# US 2020/0401743 A1 · Prediction, planning, and optimization of trip time, trip cost, and/or pollutant emission for a vehicle using machine learning

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

- Number: US 2020/0401743 A1
- Document ID: US20200401743A1
- Status: Published application
- Kind: A1
- Application number: 17/011,727
- Filed: 2020-09-03
- Published: 2020-12-24
- Earliest claimed: 2018-11-09
- Assignees: Iocurrents, Inc.
- Applicants: ioCurrents, Inc.
- Inventors: Bhaskar Bhattacharyya; Cosmo King; Samuel Friedman; Kiersten Henderson; Alexa Rust
- Web page: https://patentgrep.com/patent/US20200401743A1

## CPC

- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G01C 21/20: Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence)
- G01C 21/203: {specially adapted for water-borne vessels}
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06F 2111/10: Numerical modelling
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of predicting, in real-time, a relationship between a vehicle's engine speed, trip time, cost, and fuel consumption, comprising: monitoring vehicle operation over time to acquiring data representing at least a vehicle location, a fuel consumption rate, and operating conditions; generating a predictive model relating the vehicle's engine speed, trip time, and fuel consumption; and receiving at least one constraint on the vehicle's engine speed, trip time, and fuel consumption, and automatically producing from at least one automated processor, based on the predictive model, a constrained output.

## Claims

### Claim at position 1

1-30. (canceled)

### Claim 31

A method for controlling operation of a vehicle, comprising:
generating a predictive model relating at least the vehicle's engine speed, fuel consumption rate, and vehicle speed based, at least in part, on training data including values of the vehicle's fuel consumption rate and vehicle speed that are collected over an engine speed range of at least one engine of the vehicle;
obtaining at least one constraint on at least one of a trip time, trip fuel consumption, vehicle speed, fuel consumption rate, or pollutant emissions;
automatically producing, by at least one processor and based, at least in part, on the predictive model and the at least one constraint, an output constraint on vehicle operation; and
determining a failure of the predictive model.

### Claim 32 (depends on 31)

The method according to claim 31, further comprising outputting one or more instructions to control, at least partially, an engine of the vehicle according to the output constraint.

### Claim 33 (depends on 31)

The method according to claim 31, wherein the output constraint comprises a proposed engine speed.

### Claim 34 (depends on 31)

The method according to claim 31, further comprising regenerating the predictive model based, at least in part, on newly-acquired data.

### Claim 35 (depends on 34)

The method according to claim 34, wherein the training data is obtained prior to a trip and the newly-acquired data is obtained during the trip.

### Claim 36 (depends on 31)

The method according to claim 31, wherein the determining a failure of the predictive model is based, at least in part, on a standardized error threshold.

### Claim 37 (depends on 31)

The method according to claim 31, wherein the training data further includes vehicle operating condition information associated with the values of the vehicle's fuel consumption rate and vehicle speed.

### Claim 38 (depends on 31)

The method according to claim 31, wherein the predictive model is generated based further on at least one of wind speed or water current speed.

### Claim 39

A method for controlling operation of a vehicle, comprising:
generating one or more predictive models relating vehicle speed, at least one engine or vessel parameter that indicates or influences propulsion, and at least one of directly measured operating condition or indirectly measured operating condition based, at least in part, on (a) training data collected over an engine speed range of at least one engine of the vehicle and (b) at least one of a wind condition or water condition;
obtaining at least one constraint on at least one of a trip time, trip fuel consumption, vehicle speed, fuel consumption rate, pollutant emissions, or optimization of at least fuel cost and time cost; and
automatically producing, by at least one processor and based, at least in part, on the one or more predictive models and the at least one constraint, an output constraint for the vehicle.

### Claim 40 (depends on 39)

The method according to claim 39, further comprising filtering the training data for anomalies before the one or more predictive models are generated.

### Claim 41 (depends on 39)

The method according to claim 39, wherein the at least one engine or vessel parameter includes at least one of engine load, engine speed, fuel consumption rate, propeller pitch, trim, waterline, rudder angle, or rack position.

