Patent Issued for Autonomous vehicle sensor malfunction detection (USPTO 11189112): State Farm Mutual Automobile Insurance Company

2021 DEC 20 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Christensen, Scott T. (Salem, OR, US), Farris, Scott (Bloomington, IL, US), Hayward, Gregory (Bloomington, IL, US), Konrardy, Blake (Bloomington, IL, US), filed on February 4, 2019, was published online on November 30, 2021.

The patent’s assignee for patent number 11189112 is State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Vehicles are typically operated by a human vehicle operator who controls both steering and motive controls. Operator error, inattention, inexperience, misuse, or distraction leads to many vehicle collisions each year, resulting in injury and damage. Autonomous or semi-autonomous vehicles augment vehicle operators’ information or replace vehicle operators’ control commands to operate the vehicle, in whole or part, with computer systems based upon information from sensors within, or attached to, the vehicle. Such vehicles may be operated with or without passengers, thus requiring different means of control than traditional vehicles. Such vehicles also may include a plurality of advanced sensors, capable of providing significantly more data (both in type and quantity) than is available even from GPS navigation assistance systems installed in traditional vehicles.

“Ensuring safe operation of such autonomous or semi-autonomous vehicles is of the utmost importance because the automated systems of these vehicles may not function properly in all environments. Although autonomous operation may be safer than manual operation under ordinary driving conditions, unusual or irregular environmental conditions may significantly impair the functioning of the autonomous operation features controlling the autonomous vehicle. Under some conditions, autonomous operation may become impractical or excessively dangerous. As an example, fog or heavy rain may greatly reduce the ability of autonomous operation features to safely control the vehicle. Additionally, damage or other impairment of sensors or other components of autonomous systems may significantly increase the risks associated with autonomous operation. Such conditions may change frequently, thereby changing the safety of autonomous vehicle operation. Similar risks associated with impaired sensors may also be present in a smart home environment.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “The present embodiments may be related to autonomous or semi-autonomous vehicle operation, including driverless operation of fully autonomous vehicles. The embodiments described herein relate particularly to various aspects of autonomous operation feature, component, and software monitoring and/or assessment. When malfunctions or other problems are detected, remedial responses may be determined and implemented. Alternatively, some aspects relate to assessment of features, components, or software, either generally or in particular situations. Specific systems and methods are summarized below. The methods and systems summarized below may include additional, less, or alternate actions, including those discussed elsewhere herein.

“In one aspect, a computer-implemented method for improving the functioning of a computer and/or detecting sensor malfunctions in an autonomous vehicle may be provided. The method may include, via one or more processors, transceivers, and/or sensors: (1) receiving sensor data including a plurality of signals from a plurality of sensors during operation of the autonomous vehicle; (2) selecting, by one or more processors, a first sensor from the plurality of sensors; (3) obtaining, by one or more processors, a first set of signals associated with the first sensor from the plurality of signals; (4) determining, by one or more processors, a first sensor range indicative of a range of signal values associated with proper functioning of the first sensor; (6) determining, by one or more processors, that the first sensor is malfunctioning when at least one signal in the first set of signals associated with the first sensors is outside the first sensor range and/or (7) performing, by one or more processors, an action in response to determining that the first sensor is malfunctioning. The method may include additional, less, or alternate actions, including those discussed elsewhere herein.

“For instance, in some embodiments, the first sensor range may be determined based upon a baseline plurality of signals received from the first sensor during a plurality of previous operation sessions of the autonomous vehicle. In additional embodiments, the first sensor range may be determined by predicting values of signals associated with the first sensor based upon a second set of signals from the plurality of signals, wherein the second set of signals is received from at least one second sensor of the plurality of sensors other than the first sensor during operation of the autonomous vehicle. In some such embodiments, the determination that the first sensor is malfunctioning may be based upon a determination of an inconsistency between the first set of signals and the second set of signals. The first set of signals may be considered outside the first sensor range when the first set of signals includes one or more indications that data from the first sensor is unavailable.

“In further embodiments, the first sensor may be selected in response to additional sensor data indicating a collision involving the autonomous vehicle, such as where the first sensor is disposed within an area of the autonomous vehicle involved in the collision. Alternatively, the first sensor may be determined to be malfunctioning without any indication of a vehicle collision. Determining the first sensor is malfunctioning may include determining a probability of malfunctioning based upon the sensor data, which probability of malfunctioning may indicate a probability of future failure of the first sensor based upon comparison with data from a plurality of other vehicles.

