CN-121995799-A - Automatic driving control system and control method thereof

CN121995799ACN 121995799 ACN121995799 ACN 121995799ACN-121995799-A

Abstract

The system comprises a calling interface for abstracting an external service function through a service interface set, a service realization module provides a multi-platform adaptation example, and a service locator module dynamically binds the adaptation example, the interface and the platform type, so that an automatic driving service module only depends on a virtual interface and is realized instead of a specific platform, and decoupling of service logic and platform service is effectively realized.

Inventors

ZHOU HANQING
HAN XU

Assignees

广州文远知行科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251231

Claims (10)

1. An automatic driving control system, characterized by comprising: a service interface set for calling interfaces of external service functions related to the platform during automatic driving control; The service implementation module comprises a plurality of adaptation implementation embodiments, wherein the adaptation implementation embodiments are used for defining the functions of the service interface set according to a target platform or a target operation mode; The service locator module stores the binding relation between each adaptation implementation example and the platform type of the service interface set, wherein the binding relation is obtained by extracting access records of external service functions from history control data of automatic driving to construct the adaptation implementation example and binding the constructed adaptation implementation example with the service interface set and the platform type; And the automatic driving business module is used for triggering the service locator module to match the target adaptation implementation example by calling the service interface set, and calling the matched external service function to control each intelligent module to complete the automatic driving task.
2. The autopilot control system of claim 1 wherein the service interface set is defined by a plurality of virtual interfaces without concrete implementation code by an abstract definition by external service functions, the virtual interfaces comprising: The log service virtual interface is obtained by abstracting log access protocols of log service functions aiming at different platforms and abstractly defining a log writing method; The time service virtual interface is obtained by abstracting and defining a method for obtaining the current time by extracting time synchronization protocols of a time service function aiming at different platforms; the error reporting service virtual interface is obtained by abstracting an abnormal feedback service function to abstract and define a reporting abnormal method aiming at abnormal reporting protocols of different platforms; The performance analysis service virtual interface is obtained by abstracting analysis rules of the performance analysis service function aiming at different platforms and abstractly defining a record time-consuming method.
3. The autopilot control system of claim 1 wherein the service implementation module includes a Linux platform adaptation implementation, a QNX platform adaptation implementation, and a simulation platform adaptation implementation.
4. The autopilot control system of claim 3 wherein the Linux platform adaptation implementation has at least one external service access instance recorded therein that is time consuming by writing a system log file via a syslog interface, invoking a clock_gettime clock to obtain real time, sending to a system monitor process via DBus, and invoking a perf tool interface.
5. The autopilot control system of claim 3 wherein the QNX platform adaptation implementation has recorded therein at least one external service access instance that is time consuming by writing to a secure log partition through a controlled audit interface of QNX, obtaining real time based on a QNX kernel clock, sending to a security monitoring module through a QNX messaging mechanism, and calling a tracking interface of QNX Momentics tool chain.
6. The autopilot control system of claim 3 wherein the simulation platform adaptation implementation has recorded therein at least one external service access instance that stores content in a memory queue, generates virtual time stamps in configurable steps, displays abnormal progress by marking at a simulation monitor interface, and counts module execution time consumption within a simulation framework as recording time consumption.
7. The autopilot control system of any one of claims 1-6 wherein the intelligent module includes a perception module, a prediction module, a decision module, and a control module; The automatic driving business module is specifically used for: Determining a platform for running an automatic driving task currently, and controlling a service locator module to match a target adaptation implementation example based on the platform; Based on an example in the target adaptation implementation, the control perception module calls a time service virtual interface in the service interface set to acquire a receiving time stamp of the laser radar point cloud data, and calls a log service virtual interface to record perceived data quantity and quality information; Based on the example in the target adaptation implementation, the control prediction module calls the performance analysis service virtual interface to record the execution time consumption of the traffic participant behavior prediction algorithm, and calls the error reporting service virtual interface to report the abnormal prediction failure; Based on the example in the target adaptation embodiment, the control decision module calls the time service virtual interface to synchronize the multi-sensor time stamp, and calls the log service interface to record the path planning result; Based on the example in the target adaptation embodiment, the control module calls the error reporting service virtual interface to report the abnormal control instruction of the executor, and calls the performance analysis service virtual interface to record the control instruction and generate time consumption.
8. A control method based on the automatic driving control system according to any one of claims 1 to 7, characterized in that the method comprises: When automatic driving control is started, identifying the platform type of the current platform, and determining a target adaptation implementation example from the binding relation between the adaptation implementation example and the platform type of the service interface set based on the platform type; Analyzing the target adaptation implementation to adjust the calling protocol relation between each intelligent module and each virtual interface in the service interface set; And controlling the intelligent modules to operate, and calling the external service functions to cooperate with the intelligent modules to complete the automatic driving task based on the adjusted calling protocol relationship.
9. The method of claim 8, wherein the method further comprises: Detecting whether the platform type of the current platform changes or not; If yes, clearing call protocol relations of each intelligent module and each virtual interface in the service interface set, and determining a new target adaptation implementation example based on the changed platform type; Under the condition of not interrupting the automatic driving task, defining the calling protocol relation between each intelligent module and each virtual interface in the service interface set based on the new target adaptation implementation example, and continuously completing the automatic driving task.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, the computer executable instructions, when invoked and executed by a processor, cause the processor to implement the control method of claim 8 or 9.