### Claim 42 (depends on 39)

The method according to claim 39, wherein the one or more predictive models include at least one of a generalized additive model, a neural network, or a support vector machine.

### Claim 43 (depends on 39)

The method according to claim 39, further comprising determining a failure of the one or more predictive models.

### Claim 44 (depends on 43)

The method according to claim 43, further comprising generating one or more updated predictive models in response to a determined failure of the one or more predictive models.

### Claim 45 (depends on 39)

The method according to claim 39, wherein the output constraint comprises at least one of an engine speed constraint, propeller pitch constraint, or combination of engine speed and propeller pitch.

### Claim 46

A computer-readable storage medium storing contents that, when executed by one or more processors, cause the one or more processors to perform actions comprising:
generating a predictive model relating at least a vehicle's engine speed, fuel consumption rate, and vehicle speed based, at least in part, on training data including values of the vehicle's fuel consumption rate and vehicle speed that are collected over an engine speed range of at least one engine of the vehicle;
obtaining at least one constraint on at least one of a trip time, trip fuel consumption, vehicle speed, fuel consumption rate, or pollutant emissions;
automatically producing an output constraint on vehicle operation based, at least in part, on the predictive model and the at least one constraint; and
determining a failure of the predictive model.

### Claim 47 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the actions further comprise outputting one or more instructions to control, at least partially, an engine of the vehicle according to the output constraint.

### Claim 48 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the output constraint comprises a proposed engine speed.

### Claim 49 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the actions further comprise regenerating the predictive model based, at least in part, on newly-acquired data.

### Claim 50 (depends on 49)

The computer-readable storage medium according to claim 49, wherein the training data is obtained prior to a trip and the newly-acquired data is obtained during the trip.

### Claim 51 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the determining a failure of the predictive model is based, at least in part, on a standardized error threshold.

### Claim 52 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the training data further includes vehicle operating condition information associated with the values of the vehicle's fuel consumption rate and vehicle speed.

### Claim 53 (depends on 46)

The computer-readable storage medium according to claim 46, wherein the predictive model is generated based further on at least one of wind speed or water current speed.

### Claim 54

A computer-readable storage medium storing contents that, when executed by one or more processors, cause the one or more processors to perform actions comprising:
generating one or more predictive models relating vehicle speed, at least one engine or vessel parameter that indicates or influences propulsion, and at least one of directly measured operating condition or indirectly measured operating condition based, at least in part, on (a) training data collected over an engine speed range of at least one engine of a vehicle and (b) at least one of a wind condition or water condition;
obtaining at least one constraint on at least one of a trip time, trip fuel consumption, vehicle speed, fuel consumption rate, pollutant emissions, or optimization of at least fuel cost and time cost; and
automatically producing an output constraint for the vehicle based, at least in part, on the one or more predictive models and the at least one constraint.

### Claim 55 (depends on 54)

The computer-readable storage medium according to claim 54, wherein the actions further comprise filtering the training data for anomalies before the one or more predictive models are generated.

### Claim 56 (depends on 54)

The computer-readable storage medium according to claim 54, wherein the at least one engine or vessel parameter includes at least one of engine load, engine speed, fuel consumption rate, propeller pitch, trim, waterline, rudder angle, or rack position.

### Claim 57 (depends on 54)

The computer-readable storage medium according to claim 54, wherein the one or more predictive models include at least one of a generalized additive model, a neural network, or a support vector machine.

### Claim 58 (depends on 54)

The computer-readable storage medium according to claim 54, wherein the actions further comprise determining a failure of the one or more predictive models.

### Claim 59 (depends on 58)

The computer-readable storage medium according to claim 58, wherein the actions further comprise generating one or more updated predictive models in response to a determined failure of the one or more predictive models.

### Claim 60 (depends on 54)

The computer-readable storage medium according to claim 54, wherein the output constraint comprises at least one of an engine speed constraint, propeller pitch constraint, or combination of engine speed and propeller pitch.