Method, device, equipment, and storage medium for determining sensor solution

1. A method for determining a sensor solution, applied to terminal equipment, comprising:

establishing a simulated unmanned vehicle and a simulation scene, wherein the simulation scene is used for the simulated unmanned vehicle to perform simulation driving;

determining a first sensor solution according to a initialization parameter, and determining, according to the first sensor solution, simulation data generated by the simulated unmanned vehicle during the simulation driving in the simulation scene; and

determining a first perception parameter of the first sensor solution according to the simulation data, and correcting the first sensor solution according to the first perception parameter to obtain a sensor solution applied to an unmanned vehicle for operation of the unmanned vehicle;

wherein the simulation scene comprises a static simulation scene and a dynamic simulation scene, and the dynamic simulation scene comprises at least one dynamic sub-simulation scene; and the determining, according to the first sensor solution, the simulation data generated by the simulated unmanned vehicle during the simulation driving in the simulation scene comprises:

determining, according to the first sensor solution, a first sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the static simulation scene;

the determining the first perception parameter of the first sensor solution according to the simulation data, and correcting the first sensor solution according to the first perception parameter to obtain the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle comprises:

determining the first perception parameter of the first sensor solution according to the first sub-simulation data, and correcting the first sensor solution according to the first perception parameter to obtain a second sensor solution;

determining, according to the second sensor solution, at least one second sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the at least one dynamic sub-simulation scene; and

determining a second perception parameter of the second sensor solution according to each second sub-simulation data of the at least one second sub-simulation data, correcting the second sensor solution according to the second perception parameter to obtain a third sensor solution, and using the third sensor solution as the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

2. The method according to claim 1 , wherein the determining, according to the first sensor solution, the simulation data generated the simulated unmanned vehicle during the simulation driving in the simulation scene comprises:

establishing a simulated sensor, and installing the simulated sensor in the simulation unmanned vehicle according to the first sensor solution; and

determining the simulation data generated by the simulated unmanned vehicle installed with the simulated sensor during the simulation driving in the simulation scene.

3. The method according to claim 1 , wherein the determining the first perception parameter of the first sensor solution according to the simulation data and correcting the first sensor solution according to the first perception parameter to obtain the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle comprises:

inputting the simulation data into a preset sensor perception algorithm to obtain the first perception parameter presented by the simulation data; and

correcting, according to the first perception parameter and preset sensor perception capability requirement, the first sensor solution to obtain the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

4. The method according to claim 1 , wherein the sensor comprises a lidar and a camera.

5. The method according to claim 1 , wherein the sensor solution comprises one or more of the following:

sensor model, number of sensors, and sensor installation location.

6. A device for determining a sensor solution, applied to terminal equipment, comprising:

at least one processor; and

a memory communicatively connected with the at least one processor; wherein,

the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to: establish a simulated unmanned vehicle and a simulation scene, wherein the simulation scene is used for the simulated unmanned vehicle to perform simulation driving;

determine a first sensor solution according to a initialization parameter, and determine, according to the first sensor solution, simulation data generated by the simulation unmanned vehicle during the simulation driving in the simulation scene; and

determine a first perception parameter of the first sensor solution according to the simulation data and correct the first sensor solution according to the first perception parameter to obtain a sensor solution applied to an unmanned vehicle for operation of the unmanned vehicle;

wherein the simulation scene comprises a static simulation scene and a dynamic simulation scene, and the dynamic simulation scene comprises at least one dynamic sub-simulation scene; and the instructions further cause the at least one processor to:

determine, according to the first sensor solution, first sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the static simulation scene;

determine the first perception parameter of the first sensor solution according to the first sub-simulation data, and correct the first sensor solution according to the first perception parameter to obtain a second sensor solution;

determine, according to the second sensor solution, at least one second sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the at least one dynamic sub-simulation scene; and

determine a second perception parameter of the second sensor solution according to each second sub-simulation data of the at least one second sub-simulation data, correct, according to the second perception parameter, the second sensor solution to obtain a third sensor solution, and use the third sensor solution as the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

7. The device according to claim 6 , wherein the instructions further cause the at least one processor to: establish a simulated sensor, and install the simulated sensor in the simulation unmanned vehicle according to the first sensor solution; and

determine the simulation data generated by the simulated unmanned vehicle installed with the simulated sensor during the simulation driving in the simulation scene.

8. The device according to claim 6 , wherein the instructions further cause the at least one processor to:

input the simulation data into a preset sensor perception algorithm to obtain a first perception parameter represented by the simulation data; and

correct, according to the first perception parameter and preset sensor perception capability requirement, the first sensor solution to obtain the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

9. The device according to claim 6 , wherein the sensor comprises a lidar and a camera.

10. The device according to claim 6 , wherein the sensor solution comprises one or more of the following:

sensor model, number of sensors, and sensor installation location.

11. A non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used for causing the computer to:

establish a simulated unmanned vehicle and a simulation scene, wherein the simulation scene is used for the simulated unmanned vehicle to perform simulation driving;

determine a first sensor solution according to a initialization parameter, and determine, according to the first sensor solution, simulation data generated by the simulation unmanned vehicle during the simulation driving in the simulation scene; and

determine a first perception parameter of the first sensor solution according to the simulation data and correct the first sensor solution according to the first perception parameter to obtain a sensor solution applied to an unmanned vehicle for operation of the unmanned vehicle;

wherein the simulation scene comprises a static simulation scene and a dynamic simulation scene, and the dynamic simulation scene comprises at least one dynamic sub-simulation scene; and the computer instructions are used for further causing the computer to:

determine, according to the first sensor solution, first sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the static simulation scene;

determine the first perception parameter of the first sensor solution according to the first sub-simulation data, and correct the first sensor solution according to the first perception parameter to obtain a second sensor solution;

determine, according to the second sensor solution, at least one second sub-simulation data generated by the simulated unmanned vehicle during the simulation driving in the at least one dynamic sub-simulation scene; and

determine a second perception parameter of the second sensor solution according to each second sub-simulation data of the at least one second sub-simulation data, correct, according to the second perception parameter, the second sensor solution to obtain a third sensor solution, and use the third sensor solution as the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

12. The non-transitory computer readable storage medium according to claim 11 , wherein the computer instructions are used for further causing the computer to:

establish a simulated sensor, and install the simulated sensor in the simulation unmanned vehicle according to the first sensor solution; and

determine the simulation data generated by the simulated unmanned vehicle installed with the simulated sensor during the simulation driving in the simulation scene.

13. The non-transitory computer readable storage medium according to claim 11 , wherein the computer instructions are used for further causing the computer to:

input the simulation data into a preset sensor perception algorithm to obtain a first perception parameter represented by the simulation data; and

correct, according to the first perception parameter and preset sensor perception capability requirement, the first sensor solution to obtain the sensor solution applied to the unmanned vehicle for the operation of the unmanned vehicle.

14. The non-transitory computer readable storage medium according to claim 11 , wherein the sensor comprises a lidar and a camera.