CN116594659A

CN116594659A - Vehicle-mounted domain controller program optimization system, method and device and vehicle

Info

Publication number: CN116594659A
Application number: CN202310879343.9A
Authority: CN
Inventors: 张晶威; 詹景麟; 计晶; 杨钧
Original assignee: Suzhou Inspur Intelligent Technology Co Ltd
Current assignee: Suzhou Inspur Intelligent Technology Co Ltd
Priority date: 2023-07-18
Filing date: 2023-07-18
Publication date: 2023-08-15
Anticipated expiration: 2043-07-18
Also published as: CN116594659B

Abstract

The application provides a program optimizing system, a method, a device and a vehicle of a vehicle-mounted domain controller, wherein the system comprises the following components: a simulated data signal source and an on-board domain controller; the simulation data signal source is used for acquiring vehicle drive test data, converting the vehicle drive test data into vehicle-mounted sensor port data, and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller; the vehicle-mounted domain controller is used for correcting parameters of the automatic driving program by taking the vehicle-mounted sensor data as a training sample so as to iteratively optimize the automatic driving program. According to the system provided by the scheme, the vehicle drive test data are converted into the vehicle-mounted sensor port data readable by the vehicle-mounted domain controller, so that the vehicle-mounted domain controller can perform iterative optimization of the program locally, and the optimization efficiency of the program of the vehicle-mounted domain controller is improved.

Description

Vehicle-mounted domain controller program optimization system, method and device and vehicle

Technical Field

The application relates to the technical field of automatic driving, in particular to a program optimization system, method and device for a vehicle-mounted domain controller and a vehicle.

Background

An on-board domain controller of an autopilot vehicle is an edge-computing embedded platform for running autopilot programs. Wherein the autopilot program already deployed on the vehicle domain controller requires iterative optimization.

In the prior art, usually, an automatic driving vehicle uploads drive test data to a cloud server, the cloud server performs iterative optimization on an automatic driving program based on the obtained drive test data, and the optimized automatic driving program is migrated to a vehicle-mounted domain controller again.

However, because the cloud server and the vehicle-mounted domain controller are different computing platforms, the process of program migration is complicated, and the optimization efficiency of the vehicle-mounted domain controller program is reduced.

Disclosure of Invention

The application provides a vehicle-mounted domain controller program optimization system, a device and a vehicle, which are used for solving the defects that the optimization efficiency of the vehicle-mounted domain controller program is reduced in the prior art.

A first aspect of the present application provides an on-board domain controller program optimization system comprising: a simulated data signal source and an on-board domain controller;

the simulation data signal source is used for acquiring vehicle drive test data, converting the vehicle drive test data into vehicle-mounted sensor port data, and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller;

The vehicle-mounted domain controller is used for taking the vehicle-mounted sensor data as a training sample and correcting parameters of an automatic driving program so as to iteratively optimize the automatic driving program.

In an alternative embodiment, the dummy data signal source includes: an optical network interface, a hard disk interface and a PCIe interface;

the simulation data signal source is specifically used for:

and remotely acquiring the vehicle drive test data at a cloud server based on the optical network interface, and/or acquiring the vehicle drive test data at a vehicle hard disk device based on the hard disk interface, and/or acquiring the vehicle drive test data based on the PCIe interface.

In an alternative embodiment, the autopilot program includes a perception domain model and a decision domain model, and the onboard domain controller is specifically configured to:

taking the vehicle-mounted sensor data as a training sample, and correcting parameters of the perception domain model to obtain an optimized perception domain model;

generating optimized perception data based on the optimized perception domain model;

and correcting parameters of the decision domain model based on the optimized perception data to obtain an optimized decision domain model.

In an alternative embodiment, the in-vehicle sensor port data includes lidar data, and the simulation data signal source includes: a main control chip;

The main control chip is used for determining a target Ethernet topological structure according to the Ethernet type of the vehicle-mounted domain controller so as to transmit the laser radar data to the vehicle-mounted domain controller based on the target Ethernet topological structure.

In an optional implementation manner, the master control chip is provided with an SGMII interface; the simulation data signal source also comprises a traditional Ethernet PHY chip;

when the Ethernet type of the vehicle-mounted domain controller is a traditional Ethernet, the target Ethernet topological structure is an Ethernet electric port which is communicated with the SGMII interface and the vehicle-mounted domain controller through the traditional Ethernet PHY chip.

In an alternative embodiment, the main control chip is provided with an SMI interface; the simulation data signal source also comprises a vehicle-mounted Ethernet PHY chip;

when the Ethernet type of the vehicle-mounted domain controller is the vehicle-mounted Ethernet, the target Ethernet topological structure is a vehicle-mounted Ethernet interface which is communicated with the vehicle-mounted domain controller through the vehicle-mounted Ethernet PHY chip.

In an alternative embodiment, the in-vehicle sensor port data includes image data, and the simulation data signal source includes an image sensor module;

The image sensor module is used for carrying out serialization processing on the image data so as to transmit the image data subjected to serialization processing to the vehicle-mounted domain controller based on a coaxial cable.

In an alternative embodiment, the on-board domain controller is provided with a Fakra interface;

and the image sensor module transmits the serialized image data to the vehicle-mounted domain controller through the Fakra interface.

In an alternative embodiment, the image sensor module includes a serializer and the vehicle domain controller includes a deserializer.

In an alternative embodiment, the simulation data signal source comprises an FPGA, and the serializer is connected to an MIPI interface of the FPGA;

the image data includes MIPI data and an image control signal.

In an alternative embodiment, the image sensor module or the on-board domain controller comprises an image signal processor;

when the image sensor module comprises the image signal processor, preprocessing the MIPI data based on the image signal processor according to the image control signal, and transmitting the preprocessed MIPI data to a serializer so as to perform serialization processing on the preprocessed MIPI data based on the serializer;

When the vehicle-mounted domain controller comprises the image signal processor, preprocessing the deserialized MIPI data according to the image control signal based on the image signal processor.

In an alternative embodiment, the image control signal includes a trigger signal sent by the serializer, the trigger signal being used to designate an image frame.

