Operational testing of autonomous vehicles
Disclosed are devices, systems and methods for the operational testing on autonomous vehicles. One exemplary method includes configuring a primary vehicular model with an algorithm, calculating one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm, configuring the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories, generating an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation, and integrating the updated algorithm into an algorithmic unit of the autonomous vehicle.
1. A method for operational testing of an autonomous vehicle, comprising:
reading a record created from physical experiments with the autonomous vehicle;
configuring a primary vehicular model with an algorithm;
calculating one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm;
configuring the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories;
generating an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation; and
integrating the updated algorithm into an algorithmic unit of the autonomous vehicle,
wherein the simulation comprises a multi-threading function that is configured to independently simulate the primary vehicular model and the one or more secondary vehicular models, and
wherein the simulation further comprises at least one protocol buffer that is configured to pass and record messages between the primary vehicular model and the one or more secondary vehicular models.
2. The method of claim 1 , wherein the simulation is based on an entity-component-system (ECS) architecture.
3. The method of claim 2 , wherein the primary vehicular model comprises a perception component that is configured to interact with the one or more secondary vehicular models, wherein the secondary vehicular models comprise a context component that is configured to advance along the corresponding trajectory, and wherein the primary vehicular model and the one or more secondary vehicular models each comprise a moving state component that is configured to record a current state of a respective vehicular model.
4. The method of claim 1 , wherein at least one of the one or more secondary vehicular models do not react to a trajectory of the primary vehicular model.
5. The method of claim 4 , wherein the trajectory of the primary vehicular model and the one or more trajectories are based on Dubins paths.
6. The method of claim 1 , wherein at least one of the one or more secondary vehicular models comprises an artificial intelligence module and reacts to a trajectory of the primary vehicular model.
7. The method of claim 1 , wherein each of the one or more trajectories is based on at least one of a plurality of waypoints, a speed or a heading.
8. A device for operational testing of an autonomous vehicle, comprising:
a processor; and
a memory that comprises instructions stored thereupon, wherein the instructions when executed by the processor configure the processor to:
read a record created from physical experiments with the autonomous vehicle;
configure a primary vehicular model with an algorithm;
calculate one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm;
configure the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories;
generate an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation; and
integrate the updated algorithm into an algorithmic unit of the autonomous vehicle,
wherein the simulation comprises a multi-threading function that is configured to independently simulate the primary vehicular model and the one or more secondary vehicular models, and
wherein the simulation further comprises at least one protocol buffer that is configured to pass and record messages between the primary vehicular model and the one or more secondary vehicular models.
9. The device of claim 8 , wherein the simulation is based on an entity-component-system (ECS) architecture.
10. The device of claim 9 , wherein the primary vehicular model comprises a perception component that is configured to interact with the one or more secondary vehicular models, wherein the secondary vehicular models comprise a context component that is configured to advance along the corresponding trajectory, and wherein the primary vehicular model and the one or more secondary vehicular models each comprise a moving state component that is configured to record a current state of a respective vehicular model.
11. The device of claim 8 , wherein the simulation comprises a multi-threading function that is configured to independently simulate the primary vehicular model and the one or more secondary vehicular models, and wherein the simulation further comprises at least one protocol buffer that is configured to pass and record messages between the primary vehicular model and the one or more secondary vehicular models.
12. The device of claim 8 , wherein at least one of the one or more secondary vehicular models do not react to a trajectory of the primary vehicular model.
13. The device of claim 12 , wherein the trajectory of the primary vehicular model and the one or more trajectories are based on Dubins paths.
14. The device of claim 8 , wherein at least one of the one or more secondary vehicular models comprises an artificial intelligence module and reacts to a trajectory of the primary vehicular model.
15. The device of claim 8 , wherein each of the one or more trajectories is based on at least one of a plurality of waypoints, a speed or a heading.
16. A non-transitory computer-readable program storage medium having code stored thereon, the code, when executed by a processor, causing the processor to perform operational testing of an autonomous vehicle, the method comprising:
reading a record created from physical experiments with the autonomous vehicle;
configuring a primary vehicular model with an algorithm;
calculating one or more trajectories for each of one or more secondary vehicular models that exclude the algorithm;
configuring the one or more secondary vehicular models with a corresponding trajectory of the one or more trajectories;
generating an updated algorithm based on running a simulation of the primary vehicular model interacting with the one or more secondary vehicular models that conform to the corresponding trajectory in the simulation; and
integrating the updated algorithm into an algorithmic unit of the autonomous vehicle,
wherein the simulation comprises a multi-threading function that is configured to independently simulate the primary vehicular model and the one or more secondary vehicular models, and wherein the simulation further comprises at least one protocol buffer that is configured to pass and record messages between the primary vehicular model and the one or more secondary vehicular models.
17. The non-transitory computer-readable program storage medium of claim 16 , wherein the simulation is based on an entity-component-system (ECS) architecture.
18. The non-transitory computer-readable program storage medium of claim 17 , wherein the primary vehicular model comprises a perception component that is configured to interact with the one or more secondary vehicular models, wherein the secondary vehicular models comprise a context component that is configured to advance along the corresponding trajectory, and wherein the primary vehicular model and the one or more secondary vehicular models each comprise a moving state component that is configured to record a current state of a respective vehicular model.