Autonomous driving development method and autonomous driving development platform

Abstract

Provided in the present application are an autonomous driving development method and an autonomous driving development platform. The method comprises: providing a first interface and a second interface, wherein the first interface is used for connecting to sensor systems and a chassis drive-by-wire system of a vehicle, and the second interface is used for connecting to a development and application system of the vehicle; on the basis of the first interface, receiving operating state information of a vehicle and drive control information thereof, wherein the operating state information of the vehicle is collected by means of various sensor systems mounted on the vehicle, and the drive control information of the vehicle is collected by means of the chassis drive-by-wire system mounted on the vehicle; and parsing the operating state information of the vehicle and the drive control information thereof, so as to realize unified information conversion between the first interface and the second interface, wherein the parsed operating state information of the vehicle and the parsed drive control information thereof are used by a user to develop an autonomous driving path of the vehicle on the development and application system of the vehicle. The autonomous driving development platform provided in the present application uses a standardized development method, thereby eliminating the need to take into account the issues regarding service scenarios and vehicle model capabilities.

Description

Autonomous driving development methodologies and platforms

[0001] This application claims priority to Chinese Patent Application No. 202411412826.9, filed on October 10, 2024, entitled "Autonomous Driving Development Method and Autonomous Driving Development Platform", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of autonomous driving technology, and in particular to an autonomous driving development method and an autonomous driving development platform. Background Technology

[0003] With the introduction of the concept of driverless cars, autonomous driving technology has been continuously developed, especially in mining and port business scenarios. Mining has complex terrain, and port operations have high requirements for accuracy and driving skills. Therefore, these two scenarios are more suitable for the application of autonomous driving technology.

[0004] However, current autonomous driving development is based on customized development for different vehicle models. When dealing with various business scenarios and types, the API capabilities of different vehicle models are not standardized. Technical developers need to adapt the chassis drive-by-wire, traffic control, perception, and equipment control (lifting, lowering, photography, alignment) of numerous vehicle models, resulting in a large workload, long adaptation time, and low development efficiency for autonomous driving software. Furthermore, the diverse nature of operational types limits the standardized development of autonomous driving software. Software business logic requires customized development, and software engineers need to understand the business scenarios before developing functional logic, significantly restricting development efficiency and the speed of autonomous driving business advancement. Summary of the Invention

[0005] This application provides an autonomous driving development method and an autonomous driving development platform. The autonomous driving development platform adopts a standardized development approach, eliminating the need to consider business scenarios and vehicle capabilities. It can quickly develop autonomous driving software for different business scenarios, thereby improving the efficiency of autonomous driving software development.

[0006] Firstly, this application provides an autonomous driving development method. This method is applied to an autonomous driving development platform, which is used by users to develop general-purpose autonomous driving software for different vehicle models. The method includes providing a first interface and a second interface. The first interface is used to connect to the vehicle's sensor system and chassis drive-by-wire system, and the second interface is used to connect to the vehicle's development application system. Based on the first interface, the method receives vehicle operating status information and drive control information. The vehicle operating status information is collected through various sensor systems installed on the vehicle, and the vehicle drive control information is collected through the chassis drive-by-wire system installed on the vehicle. The method parses the vehicle operating status information and drive control information to achieve unified information conversion between the first and second interfaces. The parsed vehicle operating status information and drive control information are used by the user to develop autonomous driving paths for the vehicle on the vehicle's development application system.

[0007] Based on the above method, the autonomous driving development platform establishes a unified interface relationship with the vehicle through a first interface, and receives the vehicle's operating status information and drive control information through the first interface. The autonomous driving development platform also establishes a unified interface relationship with the vehicle's development application system through a second interface. By parsing the vehicle's operating status information and drive control information, a unified information conversion between the first and second interfaces is achieved. This allows users to use the parsed vehicle operating status information and drive control information to develop autonomous driving paths for the vehicle on the vehicle's development application system. When developing autonomous driving paths for the vehicle on the vehicle's development application system, users do not need to consider the vehicle type, thus improving the efficiency of autonomous driving development.

[0008] In one possible implementation of the first aspect, the vehicle's operating status information and drive control information are parsed to achieve unified information conversion between the first interface and the second interface. Specifically, this includes: generating a set of vehicle motion states based on the operating status information, and generating a set of vehicle first interface information based on the drive control information; generating a first mapping relationship between the set of motion states and the set of first interface information; and generating a third mapping relationship between the second interface information set and the first interface information set based on a predefined second mapping relationship between the second interface information set and the set of motion states, so as to achieve unified information conversion between the first interface and the second interface.