In an alternative embodiment, the in-vehicle sensor port data includes millimeter wave radar data, and the simulation data signal source includes: a CAN physical layer transceiver;

the CAN physical layer transceiver is used for transmitting the millimeter wave radar data to a CAN interface of the vehicle-mounted domain controller; the vehicle-mounted sensor interface of the vehicle-mounted domain controller comprises the CAN interface. In an optional embodiment, the vehicle drive test data at least includes current vehicle measured data, drive test vehicle measured data and front and rear vehicle measured data;

the current measured data of the vehicle, the measured data of the drive test vehicle and the measured data of the front and rear vehicles are all multi-sensor time synchronization data.

In an alternative embodiment, the dummy data signal source includes memory particles and solid state memory.

The second aspect of the present application provides a method for optimizing a program of an on-board domain controller, comprising:

acquiring vehicle drive test data;

converting the vehicle drive test data into vehicle-mounted sensor port data;

and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller, so that the vehicle-mounted domain controller takes the vehicle-mounted sensor data as a training sample, and correcting parameters of an automatic driving program to iteratively optimize the automatic driving program.

In an alternative embodiment, the acquiring the vehicle drive test data includes:

and remotely acquiring the vehicle drive test data at a cloud server based on an optical network interface, and/or acquiring the vehicle drive test data at a vehicle hard disk device based on a hard disk interface, and/or acquiring the vehicle drive test data based on a PCIe interface.

In an alternative embodiment, the enabling the in-vehicle domain controller to correct parameters of an autopilot program using the in-vehicle sensor data as a training sample to iteratively optimize the autopilot program includes:

In an alternative embodiment, the on-board sensor port data includes laser radar data, and the transmitting the on-board sensor port data to the on-board domain controller through the on-board sensor interface of the on-board domain controller includes:

and determining a target Ethernet topology structure according to the Ethernet type of the vehicle-mounted domain controller, so as to transmit the laser radar data to the vehicle-mounted domain controller based on the target Ethernet topology structure.

In an alternative embodiment, the determining the target ethernet topology according to the ethernet type of the in-vehicle domain controller includes:

when the Ethernet type of the vehicle-mounted domain controller is the traditional Ethernet, the target Ethernet topological structure is an Ethernet electric port which is communicated with the SGMII interface of the master control chip and the vehicle-mounted domain controller through the traditional Ethernet PHY chip.

When the Ethernet type of the vehicle-mounted domain controller is the vehicle-mounted Ethernet, the target Ethernet topological structure is a vehicle-mounted Ethernet interface which is communicated with the SMI of the main control chip and the vehicle-mounted Ethernet of the vehicle-mounted domain controller through the vehicle-mounted Ethernet PHY chip.

In an alternative embodiment, the in-vehicle sensor port data includes image data, and the transmitting the in-vehicle sensor port data to the in-vehicle domain controller through the in-vehicle sensor interface of the in-vehicle domain controller includes:

and serializing the image data based on the image sensor module to transmit the serialized image data to the vehicle-mounted domain controller based on a coaxial cable.

In an alternative embodiment, the on-board domain controller is provided with a Fakra interface; the coaxial cable-based transmission of the serialized image data to the vehicle-mounted domain controller includes:

In an alternative embodiment, the image data includes MIPI data and image control signals.

In an alternative embodiment, the image sensor module or the vehicle domain controller includes an image signal processor, the method further comprising:

The vehicle-mounted sensor port data includes millimeter wave radar data, and the transmitting of the vehicle-mounted sensor port data to the vehicle-mounted domain controller through the vehicle-mounted sensor interface of the vehicle-mounted domain controller includes:

Transmitting the millimeter wave radar data to a CAN interface of the vehicle-mounted domain controller based on a CAN physical layer transceiver; the vehicle-mounted sensor interface of the vehicle-mounted domain controller comprises the CAN interface. In an optional embodiment, the vehicle drive test data at least includes current vehicle measured data, drive test vehicle measured data and front and rear vehicle measured data;

A third aspect of the present application provides an on-vehicle domain controller program optimizing apparatus, comprising:

the acquisition module is used for acquiring vehicle drive test data;

the conversion module is used for converting the vehicle drive test data into vehicle-mounted sensor port data;

and the optimization module is used for sending the vehicle-mounted sensor port data to the vehicle-mounted domain controller through the vehicle-mounted sensor interface of the vehicle-mounted domain controller so that the vehicle-mounted domain controller takes the vehicle-mounted sensor data as a training sample, and corrects parameters of an automatic driving program to carry out iterative optimization on the automatic driving program.

In an alternative embodiment, the acquiring module is specifically configured to:

In an alternative embodiment, the autopilot program includes a perception domain model and a decision domain model, and the optimization module is specifically configured to:

In an alternative embodiment, the on-board sensor port data includes lidar data, and the optimization module is specifically configured to:

In an alternative embodiment, the optimization module is specifically configured to:

In an alternative embodiment, the in-vehicle sensor port data includes image data, and the optimizing module is specifically configured to:

In an alternative embodiment, the on-board domain controller is provided with a Fakra interface; the optimizing module is specifically configured to:

In an alternative embodiment, the image sensor module or the vehicle domain controller includes an image signal processor, and the optimization module is further configured to:

In an alternative embodiment, the on-board sensor port data includes millimeter wave radar data, and the optimizing module is specifically configured to:

Transmitting the millimeter wave radar data to a CAN interface of the vehicle-mounted domain controller based on a CAN physical layer transceiver; the vehicle-mounted sensor interface of the vehicle-mounted domain controller comprises the CAN interface.

In an optional embodiment, the vehicle drive test data at least includes current vehicle measured data, drive test vehicle measured data and front and rear vehicle measured data;

A fourth aspect of the application provides a vehicle comprising: vehicle body and on-board domain controller program optimization system as described in the first aspect and various possible designs of the first aspect above.

A fifth aspect of the present application provides an electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executes the computer-executable instructions stored by the memory such that the at least one processor performs the method as described above for the second aspect and the various possible designs for the second aspect.

A sixth aspect of the application provides a computer readable storage medium having stored therein computer executable instructions which when executed by a processor implement the method as described in the second aspect and the various possible designs of the second aspect above.

The technical scheme of the application has the following advantages:

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.

