Normalized performance comparison techniques
AssigneeTraxen Inc.
InventorsSaeed ZAMANZAD GAVIDEL, Gerti TUZI, Syed ALI, Ali MALEKI
Life of this patent
Estimating the term…
Abstract
A normalized driver performance comparison framework can include predicting a plurality of scenarios of a ground vehicle. A Monte Carlo simulation can be utilized to determine results using the predicted plurality of scenarios and one or more predictive models. Best and worst possible scenarios and associated efficiency for an observed scenario can be determined based on the Monte Carlo simulation results. The efficiency for the observed scenario can be normalized as a function of the best and worst efficiencies.
Claims25
A system for normalized performance comparison of aspects of performance of a ground vehicle driver comprising:
- a predictive analytics unit configured to predict a plurality of scenarios based on a constructed parametric model or a non-parametric model;
- a Monte Carlo simulation unit configured to perform statistical Monte Carlo simulations using the predicted plurality of scenarios and the one or more predictive models;
- and
- an events reconstruction, optimization, and ranking unit configured to reconstruct driving events, evaluate driving scenarios, and determine a best/near best driving scenario.
A method of comparing performance of one or more aspects of ground vehicle operation comprising:
- constructing one or more predictive models of the ground vehicle operation;
- predicting a plurality of scenarios of the ground vehicle operation;
- determining Monte Carlo simulation results using the predicted plurality of scenarios and the one or more predictive models;
- receiving an observed scenario and associated observed efficiency/score/parameter of the ground vehicle operation;
- determining a best possible scenario and associated best efficiency that could have happened for the observed scenario based on the Monte Carlo simulation results;
- determining a worst possible scenario and associated worst efficiency that could have happened for the observed scenario based on the Monte Carlo simulation results;
- and
- normalize the observed efficiency as a function of the best efficiency and the worst efficiency.
Dependencies are inferred from the claim text.