“In some embodiments, the method may further include determining, via the one or more processors, a cause of the first sensor’s malfunction based upon the received sensor data. The received sensor data used in such determination may include a plurality of signals at different times from each of the plurality of sensors, each signal being associated with a timestamp indicating a time associated with the signal. The method may further include determining, via the one or more processors, an apportionment of liability for a cost of repair or replacement of the first sensor based upon the received sensor data. The apportionment of liability may be made between one or more of: a manufacturer of the first sensor, a manufacturer of the autonomous vehicle, an installer of the first sensor, an insurer of the autonomous vehicle, an owner of the autonomous vehicle, or an owner, operator, or insurer of a second vehicle. The action performed by the method may further include automatically scheduling, via the one or more processors, repair or replacement of the first sensor by a third party based upon the determined apportionment of liability. In further embodiments, the method may include receiving additional information associated with a plurality of other vehicles regarding a plurality of sensor malfunctions and/or determining one or more repairs to correct the first sensor’s malfunctioning based upon the received sensor data and additional information.”

The claims supplied by the inventors are:

“1. A computer-implemented method for detecting sensor malfunctions in an autonomous vehicle, comprising: obtaining, by one or more processors installed on the autonomous vehicle, a first set of signals associated with a first sensor, the first sensor being among a plurality of sensors monitoring operation of the autonomous vehicle; obtaining, by the one or more processors, a second set of signals associated with a second sensor from the plurality of sensors, the second sensor disposed in a smart infrastructure component or a personal electronic device; based upon the second set of signals, predicting, by the one or more processors, a first sensor range indicative of a range of signal values associated with proper functioning of the first sensor; determining, by the one or more processors, that the first sensor is malfunctioning when at least one signal in the first set of signals associated with the first sensor is outside the predicted first sensor range; determining, by the one or more processors, a cause of the first sensor’s malfunction based upon received sensor data; based upon the received sensor data, determining, via the one or more processors, an apportionment of liability for a cost of repair or replacement of the first sensor between one or more of: a manufacturer of the first sensor, a manufacturer of the autonomous vehicle, an installer of the first sensor, an insurer of the autonomous vehicle, an owner of the autonomous vehicle, or an owner, operator, or insurer of a second vehicle; and performing, by the one or more processors, an action in response to determining that the first sensor is malfunctioning, wherein the action comprises: identifying, via the one or more processors, one or more autonomous operation features of the autonomous vehicle that utilize data from the first sensor to control the autonomous vehicle; and limiting, via the one or more processors, operation of at least one of the identified one or more autonomous operation features.

“2. The computer-implemented method of claim 1, wherein the first sensor range is determined based upon a baseline plurality of signals received from the first sensor during a plurality of previous operation sessions of the autonomous vehicle.

“3. The computer-implemented method of claim 1, wherein the first sensor range is determined by predicting values of signals associated with the first sensor based upon another set of signals from a plurality of signals, wherein the another set of signals is received from at least one other sensor of the plurality of sensors during operation of the autonomous vehicle.

“4. The computer-implemented method of claim 3, wherein the determination that the first sensor is malfunctioning is based upon a determination of an inconsistency between the first set of signals and the another set of signals.

“5. The computer-implemented method of claim 1, wherein the first sensor is selected in response to additional sensor data indicating a collision involving the autonomous vehicle, and the first sensor is disposed within an area of the autonomous vehicle involved in the collision.

“6. The computer-implemented method of claim 1, wherein the first sensor is determined to be malfunctioning without any indication of a vehicle collision.

“7. The computer-implemented method of claim 1, wherein the received sensor data includes a plurality of signals at different times from each of the plurality of sensors, each signal being associated with a timestamp indicating a time associated with the signal.

“8. The computer-implemented method of claim 1, wherein the performed action is automatically scheduling, via the one or more processors, repair or replacement of the first sensor by a third party based upon the determined apportionment of liability.

“9. The computer-implemented method of claim 1, further comprising: receiving additional information associated with a plurality of other vehicles regarding a plurality of sensor malfunctions; and determining, via the one or more processors, one or more repairs to correct the first sensor’s malfunctioning based upon the received sensor data and the additional information.

“10. The computer-implemented method of claim 1, wherein determining the first sensor is malfunctioning includes determining a probability of malfunctioning based upon the sensor data.

