# US 2019/0378039 A1 · Normalized performance comparison techniques

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

- Number: US 2019/0378039 A1
- Document ID: US20190378039A1
- Status: Published application
- Kind: A1
- Application number: 16/438,223
- Filed: 2019-06-11
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Traxen Inc.
- Applicants: Traxen Inc.
- Inventors: Saeed ZAMANZAD GAVIDEL; Gerti TUZI; Syed ALI; Ali MALEKI
- Web page: https://patentgrep.com/patent/US20190378039A1

## CPC

- B60W 30/143: {Speed control (B60W30/16 takes precedence)}
- G06N 20/00: Machine learning
- B60W 30/14: {Adaptive} cruise control
- B60W 30/18145: {Cornering}
- B60W 50/0097: {Predicting future conditions}
- G01S 13/931: of land vehicles
- G01S 17/931: of land vehicles
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- B60W 2050/0013: {Optimal controllers}
- B60W 2400/00: Indexing codes relating to detected, measured or calculated conditions or factors
- B60W 2420/403: Image sensing, e.g. optical camera
- B60W 2520/10: Longitudinal speed
- B60W 2520/105: Longitudinal acceleration
- B60W 2520/14: Yaw
- B60W 2520/28: Wheel speed
- B60W 2540/10: Accelerator pedal position
- B60W 2540/12: Brake pedal position
- B60W 2552/15: Road slope, i.e. the inclination of a road segment in the longitudinal direction
- B60W 2552/20: Road profile, i.e. the change in elevation or curvature of a plurality of continuous road segments
- B60W 2552/30: Road curve radius
- B60W 2552/53: Road markings, e.g. lane marker or crosswalk
- B60W 2554/80: Spatial relation or speed relative to objects
- B60W 2555/20: Ambient conditions, e.g. wind or rain
- B60W 2555/60: Traffic rules, e.g. speed limits or right of way
- B60W 2720/10: Longitudinal speed
- G01S 13/582: {adapted for simultaneous range and velocity measurements}
- G01S 13/584: {adapted for simultaneous range and velocity measurements}
- G01S 13/86: Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S 13/865: {Combination of radar systems with lidar systems}
- G01S 13/867: {Combination of radar systems with cameras}
- G01S 17/86: Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
- G01S 2013/932: {using own vehicle data, e.g. ground speed, steering wheel direction}
- G01S 2013/9321: {Velocity regulation, e.g. cruise control}
- G01S 2013/9322: {using additional data, e.g. driver condition, road state or weather data}
- G01S 2013/9323: {Alternative operation using light waves}
- G01S 2013/93271: {in the front of the vehicles}
- Y02T 10/40: Engine management systems
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION

## 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.

## Claims

### Claim 1

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.

### Claim 2 (depends on 1)

The system for normalized performance comparison of claim 1, further comprising:
the events reconstruction, optimization and ranking unit further configured to determine a worst/near worst driving scenario, and rank a driving scenarios with respect to the determined best/near best and worst/near worst driving scenarios.

### Claim 3 (depends on 1)

The system for normalized performance comparison of claim 1, further comprising:
a causation analytics unit configured to extract a plurality of driving rules based on the best/near best driving scenario.

### Claim 4 (depends on 3)

The system for normalized performance comparison of claim 3, further comprising:
the events reconstruction, optimization and ranking unit further configured to determine a worst/near worst driving scenario; and
the causation analytics unit configured to extract additional driving rules based on the worst/near worst driving scenario.

### Claim 5 (depends on 3)

The system for normalized performance comparison of claim 3, further comprising:
a training unit configured to determine one or more of the driving rules for a current driving scenario and output one or more throttle, brake, and gear indications to a driver based on the one or more driving rules in a coaching mode.

### Claim 6 (depends on 3)

The system for normalized performance comparison of claim 3, further comprising:
a training unit configured to determine one or more of the driving rules for a current driving scenario and to modify one or more of a driver throttle input, a driver brake input, a driver gear input and a driver steering based on the one or more driving rules in an assist mode.