Description

Automatic driving control system and control method thereof Technical Field The disclosure relates to the technical field of automatic driving, and in particular relates to an automatic driving control system and a control method thereof. Background Autopilot systems rely on a large number of software modules to implement awareness, decision-making, and control. These modules typically run on different hardware platforms and operating systems, such as the Linux system for vehicles at road time and the QNX security system for vehicle models at mass production time. The different systems have different realization service functions on which the modules need to be dependent in the operation time interval, so that the modules in the different systems have strong coupling relations with the corresponding realization service functions, which is not beneficial to migration and compatibility between the systems. Disclosure of Invention Accordingly, an object of the present disclosure is to provide an autopilot control system and a control method thereof, which solve the problem of poor portability caused by strong coupling between each intelligent module and external service functions in the existing autopilot system. In a first aspect, an embodiment of the present disclosure provides an automatic driving control system, including: a service interface set for calling interfaces of external service functions related to the platform during automatic driving control; The service implementation module comprises a plurality of adaptation implementation embodiments, wherein the adaptation implementation embodiments are used for defining the functions of the service interface set according to a target platform or a target operation mode; The service locator module stores the binding relation between each adaptation implementation example and the platform type of the service interface set, wherein the binding relation is obtained by extracting access records of external service functions from history control data of automatic driving to construct the adaptation implementation example and binding the constructed adaptation implementation example with the service interface set and the platform type; And the automatic driving business module is used for triggering the service locator module to match the target adaptation implementation example by calling the service interface set, and calling the matched external service function to control each intelligent module to complete the automatic driving task. In a second aspect, an embodiment of the present disclosure provides a control method based on the above-provided autopilot control system, where the method includes: When automatic driving control is started, identifying the platform type of the current platform, and determining a target adaptation implementation example from the binding relation between the adaptation implementation example and the platform type of the service interface set based on the platform type; Analyzing the target adaptation implementation to adjust the calling protocol relation between each intelligent module and each virtual interface in the service interface set; And controlling the intelligent modules to operate, and calling the external service functions to cooperate with the intelligent modules to complete the automatic driving task based on the adjusted calling protocol relationship. In a third aspect, embodiments of the present disclosure provide a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to implement the control method provided above. The embodiment of the disclosure brings the following beneficial effects: According to the automatic driving control system and the control method thereof, the service interface set is used for abstracting the calling interface of the external service function, the service realization module provides the multi-platform adaptation example, and the service locator module dynamically binds the adaptation example, the interface and the platform type, so that the automatic driving service module only depends on the virtual interface and is realized by a specific platform, and the decoupling of the service logic and the platform service is effectively realized. Meanwhile, the accurate matching of the adaptation examples and the platform demands is guaranteed through the binding relation constructed by the historical control data, portability of the system among different platforms is remarkably improved, code modification cost of cross-platform deployment is reduced, seamless connection during platform switching is supported, and continuity and stability of an automatic driving control task are guaranteed. Additional features and advantages of the disclosure will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the disclosure. The object