FIG. 1 is a schematic diagram of a conventional optimization flow of a vehicle-mounted domain controller program;

fig. 2 is a schematic structural diagram of an optimizing system for a vehicle-mounted domain controller according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a simulation data signal source according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an exemplary target Ethernet topology according to an embodiment of the application;

FIG. 5 is a schematic diagram of another exemplary target Ethernet topology provided by an embodiment of the application;

FIG. 6 is a diagram of an exemplary image data transmission topology provided by an embodiment of the present application;

FIG. 7 is a diagram of another exemplary image data transmission topology provided by an embodiment of the present application;

fig. 8 is a schematic diagram of an image data transmission flow provided in an embodiment of the present application;

fig. 9 is a schematic diagram of a millimeter wave radar data transmission flow provided in an embodiment of the present application;

FIG. 10 is a schematic diagram of a simulation data signal source multi-machine synchronization logic provided in an embodiment of the present application;

FIG. 11 is an interaction schematic diagram of an on-board domain controller program optimization system according to an embodiment of the present application;

FIG. 12 is a schematic diagram of an optimization flow of an autopilot procedure according to an embodiment of the present application;

fig. 13 is a flow chart of an optimization method of a vehicle-mounted domain controller program according to an embodiment of the present application;

Fig. 14 is a schematic structural diagram of an optimizing device for a vehicle-mounted domain controller according to an embodiment of the present application;

fig. 15 is a schematic structural view of a vehicle according to an embodiment of the present application;

fig. 16 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. These drawings and the written description are not intended to limit the scope of the disclosed concept in any way, but to illustrate the inventive concept to those skilled in the art by reference to specific embodiments.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. In the following description of the embodiments, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

The vehicle drive test data, especially the sensor data actually collected by the vehicle in the road test, has important pushing effect on the automatic driving algorithm (program) implementation. The automatic driving algorithm model needs to train and adjust a large amount of actual data, and also needs to evaluate the effectiveness of the data after cleaning, so as to achieve the optimal solution.

Compared with the simulation scene data of the simulator, the drive test actual acquisition data has higher availability for training and optimizing the automatic driving system. However, the cost of collecting data in real scenes is relatively high, so that the software and hardware system for training and optimizing the autopilot domain controller by using the raw data is a concern in multiple fields such as autopilot simulation, loop test and system optimization.

The autopilot technology is a strong AI application scene, so that an autopilot algorithm has natural association with an AI computing platform (server), and the autopilot algorithm evolves in the following way: firstly, simulating and configuring parameters on an AI computing platform based on a simulator; further migrating the computing platform on the vehicle to realize an algorithm of the actual road condition; optimizing computing platform hardware in actual road conditions, and solving the engineering environmental adaptability problem (such as the requirements of environmental temperature, vehicle vibration, interface reliability and the like on the computing platform); and finally, an embedded computing platform which is low in energy consumption and high in reliability and faces to a vehicle application scene is realized, and the embedded computing platform is accompanied with the migration of software codes and algorithms.

The drive test data application at the present stage mainly comprises the following processes: the data collected by the vehicle (including the data collection vehicle or the actual drive test vehicle) is stored in a memory device of the vehicle-mounted computing platform, and the process is generally called data 'landing'. And uploading the tray data for a period of time to a cloud server by operation and maintenance personnel, wherein the operation and maintenance personnel are called as 'cloud up'. The algorithm engineer inspects and optimizes the data at the cloud. And the optimized algorithm is issued to the vehicle domain controller for verification, and the data are collected again to repeat the optimization process. As shown in fig. 1, a conventional flow chart of optimizing a program of an on-board domain controller is shown, and an on-board domain controller platform for automatic driving is an edge computing embedded platform, and an application scene of the computing platform is different from a scene of a data center server in a conventional internet industry. The traditional internet industry realizes decoupling of software and hardware, a software engineer can be far away from a hardware platform, iterative software is optimized, and finally provided service can be verified after optimization. In contrast, the code implemented by the autopilot software engineer ultimately requires vehicle control to be implemented on the domain controller platform, whose hardware is personalized and the software cannot be decoupled from the hardware platform. The running state of the actual vehicle is related to software and hardware, and a large number of software engineers cannot be developed in a vehicle test site in a centralized manner.

And the cloud development and simulation data analysis means are adopted, and finally the process of acquiring the data again by the data acquisition-algorithm optimization-verification algorithm is still needed to be realized by the codes downloaded to the vehicle-mounted domain controller. In addition, the cloud end and the vehicle end are different computing platforms, faults need to be checked in multiple aspects (such as code migration problems, field hardware or system problems and the like), software and hardware of the automatic driving domain controller are strongly correlated, and in addition, iterative optimization of the software and the hardware of the automatic driving domain controller is strongly dependent on data actually collected by drive test, so that program optimization efficiency is reduced in the prior art.

In view of the above problems, an embodiment of the present application provides a system, a method, a device and a vehicle for optimizing a program of a vehicle-mounted domain controller, where the system includes: a simulated data signal source and an on-board domain controller; the simulation data signal source is used for acquiring vehicle drive test data, converting the vehicle drive test data into vehicle-mounted sensor port data, and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller; the vehicle-mounted domain controller is used for correcting parameters of the automatic driving program by taking the vehicle-mounted sensor data as a training sample so as to iteratively optimize the automatic driving program. According to the system provided by the scheme, the vehicle drive test data are converted into the vehicle-mounted sensor port data readable by the vehicle-mounted domain controller, so that the vehicle-mounted domain controller can perform iterative optimization of the program locally, and the optimization efficiency of the program of the vehicle-mounted domain controller is improved.

The embodiment of the application provides a program optimization system of an on-board domain controller, which is used for iteratively optimizing an automatic driving program currently deployed by the on-board domain controller. As shown in fig. 2, a schematic structural diagram of an on-board domain controller program optimizing system according to an embodiment of the present application includes: and simulating a data signal source and an on-board domain controller.

The simulation data signal source is used for acquiring vehicle drive test data, converting the vehicle drive test data into vehicle-mounted sensor port data, and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller; the vehicle-mounted domain controller is used for correcting parameters of the automatic driving program by taking the vehicle-mounted sensor data as a training sample so as to iteratively optimize the automatic driving program.

It should be noted that, because the vehicle-mounted sensor sends sensor data to the vehicle-mounted domain controller through the corresponding vehicle-mounted sensor interface in the normal operation process of the vehicle-mounted domain controller, the vehicle-mounted domain controller determines the corresponding automatic driving strategy according to the obtained sensor data based on the current automatic driving program, and therefore the vehicle-mounted domain controller can only read the vehicle-mounted sensor data.

