Search

CN-121995900-A - Simulation test method and related device

CN121995900ACN 121995900 ACN121995900 ACN 121995900ACN-121995900-A

Abstract

The application provides a simulation test method and a related device, and relates to the field of simulation tests. And executing positioning operation by using the simulation map to obtain initial positioning information, performing path planning operation to obtain initial navigation information, converting the initial navigation information and the initial positioning information into target navigation information and target positioning information, performing simulation operation on a driving scene of the simulation vehicle according to the initial positioning information, and controlling the simulation vehicle to run to a destination by using the target navigation information, the target positioning information and the driving scene by using a subsequent target NOA controller. And subsequently, the target NOA controller can be used for controlling the control information of the operation of the simulation vehicle and the operation information of the simulation vehicle to realize the test of the target NOA controller. In addition, the simulation map is obtained through scene generalization, can reflect various complex situations possibly encountered in the driving process, and further can be applied to complex and large-quantity urban scenes to realize simulation test of urban NOA.

Inventors

  • SUN YAPING

Assignees

  • 北京经纬恒润科技股份有限公司

Dates

Publication Date
20260508
Application Date
20260126

Claims (10)

  1. 1. A simulation test method, comprising: Generating a simulation map, wherein the simulation map is obtained through scene generalization operation; Responding to a navigation instruction of a destination, and executing positioning operation by using the simulation map to obtain initial positioning information of a simulation vehicle; performing path planning operation based on the simulation map, the initial positioning information and the destination to obtain initial navigation information of a simulation vehicle; converting the initial navigation information and the initial positioning information into target navigation information and target positioning information which can be identified by a target piloting automatic driving NOA controller, and sending the target navigation information and the target positioning information to the target NOA controller; According to the initial positioning information, performing simulation operation on the running scene of the simulated vehicle, outputting the running scene obtained by simulation to the target NOA controller, and enabling the target NOA controller to control the running of the simulated vehicle to the destination by using the target navigation information, the target positioning information and the running scene, wherein the target NOA controller controls the control information of the running of the simulated vehicle and the running information of the simulated vehicle to serve as reference data for testing the target NOA controller.
  2. 2. The simulation test method of claim 1, wherein the generating a simulation map comprises: Acquiring data acquired by various sensors; processing the acquired data according to a processing mode corresponding to the acquired data; when the data fusion operation is carried out, the point cloud data and semantic layers in the acquired picture information are overlapped under the same coordinate system, and a three-dimensional scene is reproduced by combining inertial navigation data, so that the map scene slice data are obtained; and performing scene generalization operation on the map scene slice data to obtain a simulation map.
  3. 3. The simulation test method according to claim 2, wherein performing scene generalization operation on the map scene slice data to obtain a simulation map comprises: Performing scene generalization operation on the map scene slice data by using a scene generalization algorithm to obtain a simulation map; The operation logic of the scene generalization algorithm is as follows: and generating a random scene by using the constraint condition, and constructing a simulation map by using the random scene.
  4. 4. The simulation test method according to claim 1, wherein performing a positioning operation using the simulation map to obtain initial positioning information of the simulated vehicle comprises: Acquiring an environment simulation image of a simulation vehicle; Performing feature extraction operation on the environment simulation image to obtain multi-scale features of the environment simulation image; determining a candidate region where the simulation vehicle is located from the simulation map by utilizing the multi-scale features; And performing classification and regression operation on the candidate areas to obtain initial positioning information of the simulation vehicle.
  5. 5. The simulation test method according to claim 1, wherein performing a path planning operation based on the simulation map, the initial positioning information, and the destination, obtaining initial navigation information of a simulated vehicle, comprises: Acquiring a road network of the simulation map; determining a coverage map including the initial positioning information and the destination from a road network using the vertex separator; dividing the vertex separator into small subsets of vertices to decompose the overlay into a plurality of balancing units; and performing path planning operation by using the plurality of balance units to obtain initial navigation information of the simulated vehicle, wherein the starting point of the initial navigation information is the initial positioning information and the end point of the initial navigation information is the destination.
  6. 6. The simulation test method according to claim 5, wherein performing a path planning operation using the plurality of balancing units to obtain initial navigation information of the simulated vehicle comprises: Determining a navigation route passing through at least one balance unit through path planning operation, wherein the starting point of the navigation route is the initial positioning information and the end point of the navigation route is the destination; and determining the driving route in the balance unit through which the navigation route passes to obtain the initial navigation information of the simulated vehicle.
  7. 7. The simulation test method according to claim 1, wherein converting the initial navigation information and the initial positioning information into target navigation information and target positioning information that can be recognized by a target NOA controller, comprises: acquiring a target data format used by a target NOA controller; And carrying out format conversion on the initial navigation information and the initial positioning information, and converting the initial navigation information and the initial positioning information into target navigation information and target positioning information which are in the format of the target data.
  8. 8. The simulation test method according to claim 1, wherein performing a simulation operation on a driving scene of the simulated vehicle according to the initial positioning information comprises: rendering environment information in a preset range of the simulation vehicle according to the initial positioning information and a map in the preset range of the initial positioning information; simulating operation information of the simulated vehicle and sensor scene information; And constructing a driving scene of the simulated vehicle according to the environment information, the running information and the sensor scene information.
  9. 9. A simulation test apparatus, comprising: The map generation module is used for generating a simulation map, wherein the simulation map is obtained through scene generalization operation; The positioning module is used for responding to the navigation instruction of the destination, and executing positioning operation by using the simulation map to obtain initial positioning information of the simulation vehicle; The navigation module is used for carrying out path planning operation based on the simulation map, the initial positioning information and the destination to obtain initial navigation information of the simulation vehicle; The conversion module is used for converting the initial navigation information and the initial positioning information into target navigation information and target positioning information which can be identified by the target NOA controller, and sending the target navigation information and the target positioning information to the target NOA controller; The test module is used for carrying out simulation operation on the driving scene of the simulation vehicle according to the initial positioning information, outputting the driving scene obtained by simulation to the target NOA controller, so that the target NOA controller controls the simulation vehicle to run to the destination by utilizing the target navigation information, the target positioning information and the driving scene, and the target NOA controller controls the control information of the simulation vehicle and the running information of the simulation vehicle to be used as reference data for testing the target NOA controller.
  10. 10. An electronic device comprising at least one processor and a memory coupled to the processor, wherein: the memory is used for storing a computer program; The processor is configured to execute the computer program to enable the electronic device to implement the simulation test method according to any one of claims 1 to 8.

