Method and system for modeling autonomous vehicle behavior
The system and method make it feasible to develop an autonomous vehicle control system for complex vehicles, such as for cargo trucks and other large payload vehicles. The method and system commence by first obtaining 3-dimensional data for one or more sections of roadway. Once the 3-dimensional roadway data is obtained, that data is used to run computer simulations of a computer model of a specific vehicle being controlled by a generic vehicle control algorithm or system. The generic vehicle control algorithm is optimized by running the simulations utilizing the 3-dimensional roadway data until an acceptable performance result is achieved. Once an acceptable simulation is executed using the generic vehicle control algorithm, the control algorithm/system is used to run one or more real-world driving tests on the roadway for which the 3-dimensional data was obtained. Finally, the computer model for the vehicle is modified.
1. A method comprising:
generating map data for a roadway, the map data comprising three-dimensional information;
generating a computer model emulating a vehicle performance;
generating a control system configured to control a vehicle;
executing a simulated driving excursion on a computer utilizing the map data, the computer model, and the control system;
executing a driving test of an actual vehicle in response to the executing the simulated driving excursion; and
revising, in response to test results of the driving test being not acceptable, the computer model without revising the control system.
2. The method of claim 1 wherein the vehicle controlled by the control system is a passenger vehicle.
3. The method of claim 1 wherein the vehicle controlled by the control system is a large payload vehicle.
4. The method of claim 1 wherein the control system is configured to control a passenger vehicle or a large payload vehicle.
5. The method of claim 1 , wherein the control system comprises an initial control algorithm.
6. The method of claim 5 , wherein the initial control algorithm remains unchanged in response to the executing the simulated driving excursion.
7. The method of claim 1 , further comprising:
eliminating noise in the map data by smoothing raw data of the map data.
8. A system comprising:
a data processor; and
a memory storing a computer module, executable by the data processor to:
generate map data for a roadway, the map data comprising three-dimensional information;
generate a computer model emulating a vehicle performance;
generate a control system configured to control a vehicle;
execute a simulated driving excursion on a computer utilizing the map data, the computer model, and the control system;
execute a driving test of an actual vehicle in response to the simulated driving excursion being executed; and
revise, in response to test results of the driving test being not acceptable, the computer model without revising the control system.
9. The system of claim 8 , wherein the control system comprises an initial control algorithm.
10. The system of claim 9 , wherein the initial control algorithm remains unchanged in response to the simulated driving excursion being executed.
11. The system of claim 8 , wherein the control system is configured to control a passenger vehicle or a large payload vehicle.
12. The system of claim 8 , wherein the memory storing the computer module, is executable by the data processor further to:
eliminate noise in the map data by smoothing raw data of the map data.
13. The system of claim 8 , wherein the map data is a three-dimensional map (3-D map).
14. The system of claim 13 , wherein the three-dimensional information is in a space constructed by three relatively perpendicular axes.
15. The system of claim 8 , wherein the map data is collected by using a Global Positioning System (GPS) sensor or a Light Detection and Ranging (LiDAR) sensor.
16. The system of claim 8 , wherein the map data comprises roadway shape data, wherein the roadway shape data comprises at slopes, banks, apexes, or dips.
17. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to:
generate map data for a roadway, the map data comprising three-dimensional information;
generate a computer model emulating a vehicle performance;
generate a control system configured to control a vehicle;
execute a simulated driving excursion on a computer utilizing the map data, the computer model, and the control system;
execute a driving test of an actual vehicle in response to the executing the simulated driving excursion; and
revise, in response to test results of the driving test being not acceptable, the computer model without revising the control system.
18. The non-transitory machine-useable storage medium of claim 17 wherein the control system comprises a non-vehicle-specific control system.
19. The non-transitory machine-useable storage medium of claim 17 wherein the three-dimensional information comprises an elevation of the roadway.
20. The non-transitory machine-useable storage medium of claim 17 wherein the vehicle controlled by the control system is an autonomous semitrailer truck.