Specifically, after the vehicle drive test data are obtained in multiple modes, the vehicle drive test data can be converted into corresponding type vehicle-mounted sensor port data according to the specific type (such as radar data, image data and the like) of the current vehicle drive test data, and then the vehicle-mounted sensor port data are transmitted to the vehicle-mounted domain controller through the corresponding vehicle-mounted sensor port, so that the vehicle-mounted domain controller can read normally, further iteration optimization is carried out on an automatic driving program by utilizing the vehicle-mounted sensor data, and the vehicle-mounted sensor data can be used as a training sample to carry out iteration optimization on a machine learning model related to the automatic driving program.

Specifically, in one embodiment, the vehicle drive test data at least includes current vehicle actual measurement data, drive test vehicle actual measurement data, and front-rear vehicle actual measurement data; the current measured data of the vehicle, the measured data of the drive test vehicle and the measured data of the front and rear vehicles are all multi-path sensor time synchronization data.

The drive test vehicle is a vehicle specially used for collecting actual measurement data. Because different vehicles have different kinds and numbers of sensors, the output interfaces of the simulation data signal sources need to be aligned with the number of the vehicle-mounted sensors. However, because the sensor configurations of different manufacturers and vehicles are different, the semi-physical simulation data source (simulation data signal source) should support parallel attribute, so as to realize multi-sensor time synchronization and support the requirements of a larger number of sensor signals of various vehicles.

On the basis of the above embodiment, in order to ensure the reliability of the obtained vehicle drive test data, as shown in fig. 3, a schematic structural diagram of a simulation data signal source provided in an embodiment of the present application is provided, as an implementation manner, in an embodiment, the simulation data signal source includes: an optical network interface.

The simulation data signal source can specifically remotely acquire vehicle drive test data at the cloud server based on the optical network interface, namely, the cloud data can be read through the optical network interface.

It should be noted that the vehicle drive test data stored in the cloud server at least includes vehicle drive test data of each automatic driving vehicle and clouds on the drive test vehicle.

The emulation data signal source further comprises memory granules and a solid state memory, and correspondingly further comprises a memory controller for controlling the memory granules, as shown in fig. 3. The semi-physical simulation data signal source of the automatic driving sensor takes an FPGA as a main processor of the System, wherein ARM processor resources (generally called Prosessor System) and logic resources (Programming Logic) are included in the FPGA, in addition, a memory is mounted outside a memory controller of the FPGA, the FPGA can be used as the main memory resources of the processor in the FPGA, and also can be used as a Buffer (Buffer) of the FPGA logic resources, and in addition, the FPGA also comprises memory resources and IO interfaces for storing mirror images of the System. The simulation data signal source also comprises a power supply module and a clock module, wherein the power supply module is used for supplying power to the whole simulation data signal source, the clock module is used for guaranteeing time synchronization of vehicle drive test data, and the simulation data signal source also comprises a time synchronization signal output interface and a time synchronization signal input interface for realizing time synchronization of data. In order to further ensure the data communication capability of the simulation data signal source, the simulation data signal source is further provided with a USB interface and an I2C UART SPI interface. Realizing the semi-physical simulation data signal source of automatic driving needs to be aligned with the main sensor of the current automatic driving vehicle perception domain at first, comprising: lidar (Lidar) and image sensors. The laser radar also comprises a main laser radar and a blind supplementing laser radar, and the image sensor comprises forward looking, looking around, specific traffic sign tracking and the like. The above mentioned sensors also have a requirement for time synchronization.

Specifically, in one embodiment, the simulated data signal source comprises: a hard disk interface (SATA interface); the simulation data signal source can be used for acquiring vehicle drive test data from the vehicle hard disk device based on the hard disk interface.

Specifically, the simulation data signal source can acquire the drive test data of the vehicle after the disc is dropped through the hard disc interface, wherein the storage data of the hard disc equipment of the vehicle is derived from the drive test acquisition sensor data of the vehicle.

Specifically, in one embodiment, the simulated data signal source comprises: a PCIe interface; the simulation data signal source can specifically acquire vehicle drive test data based on a PCIe interface.

Specifically, the vehicle drive test data stored in the cloud server and other platforms can be stored in the PCIe card, so that the vehicle drive test data can be provided for the emulation data signal source in a manner that the PCIe card is inserted into the PCIe interface of the emulation data signal source.

On the basis of the above embodiment, as a practical manner, in one embodiment, the on-board sensor port data includes lidar data, and the simulation data signal source includes: and a main control chip.

The main control chip is used for determining a target Ethernet topological structure according to the Ethernet type of the vehicle-mounted domain controller so as to transmit laser radar data to the vehicle-mounted domain controller based on the target Ethernet topological structure.

It should be noted that, the data output interface of the early-stage autopilot vehicle-mounted laser radar is mostly an ethernet interface, so that most of the road-test vehicle-mounted domain controllers directly or indirectly access the laser radar data through an ethernet electrical interface (Copper). Along with the progress of the laser radar technology, the cost is reduced, the method is gradually applied to new mass production vehicle types, and the laser radar supporting a vehicle-mounted Ethernet (1000 Base-T1) interface also enters the market. The physical layer of the Ethernet interface (1000 Base-T) is different from that of the in-vehicle Ethernet (1000 Base-T1). In order to enable the simulation data signal source provided by the embodiment of the application to be applicable to various vehicle-mounted domain controllers, a main control chip can be arranged in the simulation data signal source so as to determine a target Ethernet topological structure adapting to the Ethernet type of the vehicle-mounted domain controller based on the main control chip according to the Ethernet type of the vehicle-mounted domain controller, and then laser radar data is transmitted to the vehicle-mounted domain controller based on the target Ethernet topological structure, so that the vehicle-mounted domain controller can be ensured to normally read the laser radar data transmitted by the simulation data signal source.

Specifically, in an embodiment, the master control chip is provided with an SGMII interface; the simulation data signal source also comprises a traditional Ethernet PHY chip; when the Ethernet type of the vehicle-mounted domain controller is the traditional Ethernet, the target Ethernet topology structure is an Ethernet electric port which is used for communicating the SGMII interface and the vehicle-mounted domain controller through the traditional Ethernet PHY chip.

Wherein, the main control chip can adopt a MAC chip.

