# US 2026/0219053 A1 · Machine learning based generation and use of synthetic drive cycles

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

- Number: US 2026/0219053 A1
- Document ID: US20260219053A1
- Status: Published application
- Kind: A1
- Application number: 19/573,474
- Filed: 2026-03-20
- Published: 2026-07-30
- Earliest claimed: 2024-01-31
- Assignees: Exergi Predictive LLC
- Applicants: Exergi Predictive LLC
- Inventors: Harish Panneer Selvam; Andrew Kotz; William Northrop
- Web page: https://patentgrep.com/patent/US20260219053A1

## CPC

- G01C 21/3446: {Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags or using precalculated routes}
- G01C 21/3484: {Personalized, e.g. from learned user behaviour or user-defined profiles}
- G01C 21/3469: {Fuel consumption; Energy use; Emission aspects}
- G01C 21/3667: {Display of a road map (G01C21/3614 takes precedence; guidance using 3D or perspective road maps G01C21/3635)}
- 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)

## Abstract

Techniques for using machine learning to generate and use synthetic drive cycles of mobile actors such as a moving person or a mobile machine, as well as technologies for using machine learning to generate and use synthetic duty cycles of mobile machines. Synthetic drive or duty cycle generation and use can be for a person or machine moving from one place to another regardless of the complexity of the corresponding route and the complexity of other variables involved. Mobile machines can include any type of mobile machine for any industrial or consumer use. Mobile machines can include watercraft, aircraft, terrestrial vehicles, automobiles, or robots, for example.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method, comprising:
recording, by a computing system, actual drive cycles, wherein each of the actual drive cycles comprises a series of data points representing the speed of a respective mobile machine versus time or distance while the respective mobile machine is moving through a respective area;
training, by the computing system, a route optimized drive cycle generator request (RODGR) model using the actual drive cycles;
using, by the computing system, a selected path as input for the trained RODGR model to generate a synthetic drive cycle; and
using the synthetic drive cycle to at least partially control a mobile machine according to data in the synthetic drive cycle.

### Claim 22 (depends on 21)

The method of claim 21, wherein the generation of the synthetic drive cycle comprises dividing a route in the selected path into segments.

### Claim 23 (depends on 22)

The method of claim 22, wherein the generation of the synthetic drive cycle comprises selecting a speed value for each segment of the segments.

### Claim 24 (depends on 22)

The method of claim 22, wherein the segmentation of the path is determined by stop-and-go points.

### Claim 25 (depends on 22)

The method of claim 22, wherein the segmentation of the path is determined by points where terrain changes.

### Claim 26 (depends on 21)

The method of claim 21, further comprising:
recording, by the computing system, route information corresponding to the actual drive cycles, wherein the route information comprises information on respective areas that respective mobile machines are moving through while the actual drive cycles are recorded; and
using, by the computing system, the selected path and the route information as inputs for the trained RODGR model to generate the synthetic drive cycle.

### Claim 27 (depends on 21)

The method of claim 21, wherein the respective areas are part of a given path, and wherein a set of parameters of the given path have been recorded from actual use of the given path.

### Claim 28 (depends on 21)

The method of claim 21, wherein the respective areas are part of a given path, and wherein a set of parameters of the given path are unknown and artificially generated using the trained RODGR model.

### Claim 29 (depends on 28)

The method of claim 28, wherein a second set of parameters of the given path have been recorded from actual use of the given path.

### Claim 30 (depends on 21)

The method of claim 21, wherein the actual drive cycles comprise drive cycles of different mobile machines.

### Claim 31 (depends on 21)

The method of claim 21, wherein the selected path is selected from a map displayed by a graphical user interface.

### Claim 32 (depends on 21)

The method of claim 21, further comprising using the synthetic drive cycle to generate a graphical user interface according to data in the synthetic drive cycle.

### Claim 33 (depends on 21)

The method of claim 21, further comprising driving mobile machines through at least part of the selected path during the recording of the actual drive cycles.

### Claim 34 (depends on 21)

The method of claim 21, wherein the mobile machines used in the method comprise terrestrial vehicles.

### Claim 35 (depends on 21)

The method of claim 21, wherein the mobile machines used in the method comprise automobiles.

### Claim 36 (depends on 21)

The method of claim 21, wherein the mobile machines used in the method comprise robots.

### Claim 37 (depends on 21)

The method of claim 21, further comprising using deep learning with the RODGR model to enhance the generation of the synthetic drive cycle.

### Claim 38

A method, comprising:
recording, by a computing system, actual drive cycles, wherein each of the actual drive cycles comprises a series of data points representing the speed of a respective mobile machine versus time or distance while the respective mobile machine is moving through a respective area;
training, by the computing system, a route optimized drive cycle generator request (RODGR) model using the actual drive cycles;
using, by the computing system, a selected path as input for the trained RODGR model to generate a synthetic drive cycle, wherein the generation of the synthetic drive cycle by the RODGR model comprises selecting a respective speed value for different parts of the selected path; and
using the synthetic drive cycle to at least partially control a mobile machine according to data in the synthetic drive cycle.

### Claim 39 (depends on 38)

The method of claim 38, wherein at least some of the different parts of the selected path have different terrain.

### Claim 40

A method, comprising:
recording, by a computing system, actual drive cycles, wherein each of the actual drive cycles comprises a series of data points representing the speed of a respective terrestrial mobile machine versus time or distance while the respective mobile machine is moving through a respective area;
training, by the computing system, a route optimized drive cycle generator request (RODGR) model using the actual drive cycles;
using, by the computing system, a selected path as input for the trained RODGR model to generate a synthetic drive cycle, wherein the generation of the synthetic drive cycle by the RODGR model comprises selecting a respective speed value for different parts of the selected path; and
using the synthetic drive cycle to at least partially control a terrestrial mobile machine according to data in the synthetic drive cycle.