“11. The computer-implemented method of claim 10, wherein the probability of malfunctioning indicates a probability of future failure of the first sensor based upon comparison with data from a plurality of other vehicles.

“12. The computer-implemented method of claim 1, wherein performing the action further comprises: generating, via the one or more processors, an alert regarding the first sensor’s malfunctioning; and presenting the alert to one or more of the following: an operator of the autonomous vehicle or an owner of the autonomous vehicle.

“13. The computer-implemented method of claim 12, wherein the alert includes a recommendation to take one or more of the following actions: repair the first sensor, replace the first sensor, avoid using one or more autonomous operation features of the autonomous vehicle, or avoid using one or more settings associated with the one or more autonomous operation features.

“14. The computer-implemented method of claim 12, wherein the alert includes an indication of an adjustment to a cost or coverage associated with an insurance policy covering operation of the autonomous vehicle based upon at least one of the determination that the first sensor is malfunctioning or an increase in a risk based upon the first sensor’s malfunctioning.

“15. The computer-implemented method of claim 14, wherein the adjustment is contingent upon usage of one or more autonomous operation features of the autonomous vehicle that utilize data from the first sensor to control the autonomous vehicle.

“16. The computer-implemented method of claim 1, wherein performing the action further comprises: determining, via the one or more processors, a risk level for each of the identified autonomous operation features, wherein each risk level indicates a risk associated with operation of the autonomous operation feature when the first sensor is malfunctioning; and limiting, via the one or more processors, operation of the at least one of the identified one or more autonomous operation features based upon the associated risk level exceeding a safety threshold level.

“17. A computer system configured to detect sensor malfunctions in an autonomous vehicle, comprising: one or more processors; a communication module adapted to communicate with a plurality of sensors monitoring the autonomous vehicle; 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: obtain a first set of signals associated with a first sensor, the first sensor being among a plurality of sensors monitoring operation of the autonomous vehicle; obtain a second set of signals associated with a second sensor from the plurality of sensors, the second sensor disposed in a smart infrastructure component or a personal electronic device; based upon the second set of signals, predict a first sensor range indicative of a range of signal values associated with proper functioning of the first sensor; determine that the first sensor is malfunctioning when at least one signal in the first set of signals associated with the first sensors is outside the predicted first sensor range; determine a cause of the first sensor’s malfunction based upon received sensor data; based upon the received sensor data, determine an apportionment of liability for a cost of repair or replacement of the first sensor between one or more of: a manufacturer of the first sensor, a manufacturer of the autonomous vehicle, an installer of the first sensor, an insurer of the autonomous vehicle, an owner of the autonomous vehicle, or an owner, operator, or insurer of a second vehicle; identify one or more autonomous operation features of the autonomous vehicle that utilize data from the first sensor to control the autonomous vehicle; and limit operation of at least one of the identified one or more autonomous operation features.

“18. A non-transitory computer-readable storage medium storing processor-executable instructions, that when executed cause one or more processors to: obtain a first set of signals associated with a first sensor, the first sensor being among a plurality of sensors monitoring operation of an autonomous vehicle; obtain a second set of signals associated with a second sensor from the plurality of sensors, the second sensor disposed in a smart infrastructure component or a personal electronic device; based upon the second set of signals, predict a first sensor range indicative of a range of signal values associated with proper functioning of the first sensor; determine that the first sensor is malfunctioning when at least one signal in the first set of signals associated with the first sensors is outside the predicted first sensor range; determine a cause of the first sensor’s malfunction based upon received sensor data; based upon the received sensor data, determine an apportionment of liability for a cost of repair or replacement of the first sensor between one or more of: a manufacturer of the first sensor, a manufacturer of the autonomous vehicle, an installer of the first sensor, an insurer of the autonomous vehicle, an owner of the autonomous vehicle, or an owner, operator, or insurer of a second vehicle; identify one or more autonomous operation features of the autonomous vehicle that utilize data from the first sensor to control the autonomous vehicle; and limit operation of at least one of the identified one or more autonomous operation features.”

For additional information on this patent, see: Christensen, Scott T. Autonomous vehicle sensor malfunction detection. U.S. Patent Number 11189112, filed February 4, 2019, and published online on November 30, 2021. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=11189112.PN.&OS=PN/11189112RS=PN/11189112

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