Accordingly, in one embodiment, the main control chip is provided with an SMI interface; the simulation data signal source also comprises a vehicle-mounted Ethernet PHY chip; when the Ethernet type of the vehicle-mounted domain controller is the vehicle-mounted Ethernet, the target Ethernet topological structure is a vehicle-mounted Ethernet interface which connects the SMI interface and the vehicle-mounted domain controller through the vehicle-mounted Ethernet PHY chip.

Exemplary, as shown in fig. 4, an exemplary target ethernet topology schematic diagram is provided for an embodiment of the present application, and is suitable for a vehicle domain controller with an ethernet type that is a conventional ethernet, where the conventional ethernet PHY chip (PHY in fig. 4) is an ethernet (1000 Base-T) PHY chip supporting an RGMII interface and an SGMII interface, for example, an 88E1512 chip (vehicle model 88EA 1512) of Marvell corporation, and configures a data path through an SMI interface of a master control chip. When the analog lidar outputs lidar data from an ethernet (1000 Base-T) electrical port (Copper), the PHY interface is configured to be SGMII to Copper, where the SGMII interface to RGMII interface are not connected.

As shown in fig. 5, another exemplary target ethernet topology schematic diagram is provided for an embodiment of the present application, which is suitable for a vehicle-mounted domain controller with an ethernet type being a vehicle-mounted ethernet, that is, when simulating a lidar with a vehicle-mounted ethernet (1000 Base-T1) interface, the PHY interface is configured to be SGMII to RGMII, at this time, the RGMII interface of the PHY chip is connected to another PHY chip supporting the vehicle-mounted ethernet, for example, an 88Q2112 chip of Marvell corporation, so that information supporting the vehicle-mounted ethernet (1000 Base-T1) may be output, and meanwhile, a mode 100Base-T1 or 1000Base-T1 of the vehicle-mounted ethernet PHY chip may be configured through an SMI interface of the Master chip, and a corresponding Master (Master) or Slave (Slave) mode may be configured.

Specifically, when the vehicle includes a plurality of lidars, the ethernet topology structure shown in fig. 4 or 5 can be duplicated in parallel according to the ethernet type of each lidar, so that the signal source can output a plurality of lidar data, and the current vehicle-mounted perception domain multi-lidar system is simulated.

On the basis of the above embodiment, as a practical implementation manner, in one embodiment, the vehicle-mounted sensor port data includes image data, and the simulation data signal source includes an image sensor module.

The image sensor module is used for serializing the image data so as to transmit the serialized image data to the vehicle-mounted domain controller based on the coaxial cable.

Specifically, the image data includes MIPI data, which can only be transmitted in a short distance, and in order to realize long-distance transmission of the image data, serializing processing is performed on the image data based on the image sensor module, so that the serialized image data can be transmitted to the vehicle-mounted domain controller based on the coaxial cable.

Specifically, in one embodiment, the on-board domain controller is provided with a Fakra interface; the image sensor module transmits the serialized image data to the vehicle-mounted domain controller through the Fakra interface.

The Fakra interface of the vehicle-mounted domain controller is a data interaction interface of an image sensor such as a camera of the vehicle-mounted domain controller.

Specifically, in one embodiment, the image sensor module includes a serializer and the on-board domain controller includes a deserializer.

The simulation data signal source comprises an FPGA, and the serializer is connected with an MIPI interface of the FPGA; the image data includes MIPI data and image control signals.

Specifically, in one embodiment, the image sensor module or the vehicle-mounted domain controller includes an image signal processor; when the image sensor module comprises an image signal processor, preprocessing MIPI data based on the image signal processor according to an image control signal, and transmitting the preprocessed MIPI data to a serializer so as to serialize the preprocessed MIPI data based on the serializer; when the vehicle-mounted domain controller comprises an image signal processor, the deserialized MIPI data is preprocessed according to the image control signal based on the image signal processor.

Exemplary, as shown in fig. 6, an exemplary image data transmission topology structure provided in an embodiment of the present application employs an ISP (image signal processor) front-mounted image acquisition. As shown in fig. 7, another exemplary image data transmission topology structure provided in an embodiment of the present application employs ISP (image signal processor) post-vehicle image acquisition, and the ECU in fig. 6 and 7 is a core processor of a vehicle domain controller. The in-vehicle image sensor and in-vehicle domain controller typically include two topologies as shown in fig. 6 and 7, both of which include serializers (serializers) and deserializers (deserializers) for transmitting a set of signals in the transmission and control links of the two topologies, which function to serialize image data and/or control signals into high-speed signals and transmit the high-speed signals over the coaxial cable, and deserialize the high-speed signals transmitted over the coaxial cable. The MIPI signal output by the CMOS sensor is converted into a high-speed serial signal with longer transmission distance and stronger anti-interference capability.

Specifically, in one embodiment, the image control signal includes a trigger signal sent by the serializer, the trigger signal being used to designate the image frame.

As shown in fig. 8, in the image data transmission flow schematic diagram provided by the embodiment of the application, the realization of the data interface of the semi-physical simulation data signal source simulation vehicle-mounted image sensor of the automatic driving sensor is to convert the MIPI signal of the image data into the high-speed serial data link signal, wherein the FPGA realizes the MIPI interface and MIPI PHY functions, the serializer is connected with the FPGA through the MIPI interface, and the serializer outputs the high-speed serial data link signal. On the other hand, functions such as control and preprocessing of the image sensor data stream need to be realized by the FPGA logic, the data stream control function includes that the on-board domain controller realizes functions such as triggering (sensor exposure) synchronization through a reverse control signal of the high-speed serial link, and the data stream control logic of the FPGA includes the functions of receiving the trigger signal of the serializer and outputting the designated image frame.

It should be noted that, time synchronization of the autopilot sensor is very important, and the laser radar and the image sensor need to be synchronized, and the same sensor needs to be synchronized in time, so that the synchronization precision is hundreds of μs to several ms at present. The vehicle drive test collected data is generally synchronous data. The semi-physical simulation data signal source provided by the embodiment of the application needs to disassemble and distribute different sensor data to each data interface and needs to identify the synchronous time stamp of the original data. For laser radar signals, the data packet of the laser radar signals contains GPRMC time information, and the laser radar signals can be accurate to a certain laser beam excitation time according to the luminous principle of the sensor, which is about tens of mu s. The image sensor synchronization signal in the drive test data is generally a frame synchronization trigger signal based on a laser radar time stamp. The trigger mark needs to be identified in the FPGA logic, and the image data stream is controlled by the trigger signal generated by the vehicle-mounted domain controller through the serializer.

