Patent Issued for Autonomous vehicle operation feature monitoring and evaluation of effectiveness (USPTO 11669090): State Farm Mutual Automobile Insurance Company

2023 JUN 26 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Christensen, Scott T. (Salem, OR, US), Farris, Scott (Bloomington, IL, US), Hayward, Gregory (Bloomington, IL, US), Konrardy, Blake (San Francisco, CA, US), filed on January 16, 2020, was published online on June 6, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11669090 is assigned to State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Vehicle or automobile insurance exists to provide financial protection against physical damage and/or bodily injury resulting from traffic accidents and against liability that could arise therefrom. Typically, a customer purchases a vehicle insurance policy for a policy rate having a specified term. In exchange for payments from the insured customer, the insurer pays for damages to the insured which are caused by covered perils, acts, or events as specified by the language of the insurance policy. The payments from the insured are generally referred to as “premiums,” and typically are paid on behalf of the insured over time at periodic intervals. An insurance policy may remain “in-force” while premium payments are made during the term or length of coverage of the policy as indicated in the policy. An insurance policy may “lapse” (or have a status or state of “lapsed”), for example, when premium payments are not being paid or if the insured or the insurer cancels the policy.

“Premiums may be typically determined based upon a selected level of insurance coverage, location of vehicle operation, vehicle model, and characteristics or demographics of the vehicle operator. The characteristics of a vehicle operator that affect premiums may include age, years operating vehicles of the same class, prior incidents involving vehicle operation, and losses reported by the vehicle operator to the insurer or a previous insurer. Past and current premium determination methods do not, however, account for use of autonomous vehicle operating features. The present embodiments may, inter alia, alleviate this and/or other drawbacks associated with conventional techniques.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “The present embodiments may be related to autonomous or semi-autonomous vehicle functionality, including driverless operation, accident avoidance, or collision warning systems. These autonomous vehicle operation features may either assist the vehicle operator to more safely or efficiently operate a vehicle or may take full control of vehicle operation under some or all circumstances. The present embodiments may also facilitate risk assessment and premium determination for vehicle insurance policies covering vehicles with autonomous operation features.

“In accordance with the described embodiments, the disclosure herein generally addresses systems and methods for determining risk levels associated with one or more autonomous (and/or semi-autonomous) operation features for controlling a vehicle or assisting a vehicle operator in controlling the vehicle. A server or other computer system may present test input signals to the one or more autonomous operation features to test the response of the features in a virtual environment. This virtual testing may include presentation of fixed inputs or may include a simulation of a dynamic virtual environment in which a virtual vehicle is controlled by the one or more autonomous operation features. The one or more autonomous operation features generate output signals that may then be used to determine the effectiveness of the control decisions by predicting the responses of vehicles to the output signals. Risk levels associated with the effectiveness of the autonomous operation features may be used to determine a premium for an insurance policy associated with the vehicle, which may be determined by reference to a risk category.

“In one aspect, a computer system for testing the effectiveness of one or more autonomous operation features for controlling a virtual vehicle in a virtual test environment may be provided. The computer system may include one or more processors and a non-transitory program memory coupled to the one or more processors and storing executable instructions. The executable instruction may, when executed by the one or more processors, cause the computer system to receive a set of computer-readable instructions for implementing the one or more autonomous operation features, execute the one or more software routines, receive one or more test input signals that simulate the one or more signals from at least one sensor, generate one or more test output signals for the virtual vehicle in response to the received one or more test input signals, predict one or more responses of the virtual vehicle in the virtual test environment to the one or more test output signals, and/or determine a measure of the effectiveness of the one or more autonomous operation features based upon the one or more predicted responses of the virtual vehicle to the one or more test output signals. The set of computer-readable instructions may include one or more software routines configured to receive one or more input signals from at least one sensor and generate one or more output signals for controlling a vehicle. The system may include additional, fewer, or alternate actions, including those discussed elsewhere herein.

“In some systems, the one or more test input signals may be received from a database containing a plurality of test signals. Alternatively, the test input signals may be received by generating a simulation of the virtual vehicle in the virtual test environment, determining simulated sensor data associated with the virtual vehicle in the virtual test environment, and determining the one or more test input signals based upon the simulated sensor data.

“In further embodiments, the measure of the effectiveness of the one or more autonomous operation features may include one or more risk levels associated with autonomous operation of the virtual vehicle by the one or more autonomous operation features. Determining the measure of the effectiveness of the one or more autonomous operation features may also include determining the measure of the effectiveness of the one or more autonomous operation features in a plurality of virtual test environments. Each virtual test environment may be based upon observed data regarding actual environments recorded by sensors communicatively connected to a plurality of vehicles operating outside the virtual test environment.”

The claims supplied by the inventors are:

“1. A computer system for monitoring an autonomous vehicle having an autonomous system, comprising: one or more processors; and a non-transitory program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to: receive, via wireless communication or data transmission over one or more radio links, initial sensor data indicating the occurrence of a vehicle collision involving the autonomous vehicle; receive, via wireless communication or data transmission over the one or more radio links, additional sensor data from at least one vehicle-mounted sensor, autonomous system sensor, or mobile device sensor; process the additional sensor data using a trained machine learning program to determine one or more preferred control decisions the autonomous system should have made to control the autonomous vehicle immediately before or during the vehicle collision; receive control decision data indicating one or more actual control decisions the autonomous system made to control the autonomous vehicle immediately before or during the vehicle collision; determine a degree of similarity between the one or more preferred control decisions that should have been made by the autonomous system to control the autonomous vehicle and the one or more actual control decisions made by the autonomous system to control the autonomous vehicle; and assign a percentage of fault for the vehicle collision to the autonomous system based upon the determined degree of similarity between the one or more preferred control decisions and the one or more actual control decisions.

