Programmatic application of router flags for vehicle limitations

Patent metadata

Field	Value
Publication number	US-11429097-B2
Application number	US-201916557635-A
Country	US
Kind code	B2
Filing date	Aug 30, 2019
Priority date	Jun 28, 2019
Publication date	Aug 30, 2022
Grant date	Aug 30, 2022

Abstract

Systems and methods provide for routing autonomous vehicles by simulating an autonomous vehicle traversing a route on a map representing a physical area. A router flag can be generated at a specific location on the map. A router flag rule that defines a factor that caused a failure of the autonomous vehicle can then be created at the location, and the autonomous vehicle can be simulated traversing the to identify at least one other area on the map where the autonomous vehicle is likely to fail. An identifier can be applied to the other area on the map where the autonomous vehicle is likely to fail according to the router flag rule. The other area with the applied identifier can be omitted from a routable graph applied to the routing map, such that the route for the autonomous vehicle is generated in accordance with the routable graph.

First claim

What is claimed is:

1. A method for routing autonomous vehicles comprising:
receiving diagnostic data from a fleet of autonomous vehicles as the fleet of autonomous vehicles navigate in a physical area represented by a map;
modifying a model based on the diagnostic data to generate an updated model;
simulating, based on a set of rules comprising the updated model, one of the fleet of autonomous vehicles traversing at least one route on the map representing the physical area;
generating a router flag at a location on the map when a feature in the simulated route causes a failure of the one of the fleet of autonomous vehicles in the simulation;
creating a router flag rule that defines at least one factor that caused the failure of the one of the fleet of autonomous vehicles associated with the router flag at the location on the map;
simulating the one of the fleet of autonomous vehicles traversing the map based on the router flag rule to identify at least one other area on the map where the one of the fleet of autonomous vehicles is likely to fail;
applying an identifier to the at least one other area on the map where the one of the fleet of autonomous vehicles is likely to fail according to the router flag rule;
omitting the at least one other area with the applied identifier from a routable graph applied to the map;
generating the route for the one of the fleet of autonomous vehicles in accordance with the routable graph;
driving the one of the fleet of autonomous vehicles on the generated route;
confirming an inability of one or more autonomous vehicles within the fleet to operate along the route having the applied identifier; and
based on the inability, determining that the feature associated with the failure is a systemic issue to the one or more autonomous vehicles within the fleet.

2. The method of claim 1 , wherein the updated model is based on the diagnostics data received from a specific type of autonomous vehicle within the fleet of autonomous vehicles.

3. The method of claim 1 , further comprising applying the identifier each time the map is created based on a current model of the one of the fleet of autonomous vehicles.

4. The method of claim 1 , wherein the router flag rule includes one or more logical combinations associated with the failure of the one of the fleet of autonomous vehicles.

5. The method of claim 4 , wherein the applying the identifier to the map includes determining if the at least one other area on the map is associated with the one or more logical combinations.

6. The method of claim 1 , further comprising:
confirming that the failure applies across one or more autonomous vehicles of a same type within the fleet; and
omitting a portion of the route from the routable graph for each of the one or more autonomous vehicles of the same type, but not for autonomous vehicles of another type that is not prone to the failure.

7. A system comprising:
one or more processors; and
at least one non-transitory computer-readable medium containing instructions which, when executed by the one or more processors, cause the one or more processors to:
receive diagnostic data from a fleet of autonomous vehicles as the fleet of autonomous vehicles navigate in a physical area represented by a map;
modify a model based on the diagnostic data to generate an updated model;
simulate, based on a set of rules comprising the updated model, one of fleet of autonomous vehicles traversing at least one route on a map representing a physical area;
generate a router flag at a location on the map when a feature in the simulated route causes a failure of the one of fleet of autonomous vehicles in the simulation;
create a router flag rule that defines at least one factor that caused the failure of the one of fleet of autonomous vehicles at the location on the map;
simulate the one of fleet of autonomous vehicles traversing the map based on the router flag rule to identify at least one other area on the map where the one of fleet of autonomous vehicles is likely to fail;
apply an identifier to the at least one other area on the map where the one of fleet of autonomous vehicles is likely to fail according to the router flag rule;
omit the at least one other area with the applied identifier from a routable graph applied to the map;
generate the route for the autonomous vehicle in accordance with the routable graph;
instruct the one of fleet of autonomous vehicle to drive on the generated route;
confirm an inability of one or more autonomous vehicles within the fleet to operate along the route having the applied identifier; and
based on the inability, determine that the feature associated with the failure is a systemic issue to the one or more autonomous vehicles within the fleet.

8. The system of claim 7 , wherein the updated model is based on diagnostics data received from a specific type of autonomous vehicle within the fleet of autonomous vehicles.

9. The system of claim 7 , wherein the at least one non-transitory computer-readable medium contains instructions which, when executed by the one or more processors, cause the one or more processors to apply the identifier every time the map is created based on a current model of the one of fleet of autonomous vehicles.

10. The system of claim 7 , wherein the router flag rule includes one or more logical combinations associated with the failure of the one of fleet of autonomous vehicles.

11. The system of claim 10 , wherein applying the identifier to the map includes determining if the at least one other area on the map is associated with the one or more logical combinations.

12. The system of claim 7 , wherein the at least one non-transitory computer-readable medium contains instructions which, when executed by the one or more processors, cause the one or more processors to:
confirm that the failure applies across one or more autonomous vehicles of a same type within the fleet; and
omit a portion of the route from the routable graph for each of the one or more autonomous vehicles of the same type, but not for autonomous vehicles of another type that is not prone to the failure.

13. A non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:
receive diagnostic data from a fleet of autonomous vehicles as the fleet of autonomous vehicles navigate in a physical area represented by a map;
modify a model based on the diagnostic data to generate an updated model;
simulate one of fleet of autonomous vehicles traversing at least one route on a map representing a physical area based on a set of rules comprising the updated model;
generate a router flag at a location on the map when a feature in the simulated route causes a failure of the one of fleet of autonomous vehicles in the simulation;
create a router flag rule that defines at least one factor that caused the failure of the one of fleet of autonomous vehicles at the location on the map;
simulate the one of fleet of autonomous vehicles traversing the map based on the router flag rule to identify at least one other area on the map where the one of fleet of autonomous vehicles is likely to fail;
apply an identifier to the at least one other area on the map where the one of fleet of autonomous vehicles is likely to fail according to the router flag rule;
omit the at least one other area with the applied identifier from a routable graph applied to the map;
generate the route for the autonomous vehicle in accordance with the routable graph;
instruct the one of fleet of autonomous vehicle to drive on the generated route;
confirm an inabil

Assignees

• Gm Cruise Holdings Llc

Inventors

• Rusignola Michael
• Donohue Brian
• Rech Lucio
• Worlow Stephen
• Blick Daniel
• Bharadwaj Varun

Classifications

• G01C21/3807

  characterised by the type of data · CPC title

• G07C5/0816

  Indicating performance data, e.g. occurrence of a malfunction · CPC title

• G08G1/096844

  where the complete route is dynamically recomputed based on new data · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G06N20/00

  Machine learning · CPC title