On the basis of the foregoing embodiment, as a practical implementation manner, in an embodiment, the on-vehicle sensor port data includes millimeter wave radar data, and the simulation data signal source includes: CAN physical layer transceiver.

The CAN physical layer transceiver is used for transmitting the millimeter wave radar data to a CAN interface of the vehicle-mounted domain controller; the vehicle-mounted sensor interface of the vehicle-mounted domain controller comprises the CAN interface.

Specifically, as shown in fig. 9, a schematic diagram of a millimeter wave radar data transmission flow provided by the embodiment of the application is shown, and the CAN PHY is a CAN physical layer transceiver. The millimeter wave radar data CAN only be transmitted based on the CAN bus, but a main processor FPGA of the simulation data signal source is not provided with a CAN interface, namely CAN not be directly connected with the CAN bus, so that a CAN physical layer transceiver is arranged in the simulation data signal source, and the FPGA CAN transmit the millimeter wave radar data to the millimeter wave radar CAN interface of the vehicle-mounted domain controller based on the CAN physical layer transceiver.

For example, as shown in fig. 10, a logic diagram of multi-machine synchronization of a simulation data signal source provided by the embodiment of the application is that a semi-physical simulation data signal source supports multi-machine time synchronization, a single machine includes input and output signals supporting time synchronization signals, and signal pulses can be synchronized in the multi-machine. This synchronization mechanism supports two types of applications, one is that multiple sensors are supported as in the domain controller I of fig. 10, and multiple machines supporting synchronization can access the domain controller I. Another application is that the domain controller I and the domain controller II are two vehicle domain controllers that need to cooperate, and multiple controllers can be co-simulated based on synchronous data.

It should be noted that, the vehicle drive test data collected by automatic driving needs to be trained and utilized repeatedly, so as to continuously improve the performance and reliability of the automatic driving system. By using the collected data, model training is required for constructing an automatic driving model. Model training is an iterative process requiring continuous data input into the model to train a more accurate and reliable autopilot model. Meanwhile, the change in nature is fed back, and the model is continuously optimized, so that the driving requirements of people are better met.

Specifically, in an embodiment, as shown in fig. 11, an interaction schematic diagram of a program optimization system of a vehicle-mounted domain controller provided by the embodiment of the present application is shown, where the autopilot program includes a perception domain model and a decision domain model, and the vehicle-mounted domain controller may specifically use the vehicle-mounted sensor data as a training sample to correct parameters of the perception domain model, so as to obtain an optimized perception domain model; generating optimized perception data based on the optimized perception domain model; and correcting parameters of the decision domain model based on the optimized perception data to obtain an optimized decision domain model. As shown in fig. 11, the vehicle-mounted domain controller includes a perception domain and a decision domain, the perception domain model is applied to the perception domain, the decision domain model is applied to the decision domain, and the simulation data signal source is mainly communicated with the perception domain of the vehicle-mounted domain controller. The data preprocessed by the perception domain of the vehicle-mounted domain controller is returned to the semi-physical simulation data signal source and is used as one of the data sources, and the data preprocessing and recognition of the vehicle-mounted domain controller are trained. Correspondingly, the decision domain of the information vehicle-mounted domain controller based on the perception domain can also be correspondingly trained, and the specific training mode can be set according to actual training requirements, so that the embodiment of the application is not limited.

As shown in fig. 12, in the schematic view of the automatic driving program optimization flow provided in the embodiment of the present application, the collected raw data (vehicle drive test data) is processed by the simulation data signal source to obtain the vehicle-mounted sensor port data, so that the vehicle-mounted sensor data is used as a training sample. Optimization of the perception domain model includes two parts, on the one hand, the perception domain preprocessing and optimization of algorithm parameters self-perceived data usage, and on the other hand, attempts to discard part of the raw data by modifying the control manner of the sensor (e.g., modifying the frame rate of the perception domain sampling camera through the in-vehicle sensor control interface as shown in fig. 11). Specifically, the method comprises the steps of firstly carrying out parameter optimization on a related program of perception domain preprocessing and algorithm processing based on a training sample, then evaluating whether the optimized evaluation preprocessing and algorithm parameters reach preset standards or not, if not, repeating the steps of carrying out parameter optimization on the related program of perception domain preprocessing and algorithm processing based on the training sample, if so, further carrying out parameter optimization processing (decision layer processing) on a decision domain model, wherein the decision domain model is used for controlling application by using perception data provided by the optimized perception domain model, so that optimized perception data can be generated based on the optimized perception domain model, further taking the optimized perception data as decision domain training sample to optimize parameters of the decision domain model, obtaining an optimized decision domain model, then evaluating control results of the control algorithm in the decision domain model, and if the model accuracy represented by the results does not reach the preset standards, returning to the step of carrying out parameter optimization on the related program of perception domain preprocessing and algorithm processing based on the training sample until the decision domain model accuracy reaches the preset standards, and determining that the parameter optimization of a perception control system (vehicle-mounted domain controller program) is finished.

The program optimizing system for the vehicle-mounted domain controller provided by the embodiment of the application comprises the following components: a simulated data signal source and an on-board domain controller; the simulation data signal source is used for acquiring vehicle drive test data, converting the vehicle drive test data into vehicle-mounted sensor port data, and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller; the vehicle-mounted domain controller is used for correcting parameters of the automatic driving program by taking the vehicle-mounted sensor data as a training sample so as to iteratively optimize the automatic driving program.

The system provided by the embodiment of the application has the advantages that the drive test data is reproduced and the drive test data signal source consistent with the signal interface of the vehicle-mounted sensor is provided, so that the sensing signal of the drive test data connected to the vehicle-mounted domain controller has the same effect as the access of the vehicle-mounted sensor, namely, the drive test data of the vehicle is converted into the port data of the vehicle-mounted sensor readable by the vehicle-mounted domain controller, the vehicle-mounted domain controller can perform iterative optimization of a program locally, and the optimization efficiency of the program of the vehicle-mounted domain controller is improved. And in addition, the vehicle drive test data acquisition support storage equipment and network acquisition of the simulation data signal source can form an automatic driving perception and decision system with the vehicle-mounted domain controller in a laboratory environment, so that the performance and algorithm of the vehicle-mounted domain controller are optimized in a semi-physical simulation mode, and the problem is solved intensively by research personnel. And the development cost of the system is far lower than the test cost of the drive test vehicle.

