Automatic navigation based on traffic management vehicles and road signs

1 . A computer-implemented method comprising:

determining, by a computing system, that a first portion of a sign in an environment of a vehicle instructs movement of the vehicle that is inconsistent with a standard, wherein the standard is a navigation rule associated with at least one of vehicle safety, fuel economy, or comfortability;

determining, by the computing system, a second portion of the sign is unrecognized;

not performing, by the computing system, movement of the vehicle based on the second portion of the sign;

providing, by the computing system, a request to an operations center remote from the vehicle for authorization to perform the movement; and

causing, by the computing system, performance of the movement of the vehicle in response to receipt of authorization to perform the movement.

2 . The computer-implemented method of claim 1 , further comprising:

providing to the operations center sensor data associated with features of the second portion of the sign and scenario context data.

3 . The computer-implemented method of claim 1 , wherein the standard provides that a vehicle should not cross into a lane of oncoming traffic.

4 . The computer-implemented method of claim 1 , further comprising:

receiving from the operations center the authorization to perform the movement of the vehicle, wherein the authorization is based on an associated scenario context and environmental conditions.

5 . The computer-implemented method of claim 4 , further comprising:

determining that the second portion of the sign is recognized; and

updating a local map associated with the vehicle to reflect the second portion of the sign and features associated with the second portion of the sign.

6 . The computer-implemented method of claim 1 , further comprising:

obtaining sensor data associated with performance of the movement of the vehicle;

generating assessment data including safety data associated with the performance of the movement of the vehicle; and

providing the assessment data to the operations center to train a central machine learning model.

7 . The computer-implemented method of claim 6 , wherein the central machine learning model is configured to recognize variable signage and retrained based on the assessment data generated by the vehicle and other assessment data generated by other vehicles in a fleet.

8 . The computer-implemented method of claim 1 , wherein the determining that the second portion of the sign is unrecognized comprises:

extracting from the sign a first sign element that is recognized by a local machine learning model; and

extracting from the sign a second sign element that is unrecognized by the local machine learning model.

9 . A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:

determining that a first portion of a sign in an environment of a vehicle instructs movement of the vehicle that is inconsistent with a standard, wherein the standard is a navigation rule associated with at least one of vehicle safety, fuel economy, or comfortability;

determining a second portion of the sign is unrecognized;

not performing movement of the vehicle based on the second portion of the sign;

providing a request to an operations center remote from the vehicle for authorization to perform the movement; and

causing performance of the movement of the vehicle in response to receipt of authorization to perform the movement.

10 . The system of claim 9 , wherein the operations further comprise:

providing to the operations center sensor data associated with features of the second portion of the sign and scenario context data.

11 . The system of claim 9 , wherein the standard provides that a vehicle should not cross into a lane of oncoming traffic.

12 . The system of claim 9 , the operations further comprising:

receiving from the operations center the authorization to perform the movement of the vehicle, wherein the authorization is based on an associated scenario context and environmental conditions.

13 . The system of claim 9 , further comprising:

obtaining sensor data associated with performance of the movement of the vehicle;

generating assessment data including safety data associated with the performance of the movement of the vehicle; and

providing the assessment data to the operations center to train a central machine learning model.

14 . The system of claim 13 , wherein the central machine learning model is configured to recognize variable signage and retrained based on the assessment data generated by the vehicle and other assessment data generated by other vehicles in a fleet.

15 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations comprising:

determining that a first portion of a sign in an environment of a vehicle instructs movement of the vehicle that is inconsistent with a standard, wherein the standard is a navigation rule associated with at least one of vehicle safety, fuel economy, or comfortability;

determining a second portion of the sign is unrecognized;

not performing movement of the vehicle based on the second portion of the sign;

providing a request to an operations center remote from the vehicle for authorization to perform the movement; and

causing performance of the movement of the vehicle in response to receipt of authorization to perform the movement.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein the operations further comprise:

providing to the operations center sensor data associated with features of the second portion of the sign and scenario context data.

17 . The non-transitory computer-readable storage medium of claim 15 , wherein the standard provides that a vehicle should not cross into a lane of oncoming traffic.

18 . The non-transitory computer-readable storage medium of claim 15 , the operations further comprising:

receiving from the operations center the authorization to perform the movement of the vehicle, wherein the authorization is based on an associated scenario context and environmental conditions.

19 . The non-transitory computer-readable storage medium of claim 15 , further comprising:

obtaining sensor data associated with performance of the movement of the vehicle;

generating assessment data including safety data associated with the performance of the movement of the vehicle; and

providing the assessment data to the operations center to train a central machine learning model.

20 . The non-transitory computer-readable storage medium of claim 19 , wherein the central machine learning model is configured to recognize variable signage and retrained based on the assessment data generated by the vehicle and other assessment data generated by other vehicles in a fleet.