### Claim 7 (depends on 1)

The system for normalized performance comparison of claim 1, further comprising:
a data logistic unit configured to receive data from one or more data sources;
a data ingestion unit configured to ingest the data received by the data logistic unit and prepare the data for further analysis;
a data management unit configured to store, manage, query, and retrieve the data from the data ingestion unit, a data extraction, transformation and loading unit, the Monte Carlo simulation unit and the events reconstruction, optimization and ranking, unit; and
the data extraction, transformation and loading unit configured to extract and mine the data from the data management unit and transform the data to a data structure and format appropriate for the predictive analytics unit.

### Claim 8 (depends on 7)

The system for normalized performance comparison of claim 7, further comprising:
a data governance unit for determining the data received from the one or more data sources conforms with one or more regulations before ingestion by the data ingestion unit.

### Claim 9 (depends on 8)

The system for normalized performance comparison of claim 8, wherein the data governance unit is configured to determine the data meets one or more of government regulations, industry regulation, and organization regulation.

### Claim 10 (depends on 7)

The system for normalized performance comparison of claim 7, wherein the data logistic unit is configured to:
cleanse the data;
unify the data from different runs (data sources);
convert the data to a structured type; and
compress the data.

### Claim 11 (depends on 7)

The system for normalized performance comparison of claim 7, wherein the data management unit is configured to receive queries and return file pointers to a file-residing directory.

### Claim 12 (depends on 6)

The system for normalized performance comparison of claim 6, wherein the predictive analytics unit is further configured to:
binarize and discretize continuous input data (continuous variable to discretized variable);
select a subset of significant features from a set of available features;
construct one or more predictive models; and
analyze the robustness of the plurality of predictive models for accuracy and variability.

### Claim 13 (depends on 12)

The system for normalized performance comparison of claim 12, wherein the significant features are selected utilizing one or mare feature selection algorithms, a dimensionality reduction algorithm, and a vote-counting algorithm.

### Claim 14 (depends on 6)

The system for normalized performance comparison of claim 6, wherein the Monte Carlo simulation unit is configured to assess a plurality of possible scenarios based on binarized and discretized input data.

### Claim 15 (depends on 6)

The system for normalized performance comparison of claim 6, wherein one or more of a number, a type, and a scope of input features to the Monte Carlo simulation unit are adjustable.

### Claim 16 (depends on 6)

The system for normalized performance comparison of claim 6, wherein the event reconstruction, optimization and ranking unit is configured to:
receive an observed scenario and associated observed efficiency;
determine a best or near best possible scenario and associated best or near best efficiency that could have happened for the observed scenario based on the Monte Carlo simulation results;
determine a worst or near worst possible scenario and associated worst or near 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.

### Claim 17 (depends on 16)

The system for normalized performance comparison of claim 16, wherein the normalized observed efficiency comprises a ranking.

### Claim 18

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.

### Claim 19 (depends on 18)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 18, wherein the one or more predictive models includes one or more models selected from a group comprising one or more parametric models and one or more non-parametric models.

### Claim 20 (depends on 18)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 18, further comprising:
selecting a set of significant features of the ground vehicle operation; and
construction the one or more predictive models based on the set of significant features.

### Claim 21 (depends on 18)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 18, further comprising:
segmenting the received observed scenario;
determining a best possible segmented scenario and associated best segmented efficiency that could have happened for each segment of the observed scenario based on the Monte Carlo simulation results;
determining a worst possible segmented scenario and associated worst segmented efficiency that could have happened for each segment of the observed scenario based on the Monte Carlo simulation results; and
normalize the observed efficiency as a function of the best segmented efficiency and the worst efficiency.

### Claim 22 (depends on 18)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 18, further comprising:
binarizing and discretizing continuous input data of the plurality of scenarios.

### Claim 23 (depends on 22)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 22, wherein the input data includes one or more of road data, environmental data, traffic, data, ground vehicle data and driver data.

### Claim 24 (depends on 23)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 23, further comprising:
determining that the input data conforms with one or more regulations before ingestion by the data ingestion unit.

### Claim 25 (depends on 18)

The method of comparing performance of one or more aspects of ground vehicle operation according to claim 18, wherein the efficiency comprises a ground vehicle energy efficiency.