The embodiment of the application provides a program optimization method for an on-board domain controller, which is used for performing iterative optimization on an automatic driving program currently deployed by the on-board domain controller. The execution main body of the embodiment of the application is electronic equipment such as a server, a desktop computer, a notebook computer, a tablet personal computer and other electronic equipment which can be used for carrying out iterative optimization on the automatic driving program currently deployed by the vehicle-mounted domain controller.

As shown in fig. 13, a flow chart of an optimization method for a vehicle-mounted domain controller program according to an embodiment of the present application is shown, where the method includes:

step 1201, obtaining vehicle drive test data;

step 1202, converting the vehicle drive test data into vehicle-mounted sensor port data;

in step 1203, the on-vehicle sensor port data is sent to the on-vehicle domain controller through the on-vehicle sensor interface of the on-vehicle domain controller, so that the on-vehicle domain controller uses the on-vehicle sensor data as a training sample, and corrects the parameters of the automatic driving program to perform iterative optimization on the automatic driving program.

Specifically, in an embodiment, acquiring vehicle drive test data includes:

and remotely acquiring the vehicle drive test data at the cloud server based on the optical network interface.

Specifically, in an embodiment, acquiring vehicle drive test data includes:

and acquiring vehicle drive test data from the vehicle hard disk device based on the hard disk interface.

Specifically, in an embodiment, acquiring vehicle drive test data includes:

and acquiring the vehicle drive test data based on the PCIe interface.

Specifically, in an embodiment, the method for enabling the vehicle-mounted domain controller to take the vehicle-mounted sensor data as a training sample and correct parameters of the automatic driving program so as to iteratively optimize the automatic driving program includes:

and taking the vehicle-mounted sensor data as a training sample, and correcting parameters of the perception domain model and the decision domain model so as to iteratively optimize the automatic driving program.

Specifically, in an embodiment, the in-vehicle sensor port data includes laser radar data, and the in-vehicle sensor port data is sent to the in-vehicle domain controller through an in-vehicle sensor interface of the in-vehicle domain controller, including:

and determining a target Ethernet topology structure according to the Ethernet type of the vehicle-mounted domain controller, so as to transmit laser radar data to the vehicle-mounted domain controller based on the target Ethernet topology structure.

Specifically, in an embodiment, determining the target ethernet topology according to the ethernet type of the on-board domain controller includes:

When the Ethernet type of the vehicle-mounted domain controller is the traditional Ethernet, the target Ethernet topology structure is an Ethernet electric port which is communicated with the SGMII interface of the master control chip and the vehicle-mounted domain controller through the traditional Ethernet PHY chip.

when the Ethernet type of the vehicle-mounted domain controller is the vehicle-mounted Ethernet, the target Ethernet topological structure is a vehicle-mounted Ethernet interface which is communicated with the SMI of the main control chip through the vehicle-mounted Ethernet PHY chip.

Specifically, in an embodiment, the in-vehicle sensor port data includes image data, and the in-vehicle sensor port data is sent to the in-vehicle domain controller through an in-vehicle sensor interface of the in-vehicle domain controller, including:

and serializing the image data based on the image sensor module to transmit the serialized image data to the vehicle-mounted domain controller based on the coaxial cable.

Specifically, in one embodiment, the on-board domain controller is provided with a Fakra interface; transmitting the serialized image data to the on-board domain controller based on the coaxial cable, comprising:

The image sensor module transmits the serialized image data to the vehicle-mounted domain controller through the Fakra interface.

Specifically, in one embodiment, the image sensor module includes a serializer and the on-board domain controller includes a deserializer. Specifically, in one embodiment, the image data includes MIPI data and image control signals.

Specifically, in an embodiment, the image sensor module or the vehicle domain controller includes an image signal processor, and the method further includes:

when the image sensor module comprises an image signal processor, preprocessing MIPI data based on the image signal processor according to an image control signal, and transmitting the preprocessed MIPI data to a serializer so as to serialize the preprocessed MIPI data based on the serializer;

when the vehicle-mounted domain controller comprises an image signal processor, the deserialized MIPI data is preprocessed according to the image control signal based on the image signal processor. Specifically, in one embodiment, the image control signal includes a trigger signal sent by the serializer, the trigger signal being used to designate the image frame.

Specifically, in one embodiment, the vehicle drive test data at least includes current vehicle actual measurement data, drive test vehicle actual measurement data, and front-rear vehicle actual measurement data;

the current measured data of the vehicle, the measured data of the drive test vehicle and the measured data of the front and rear vehicles are all multi-path sensor time synchronization data.

The vehicle-mounted domain controller program optimizing method provided by the embodiment of the application obtains the vehicle drive test data; converting the vehicle drive test data into vehicle-mounted sensor port data; and transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through a vehicle-mounted sensor interface of the vehicle-mounted domain controller so that the vehicle-mounted domain controller takes the vehicle-mounted sensor data as a training sample, and correcting parameters of the automatic driving program to iteratively optimize the automatic driving program. According to the method provided by the scheme, the vehicle drive test data are converted into the vehicle-mounted sensor port data readable by the vehicle-mounted domain controller, so that the vehicle-mounted domain controller can perform iterative optimization of the program locally, and the optimization efficiency of the program of the vehicle-mounted domain controller is improved.

The embodiment of the application provides a vehicle-mounted domain controller program optimizing device which is used for executing the vehicle-mounted domain controller program optimizing method provided by the embodiment.

Fig. 14 is a schematic structural diagram of an on-board domain controller program optimizing apparatus according to an embodiment of the present application. The in-vehicle domain controller program optimizing apparatus 130 includes: an acquisition module 1301, a conversion module 1302 and an optimization module 1303.

The acquisition module is used for acquiring vehicle drive test data; the conversion module is used for converting the vehicle drive test data into vehicle-mounted sensor port data; and the optimization module is used for transmitting the vehicle-mounted sensor port data to the vehicle-mounted domain controller through the vehicle-mounted sensor interface of the vehicle-mounted domain controller so that the vehicle-mounted domain controller takes the vehicle-mounted sensor data as a training sample, and corrects the parameters of the automatic driving program to carry out iterative optimization on the automatic driving program.

Specifically, in an embodiment, the obtaining module is specifically configured to:

and acquiring the vehicle drive test data based on the PCIe interface.