“2. The computer system of claim 1, wherein the one or more preferred control decisions and the one or more actual control decisions are virtually time-stamped for comparison of such controlled and actual control decisions based upon matching virtual time stamps.

“3. The computer system of claim 1, wherein the executable instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to capabilities of the autonomous systems.

“4. The computer system of claim 3, wherein the executable instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon (i) data related to individual driver driving behavior, or (ii) telematics data associated with the individual driver driving behavior.

“5. The computer system of claim 4, wherein the executable instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to a plurality of the following: environmental conditions, road conditions, construction conditions, and traffic conditions.

“6. The computer system of claim 5, wherein the executable instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to levels of pedestrian traffic.

“7. The computer system of claim 1, wherein the one or more actual control decisions include a control decision to change lanes or to turn the autonomous vehicle.

“8. The computer system of claim 1, wherein the one or more actual control decisions include (i) a control decision to accelerate or to decelerate, or (ii) an indication of a rate of acceleration or deceleration.

“9. The computer system of claim 1, wherein the additional sensor data indicates (i) one or more environmental conditions in which the vehicle collision occurred and (ii) an identification of a person positioned within the autonomous vehicle to operate the autonomous vehicle at the time of the vehicle collision.

“10. The computer system of claim 1, wherein the executable instructions further cause the computer system to adjust a risk level or model parameter associated with the autonomous vehicle or the autonomous system based upon the one or more actual control decisions made by the autonomous system.

“11. A tangible, non-transitory computer-readable medium storing executable instructions for monitoring an autonomous vehicle having an autonomous system that, when executed by at least one processor of a computer system, cause the computer system to: receive, via wireless communication or data transmission over one or more radio links, initial sensor data indicating the occurrence of a vehicle collision involving the autonomous vehicle; receive, via wireless communication or data transmission over the one or more radio links, additional sensor data from at least one vehicle-mounted sensor, autonomous system sensor, or mobile device sensor; process the additional sensor data using a trained machine learning program to determine one or more preferred control decisions the autonomous system should have made to control the autonomous vehicle immediately before or during the vehicle collision; receive control decision data indicating one or more actual control decisions the autonomous system made to control the autonomous vehicle immediately before or during the vehicle collision; determine a degree of similarity between the one or more preferred control decisions that should have been made by the autonomous system to control the autonomous vehicle and the one or more actual control decisions made by the autonomous system to control the autonomous vehicle; and assign a percentage of fault for the vehicle collision to the autonomous system based upon the determined degree of similarity between the one or more preferred control decisions and the one or more actual control decisions.

“12. The tangible, non-transitory computer-readable medium of claim 11, wherein the one or more preferred control decisions and the one or more actual control decisions are virtually time-stamped for comparison of such controlled and actual control decisions based upon matching virtual time stamps.

“13. The tangible, non-transitory computer-readable medium of claim 11, wherein the instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to capabilities of the autonomous systems.

“14. The tangible, non-transitory computer-readable medium of claim 11, wherein the instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon (i) data related to individual driver driving behavior, or (ii) telematics data associated with the individual driver driving behavior.

“15. The tangible, non-transitory computer-readable medium of claim 11, wherein the instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to a plurality of the following: environmental conditions, road conditions, construction conditions, and traffic conditions.

“16. The tangible, non-transitory computer-readable medium of claim 11, wherein the instructions further cause the computer system to: train the machine learning program to determine control decisions that should be preferably made by autonomous systems based upon data related to levels of pedestrian traffic.

“17. The tangible, non-transitory computer-readable medium of claim 11, wherein the one or more actual control decisions include a control decision to change lanes or to turn the autonomous vehicle.

“18. The tangible, non-transitory computer-readable medium of claim 11, wherein the one or more actual control decisions include a control decision to accelerate or to decelerate.

“19. The tangible, non-transitory computer-readable medium of claim 11, wherein the additional sensor data indicates (i) one or more environmental conditions in which the vehicle collision occurred and (ii) an identification of a person positioned within the autonomous vehicle to operate the autonomous vehicle at the time of the vehicle collision.

“20. A computer-implemented method of monitoring an autonomous vehicle having an autonomous system, the method comprising: receiving, via wireless communication or data transmission over one or more radio links, initial sensor data indicating the occurrence of a vehicle collision involving the autonomous vehicle; receiving, via wireless communication or data transmission over the one or more radio links, additional sensor data from at least one vehicle-mounted sensor, autonomous system sensor, or mobile device sensor; processing the additional sensor data using a trained machine learning program to determine one or more preferred control decisions the autonomous system should have made to control the autonomous vehicle immediately before or during the vehicle collision; receiving control decision data indicating one or more actual control decisions the autonomous system made to control the autonomous vehicle immediately before or during the vehicle collision; determining a degree of similarity between the one or more preferred control decisions that should have been made by the autonomous system to control the autonomous vehicle and the one or more actual control decisions made by the autonomous system to control the autonomous vehicle; and assigning a percentage of fault for the vehicle collision to the autonomous system based upon the determined degree of similarity between the one or more preferred control decisions and the one or more actual control decisions.”

URL and more information on this patent, see: Christensen, Scott T. Autonomous vehicle operation feature monitoring and evaluation of effectiveness. U.S. Patent Number 11669090, filed January 16, 2020, and published online on June 6, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11669090)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)