Methods and apparatus for using scene-based metrics to gate readiness of autonomous systems
AssigneeNuro, Inc.
InventorSreeja Nag
Life of this patent
Estimating the term…
Abstract
According to one aspect, a method is provided to determine whether an autonomous system is ready to be deployed or is otherwise ready for use, scene-based metrics, or metrics based on instances of scenarios. Scene-based metrics are mapped, or otherwise translated, to distance-based metrics such that substantially standard distance-based metrics may be used to gate the readiness of an autonomy system for deployment.
Claims20
A method comprising:
- obtaining, by a computing device, a test data set that includes a plurality of scenario categories for a vehicle to encounter along a test path and a scene failure rate of an autonomous driving system for each of the plurality of scenario categories;
- determining deployment scene-based metrics that include one or more of the plurality of scenario categories that are encountered by the vehicle in a deployment region;
- mapping the deployment scene-based metrics to the test data set to determine the scene failure rate for each of the one or more of the plurality of scenario categories;
- determining whether the autonomous driving system meets a minimum deployment standard in the deployment region using a distance-based metric, wherein the distance-based metric is obtained by mapping the deployment scene-based metrics and frequency of the one or more of the plurality of scenario categories in the deployment region;
- and
- deploying the vehicle that uses the autonomous driving system based on determining that the autonomous driving system meets the minimum deployment standard.
An apparatus comprising:
- a memory;
- a network interface configured to enable network communications;
- and
- a processor, wherein the processor is configured to perform operations comprising:
- obtaining a test data set that includes a plurality of scenario categories for a vehicle to encounter along a test path and a scene failure rate of an autonomous driving system for each of the plurality of scenario categories;
- determining deployment scene-based metrics that include one or more of the plurality of scenario categories that are encountered by the vehicle in a deployment region;
- mapping the deployment scene-based metrics to the test data set to determine the scene failure rate for each of the one or more of the plurality of scenario categories;
- determining whether the autonomous driving system meets a minimum deployment standard in the deployment region using a distance-based metric, wherein the distance-based metric is obtained by mapping the deployment scene-based metrics and a frequency of the one or more of the plurality of scenario categories in the deployment region;
- and
- control operations to deploy an autonomous vehicle that uses the autonomous driving system based on determining that the autonomous driving system meets the minimum deployment standard.
One or more non-transitory computer readable storage media encoded with instructions that, when executed by a processor, cause the processor to execute a method comprising:
- obtaining a test data set that includes a plurality of scenario categories for a vehicle to encounter along a test path and a scene failure rate of an autonomous driving system for each of the plurality of scenario categories;
- determining deployment scene-based metrics that include one or more of the plurality of scenario categories that are encountered by the vehicle in a deployment region;
- mapping the deployment scene-based metrics to the test data set to determine the scene failure rate for each of the one or more of the plurality of scenario categories;
- determining whether the autonomous driving system meets a minimum deployment standard in the deployment region using a distance-based metric, wherein the distance-based metric is obtained by mapping the deployment scene-based metrics and frequency of the one or more of the plurality of scenario categories in the deployment region;
- and
- deploying an autonomous vehicle that uses the autonomous driving system based on determining that the autonomous driving system meets the minimum deployment standard.
Dependencies are inferred from the claim text.