Specifically, in an embodiment, the autopilot program includes a perception domain model and a decision domain model, and the optimization module is specifically configured to:

Specifically, in an embodiment, the on-board sensor port data includes lidar data, and the optimization module is specifically configured to:

Specifically, in an embodiment, the optimization module is specifically configured to:

Specifically, in an embodiment, the on-board sensor port data includes image data, and the optimization module is specifically configured to:

Specifically, in one embodiment, the on-board domain controller is provided with a Fakra interface; the optimizing module is specifically used for:

Specifically, in one embodiment, the image data includes MIPI data and image control signals.

Specifically, in an embodiment, the image sensor module or the vehicle-mounted domain controller includes an image signal processor, and the optimization module is further configured to:

when the vehicle-mounted domain controller comprises an image signal processor, the deserialized MIPI data is preprocessed according to the image control signal based on the image signal processor.

Specifically, in an embodiment, the on-board sensor port data includes millimeter wave radar data, and the optimization module is specifically configured to:

The specific manner in which the respective modules perform the operations in the on-vehicle domain controller program optimizing apparatus in the present embodiment has been described in detail in the embodiments concerning the system, and will not be explained in detail here.

The method for executing the program optimizing device for the vehicle-mounted domain controller provided by the embodiment of the application has the same implementation mode and principle and is not repeated.

An embodiment of the present application provides a vehicle, as shown in fig. 15, which is a schematic structural diagram of the vehicle provided in the embodiment of the present application, including: the vehicle body and the on-board domain controller program optimizing system provided by the embodiment above.

The vehicle provided by the embodiment of the application has the advantages that the drive test data is reproduced and the drive test data signal source consistent with the signal interface of the vehicle-mounted sensor is provided, so that the sensing signal of the drive test data connected to the vehicle-mounted domain controller has the same effect as the access of the vehicle-mounted sensor, namely, the drive test data of the vehicle is converted into the port data of the vehicle-mounted sensor readable by the vehicle-mounted domain controller, the vehicle-mounted domain controller can perform iterative optimization of a program locally, and the optimization efficiency of the program of the vehicle-mounted domain controller is improved. And in addition, the vehicle drive test data acquisition support storage equipment and network acquisition of the simulation data signal source can form an automatic driving perception and decision system with the vehicle-mounted domain controller in a laboratory environment, so that the performance and algorithm of the vehicle-mounted domain controller are optimized in a semi-physical simulation mode, and the problem is solved intensively by research personnel. And the development cost of the system is far lower than the test cost of the drive test vehicle.

The embodiment of the application provides an electronic device for executing the vehicle-mounted domain controller program optimization method provided by the embodiment.

Fig. 16 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 150 includes: at least one processor 151 and a memory 152.

The memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, causing the at least one processor to perform the on-board domain controller program optimization method as provided by the embodiments above.

The processor may be a central processor, a network processor, or a combination thereof. Wherein the processor may further comprise a hardware chip. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.

Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method for implementing the embodiments described above.

The memory may include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store data created from the use of the computer device of the presentation of a sort of applet landing page, and the like. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory may optionally include memory located remotely from the processor, the remote memory being connectable to the computer device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory may also comprise a combination of the above types of memories.

The implementation manner and principle of the electronic device provided by the embodiment of the present application are the same, and are not repeated.

The embodiment of the application provides a computer readable storage medium, wherein computer execution instructions are stored in the computer readable storage medium, and when a processor executes the computer execution instructions, the method for optimizing the vehicle-mounted domain controller program provided by any embodiment is realized.

The storage medium containing computer executable instructions in the embodiments of the present application may be used to store the computer executable instructions of the vehicle-mounted domain controller program optimization method provided in the foregoing embodiments, and the implementation manner and principle of the implementation are the same, and are not repeated.

In the several embodiments provided by the present application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.

The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform part of the steps of the methods according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. The specific working process of the above-described device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.

Claims

1. An on-board domain controller program optimization system, comprising: a simulated data signal source and an on-board domain controller;

2. The system of claim 1, wherein the simulated data signal source comprises: an optical network interface, a hard disk interface and a PCIe interface;

the simulation data signal source is specifically used for:

3. The system according to claim 1, wherein the autopilot program comprises a perception domain model and a decision domain model, the onboard domain controller being specifically configured to:

4. The system of claim 1, wherein the in-vehicle sensor port data comprises lidar data, and the simulation data signal source comprises: a main control chip;

5. The system of claim 4, wherein the master control chip is provided with an SGMII interface; the simulation data signal source also comprises a traditional Ethernet PHY chip;

6. The system of claim 4, wherein the master control chip is provided with an SMI interface; the simulation data signal source also comprises a vehicle-mounted Ethernet PHY chip;

7. The system of claim 1, wherein the in-vehicle sensor port data comprises image data and the simulated data signal source comprises an image sensor module;

8. The system of claim 7, wherein the on-board domain controller is provided with a Fakra interface;

9. The system of claim 7, wherein the image sensor module comprises a serializer and the on-board domain controller comprises a deserializer.

10. The system of claim 9, wherein the source of analog data signals comprises an FPGA, and wherein the serializer is coupled to an MIPI interface of the FPGA;

The image data includes MIPI data and an image control signal.

11. The system of claim 10, wherein the image sensor module or the on-board domain controller comprises an image signal processor;

12. The system of claim 10, wherein the image control signal comprises a trigger signal sent by the serializer, the trigger signal for specifying an image frame.

13. The system of claim 1, wherein the in-vehicle sensor port data comprises millimeter wave radar data, and the simulated data signal source comprises: a CAN physical layer transceiver;

14. The system of claim 1, wherein the vehicle drive test data comprises at least current vehicle measured data, drive test vehicle measured data, and front and rear vehicle measured data;

15. The system of claim 1, wherein the source of dummy data signals comprises memory particles and solid state storage.

16. An on-board domain controller program optimization method, comprising:

acquiring vehicle drive test data;

converting the vehicle drive test data into vehicle-mounted sensor port data;

17. An on-board domain controller program optimizing apparatus, comprising:

the acquisition module is used for acquiring vehicle drive test data;

18. A vehicle, characterized by comprising: a vehicle body and in-vehicle domain controller program optimization system according to any one of claims 1 to 15.

19. An electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the method of claim 16.

20. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor implement the method of claim 16.