic speed data and the driver speed data;
determines, based on the differences, percentage increases or percentage decreases in a dynamic amount of energy; and
determines the dynamic amount of energy based on the sum and the percentage increases or percentage decreases.

### Claim 6 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module is configured to:
implement a statistical learning model of acceleration of the particular driver, wherein the particular driver is a system operator or another individual, and the statistical learning model of acceleration is specific to the particular driver for different routes traveled by the electric vehicle; and
determine the dynamic amount of energy based on the statistical learning model.

### Claim 7 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module is configured to:
perform a recursive algorithm to learn acceleration behavior of the particular driver, wherein the particular driver is a system operator or another individual, and the recursive algorithm to learn acceleration behavior of the particular driver includes determining acceleration behavior of the particular driver over time for different driving routes; and
determine the dynamic amount of energy based on the learned acceleration behavior of the particular driver.

### Claim 8 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module is configured to:
determine a categorical acceleration style of the particular driver, wherein the particular driver is a system operator or another individual; and
determine the dynamic amount of energy based on the categorical acceleration style of the particular driver.

### Claim 9 (depends on 1)

The trip energy estimation system of claim 1, wherein the control module is configured to:
determine an average acceleration of the particular driver;
compare the average acceleration of the particular driver to categorical acceleration values for different categorical acceleration styles to determine whether to perform interpolation;
in response to the average acceleration of the particular driver not matching one of the categorical acceleration values, perform interpolation to estimate stop and go energy levels or estimate the stop and go energy levels directly from a vehicle model; and
determine the dynamic amount of energy based on the estimated stop and go energy levels.

### Claim 10

A trip energy based estimation method comprising:
obtaining average traffic speed data, average traffic acceleration data, driver speed data, and driver acceleration data, wherein the driver speed data and the driver acceleration data are historical data specific to a particular driver;
executing an algorithm to estimate an amount of energy for an electric vehicle to travel from a first location to a second location, the algorithm comprising
determining, based on the average traffic speed data and the average traffic acceleration data, a baseline amount of energy for the electric vehicle to travel from the first location to the second location,
determining, based on the driver speed data and the driver acceleration data, a dynamic amount of energy based on (i) stop and go events, (ii) over speeding, and (iii) under speeding, wherein the dynamic amount of energy is based on historical over speeding and under speeding behavior of the particular driver as compared to average traffic speed and average traffic acceleration rates, and
determining a total amount of energy based on the baseline amount of energy and the dynamic amount of energy; and
based on the total amount of energy, performing operations including indicating a trip estimate,
wherein the operations are performed to minimize energy usage and extend at least one of drive time and distance traveled, and include i) limiting an acceleration rate of the electric vehicle, ii) selecting which electrical load requests to satisfy, and iii) enabling selected electronic devices of the electric vehicle corresponding to the selected electrical load requests to satisfy.

### Claim 11 (depends on 10)

The method of claim 10, further comprising determine the dynamic amount of energy for the stop and go events, over speeding and under speeding.

### Claim 12 (depends on 10)

The method of claim 10, wherein determining the dynamic amount of energy for the stop and go events comprises:
projecting path information onto a plot of average traffic speed;
determining, based on the projection, how many stop and go events occur along a route from the first location to the second location;
summing up energy associated with decelerating and accelerating associated with each of the stop and go events to provide a sum; and
determining the dynamic amount of energy based on the sum.

### Claim 13 (depends on 10)

The method of claim 10, wherein determining the dynamic amount of energy for at least one of the over speeding or the under speeding comprises:
determining differences between the average traffic speed data and the driver speed data;
determining, based on the differences, percentage increases or percentage decreases in the dynamic amount of energy; and
determining the dynamic amount of energy based on the percentage increases or percentage decreases.

### Claim 14 (depends on 10)

The method of claim 10, wherein determining the dynamic amount of energy comprises:
projecting path information onto a plot of average traffic speed;
determining, based on the projection, a number of stop and go events;
summing up the energy associated with decelerating and accelerating associated with each of the stop and go events to provide a sum;
determining differences between the average traffic speed data and the driver speed data;
determining, based on the differences, percentage increases or percentage decreases in the dynamic amount of energy; and
determining the dynamic amount of energy based on the sum and the percentage increases or percentage decreases.

### Claim 15 (depends on 10)

The method of claim 10, further comprising:
implementing a statistical learning model of acceleration of the particular driver, wherein the particular driver is a system operator or another individual, and the statistical learning model of acceleration is specific to the particular driver for different routes traveled by the electric vehicle; and
determining the dynamic amount of energy based on the statistical learning model.

### Claim 16 (depends on 10)

The method of claim 10, further comprising:
performing a recursive algorithm to learn acceleration behavior of the particular driver, wherein the particular driver is a system operator or another individual, and the recursive algorithm to learn acceleration behavior of the particular driver includes determining acceleration behavior of the particular driver over time for different driving routes; and
determining the dynamic amount of energy based on the learned acceleration behavior of the particular driver.

### Claim 17 (depends on 10)

The method of claim 10, further comprising:
determining a categorical acceleration style of the particular driver, wherein the particular driver is a system operator or another individual; and
determining the dynamic amount of energy based on the categorical acceleration style of the particular driver.

### Claim 18 (depends on 10)

The method of claim 10, further comprising:
determining an average acceleration of the particular driver;
comparing the average acceleration of the particular driver to categorical acceleration values for different categorical acceleration styles to determine whether to perform interpolation;
in response to the average acceleration of the particular driver not matching one of the categorical acceleration values, performing interpolation to estimate stop and go energy levels or estimate the stop and go energy levels directly from a vehicle model; and
determining the dynamic amount of energy based on the estimated stop and go energy levels.