Back to results
US 12,607,468 B2Granted
Machine learning based generation and use of synthetic drive cycles
AssigneeExergi Predictive LLC
InventorsHarish Panneer Selvam, Andrew Kotz, William Northrop
Life of this patent
Estimating the term…
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.
Claims20
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 dividing a route in the selected path into segments where similar route information is expected,
- wherein the generation of the synthetic drive cycle by the RODGR model comprises selecting a speed value for each segment of the segments, and
- wherein the segmentation of the selected path is determined by stop-and-go points or points where terrain changes;
- and
- using the synthetic drive cycle to at least partially control a mobile machine according to data in the synthetic drive cycle.
5 more elements
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;
- recording, by the computing system, actual duty cycles of auxiliary units of mobile machines, wherein each of the actual duty cycles comprises a series of auxiliary data points representing auxiliary unit usage 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 and the actual duty cycles;
- and
- using, by the computing system, a selected path as an input for the trained RODGR model to generate a synthetic drive cycle and a synthetic duty cycle,
- wherein the generation of the synthetic drive cycle by the RODGR model comprises dividing a route in the selected path into segments where similar route information is expected,
- wherein the generation of the synthetic drive cycle by the RODGR model comprises selecting a speed value for each segment of the segments, and
- wherein the segmentation of the selected path is determined by stop-and-go points or points where terrain changes;
- and
- using the synthetic drive cycle to at least partially control a mobile machine according to data in the synthetic drive cycle.
7 more elements
A method, comprising:
- recording, by a computing system, actual human drive cycles, wherein each of the actual human drive cycles comprises a series of data points representing the speed of a respective person versus time or distance while the respective person is moving through a respective area;
- training, by the computing system, a route optimized drive cycle generator request (RODGR) model using the actual human drive cycles;
- and
- using, by the computing system, a selected path as input for the trained RODGR model to generate a synthetic human drive cycle,
- wherein the generation of the synthetic human drive cycle by the RODGR model comprises dividing a route in the selected path into continuous segments where similar route information is expected,
- wherein the generation of the synthetic human drive cycle by the RODGR model comprises selecting a speed value for each segment of the continuous segments, and
- wherein the segmentation of the selected path is determined by stop-and-go points or points where terrain changes;
- and
- using the synthetic human drive cycle to generate a graphical user interface according to data in the synthetic human drive cycle.
6 more elements
Dependencies are inferred from the claim text.