Manufacturer-based autonomous driving assessment

A method, comprising:

• receiving a request for an assessment for an autonomous driving system of an autonomous vehicle under a particular one or more conditions;
• predicting that the autonomous vehicle will experience the particular one or more conditions, by querying one or more databases with a location of the autonomous vehicle, the query returning the particular one or more conditions;
• in response to predicting that the autonomous vehicle will experience the particular one or more conditions based on the location of the autonomous vehicle, triggering the assessment for the autonomous driving system by the autonomous vehicle via one or more commands sent by a processor to the autonomous vehicle via a communication component, the communication component is coupled to the processor and the autonomous vehicle, and the processor is remote from the autonomous vehicle;
• causing one or more sensors employed on the autonomous vehicle to measure driving response data of the autonomous driving system during the assessment via the one or more commands sent by the processor to the autonomous vehicle via the communication component, the communication component is further coupled to the one or more sensors;
• in response to triggering the assessment for the autonomous driving system of the autonomous vehicle, receiving driving data associated with the autonomous driving system via a communication component, wherein the driving data comprises the driving response data measured by the one or more sensors during the assessment, and wherein the driving response data comprises at least one of:
• roll, pitch, and yaw values of the autonomous vehicle;
• control commands of the autonomous driving system;
• or
• driver intervention data pertaining to the autonomous driving system;
• analyzing the driving data comprising the driving response data using machine learning, wherein analyzing the driving data comprises a driving performance analysis for identifying attributes of the autonomous driving system based on the driving data, and wherein the attributes comprise at least one of:
• a subset of the roll, pitch, and yaw values of the autonomous vehicle based on the control commands of the autonomous driving system;
• frenetic control of the autonomous vehicle based on the control commands of the autonomous driving system;
• or
• an amount of manual override intervention by a driver based on the driver intervention data;
• determining characteristics of the autonomous driving system using the machine learning based on the identified attributes, wherein the characteristics of the autonomous driving system comprise a reliability of the autonomous driving system under the one or more conditions, and wherein the reliability of the autonomous driving system under the one or more conditions is determined by at least one of:
• comparing the subset of the roll, pitch, and yaw values of the autonomous vehicle to acceptability thresholds;
• evaluating an impact of the amount of manual override intervention by the driver based on driver characteristics of the driver;
• generating a risk profile, wherein the risk profile comprises the identified attributes and the determined characteristics;
• storing the risk profile in a database;
• and
• providing an electronic response to the request for the assessment of the autonomous driving system of the autonomous vehicle under the particular one or more conditions, the electronic response comprising an indication of the generated risk profile.

A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause one or more processors to perform operations comprising:

• receiving a request for an assessment for an autonomous driving system of an autonomous vehicle under a particular one or more conditions;
• predicting that the autonomous vehicle will experience the particular one or more conditions, by querying one or more databases with a location of the autonomous vehicle, the query returning the particular one or more conditions;
• in response to predicting that the autonomous vehicle will experience the particular one or more conditions based on the location of the autonomous vehicle, triggering the assessment for the autonomous driving system by the autonomous vehicle via one or more commands sent by a processor to the autonomous vehicle via a communication component, the communication component is coupled to the processor and the autonomous vehicle, and the processor is remote from the autonomous vehicle;
• initiating one or more autonomous driving tests during the assessment;
• causing one or more sensors employed on the autonomous vehicle to measure driving response data of the autonomous driving system associated with the one or more autonomous driving tests via the one or more commands sent by the processor to the autonomous vehicle via the communication component, the communication component is further coupled to the one or more sensors;
• in response to triggering the assessment for the autonomous driving system of the autonomous vehicle, receiving driving data associated with the autonomous driving system via a communication component, wherein the driving data comprises the driving response data, and wherein the driving response data comprises at least one of:
• roll, pitch, and yaw values of the autonomous vehicle;
• control commands of the autonomous driving system;
• or
• driver intervention data pertaining to the autonomous driving system;
• analyzing the driving data comprising the driving response data using machine learning, wherein analyzing the driving data comprises a driving performance analysis for identifying attributes of the autonomous driving system based on the driving data, and wherein the attributes comprise at least one of:
• a subset of the roll, pitch, and yaw values of the autonomous vehicle based on the control commands of the autonomous driving system;
• frenetic control of the autonomous vehicle based on the control commands of the autonomous driving system;
• or
• an amount of manual override intervention by a driver based on the driver intervention data;
• determining characteristics of the autonomous driving system using the machine learning based on the identified attributes, wherein the characteristics of the autonomous driving system comprise a reliability of the autonomous driving system under the one or more conditions, and wherein the reliability of the autonomous driving system under the one or more conditions is determined by at least one of:
• comparing the subset of the roll, pitch, and yaw values of the autonomous vehicle to acceptability thresholds;
• evaluating an impact of the amount of manual override intervention by the driver based on driver characteristics of the driver;
• generating a risk profile, wherein the risk profile comprises the identified attributes and the determined characteristics;
• storing the risk profile in a database;
• providing an electronic response to the request for the assessment of the autonomous driving system of the autonomous vehicle under the particular one or more conditions, the electronic response comprising an indication of the generated risk profile;
• and
• generating a recommendation for one or more users based on the risk profile.