Description

Simulation test method and related device Technical Field The application relates to the field of simulation test, in particular to a simulation test method and a related device. Background Urban NOA (Navigate on Autopilot), namely urban piloting automatic driving, is taken as a higher level of L2-level intelligent driving, has become an important research direction of all intelligent driving manufacturers, and in order to improve the control level of urban NOA, simulation test of the urban NOA has become an indispensable important link. In practical application, the quantity of scenes to be processed in the urban NOA test is large, and the scene complexity is high, so that how to realize the simulation test of the urban NOA is a technical problem which needs to be solved by the technicians in the field. Disclosure of Invention In view of the above, the present application provides a simulation test method and related device to solve the problem of the need for implementing the simulation test of urban NOA. In order to solve the technical problems, the application adopts the following technical scheme: The first aspect of the present application provides a simulation test method, including: Generating a simulation map, wherein the simulation map is obtained through scene generalization operation; Responding to a navigation instruction of a destination, and executing positioning operation by using the simulation map to obtain initial positioning information of a simulation vehicle; performing path planning operation based on the simulation map, the initial positioning information and the destination to obtain initial navigation information of a simulation vehicle; converting the initial navigation information and the initial positioning information into target navigation information and target positioning information which can be identified by a target piloting automatic driving NOA controller, and sending the target navigation information and the target positioning information to the target NOA controller; According to the initial positioning information, performing simulation operation on the running scene of the simulated vehicle, outputting the running scene obtained by simulation to the target NOA controller, and enabling the target NOA controller to control the running of the simulated vehicle to the destination by using the target navigation information, the target positioning information and the running scene, wherein the target NOA controller controls the control information of the running of the simulated vehicle and the running information of the simulated vehicle to serve as reference data for testing the target NOA controller. In one possible implementation, the generating the simulated map includes: Acquiring data acquired by various sensors; processing the acquired data according to a processing mode corresponding to the acquired data; when the data fusion operation is carried out, the point cloud data and semantic layers in the acquired picture information are overlapped under the same coordinate system, and a three-dimensional scene is reproduced by combining inertial navigation data, so that the map scene slice data are obtained; and performing scene generalization operation on the map scene slice data to obtain a simulation map. In one possible implementation, performing a scene generalization operation on the map scene slice data to obtain a simulated map, including: Performing scene generalization operation on the map scene slice data by using a scene generalization algorithm to obtain a simulation map; The operation logic of the scene generalization algorithm is as follows: and generating a random scene by using the constraint condition, and constructing a simulation map by using the random scene. In one possible implementation, performing a positioning operation using the simulated map to obtain initial positioning information of the simulated vehicle includes: Acquiring an environment simulation image of a simulation vehicle; Performing feature extraction operation on the environment simulation image to obtain multi-scale features of the environment simulation image; determining a candidate region where the simulation vehicle is located from the simulation map by utilizing the multi-scale features; And performing classification and regression operation on the candidate areas to obtain initial positioning information of the simulation vehicle. In one possible implementation, performing a path planning operation based on the simulated map, the initial positioning information, and the destination to obtain initial navigation information of the simulated vehicle, including: Acquiring a road network of the simulation map; determining a coverage map including the initial positioning information and the destination from a road network using the vertex separator; dividing the vertex separator into small subsets of vertices to decompose the overlay into a plurality of balancing units; and perf