[0009] Based on the above method, the motion state set generated by the motion state information can be used as an intermediate medium to realize the unified information conversion between the first interface and the second interface. The motion state information of the vehicle is an important indicator of the vehicle's motion. Using it as an intermediate medium for the unified information conversion between the first interface and the second interface is beneficial to the user's understanding and operation in the unified information conversion process.

[0010] In one possible implementation of the first aspect, the predefined second interface information set includes a longitudinal control interface, a lateral control interface, and a single-point control interface for the vehicle. The longitudinal control interface is used to control the vehicle's driving and / or stopping operations, the lateral control interface is used to control the vehicle's driving direction operations, and the single-point control interface is used to control the operation of vehicle-related accessories.

[0011] Based on the above method, the predefined second interface information set includes the operation of controlling the vehicle's driving and / or stopping, as well as the operation of related accessories, which facilitates the development and operation of the vehicle's driving path when users develop the vehicle's autonomous driving path on the vehicle's development application system.

[0012] In one possible implementation of the first aspect, the method further includes: storing vehicle operating status information and drive control information; filtering the vehicle operating status information and drive control information to remove invalid information and obtain valid information; parsing the valid information in the vehicle operating status information and drive control information to achieve unified information conversion between the first interface and the second interface; using the parsed valid information in the vehicle operating status information and drive control information for users to develop autonomous driving paths for the vehicle in the vehicle development application system; simulating the autonomous driving path of the vehicle after development; and testing the simulated autonomous driving path of the vehicle.

[0013] Based on the above methods, the autonomous driving development platform can also store vehicle operating status information and drive control information, filter out invalid information, and retain valid information to facilitate users in developing autonomous driving paths for vehicles on the vehicle development application system. The function of filtering valid information makes the data used in development more accurate and timely. At the same time, the pre-storage method also allows users to simulate and test after completing their own driving path development, making the autonomous driving path development function more comprehensive.

[0014] In one possible implementation of the first aspect, the method further includes: receiving vehicle task execution information, wherein the vehicle task execution information is obtained by the user performing vehicle task orchestration on the vehicle's development application system, the vehicle task orchestration is based on the vehicle's task type and vehicle task flow, the vehicle's task type is used to indicate the type of task performed by the vehicle, and the vehicle's task flow is used to indicate the complexity of the task performed by the vehicle; and parsing the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0015] Based on the above methods, the autonomous driving development platform will also analyze the task execution information of the vehicle developed by the user to obtain the autonomous driving path of the vehicle. In the development of the autonomous driving path of the vehicle, the user can reasonably plan and arrange the autonomous driving path of the vehicle based on the task type and task flow of the vehicle.

[0016] In one possible implementation of the first aspect, the method further includes: receiving vehicle task execution information, wherein the vehicle task execution information is obtained by the user performing vehicle task orchestration on the vehicle's development application system, the vehicle task orchestration is based on the vehicle's hardware capability information, the vehicle's hardware capability information includes the vehicle's chassis information and the vehicle's sensor information, the vehicle's chassis information is used to indicate the vehicle's performance information for performing tasks, and the vehicle's sensor information is used to indicate the vehicle's sensitivity information for performing tasks; and parsing the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0017] Based on the above methods, the autonomous driving development platform will also analyze the task execution information of the vehicle developed by the user to obtain the autonomous driving path of the vehicle. In the development of the autonomous driving path of the vehicle, the user can reasonably plan and arrange the autonomous driving path of the vehicle based on the vehicle's hardware capability information and chassis information.

[0018] In one possible implementation of the first aspect, the sensor includes one or more of lidar, millimeter-wave radar, and cameras.

[0019] Based on the above method, the sensor device provided in this application includes one or more of a variety of devices, which can better complete the data collection during vehicle driving, making the collected data more comprehensive and accurate, and facilitating the user to develop autonomous driving paths for the vehicle in the subsequent development and application system of the vehicle.

[0020] Secondly, this application also provides an autonomous driving development platform for users to develop universal autonomous driving software for different vehicle models. The platform includes: an interface providing module for providing a first interface and a second interface, the first interface for connecting to the vehicle's sensor system and chassis drive-by-wire system, and the second interface for connecting to the vehicle's development application system; an information receiving module for receiving vehicle operating status information and drive control information based on the first interface, wherein the vehicle operating status information is collected through various sensor systems installed on the vehicle, and the vehicle drive control information is collected through the chassis drive-by-wire system installed on the vehicle; and an information conversion module for converting vehicle... The system parses the vehicle's operating status information and drive control information, achieving unified information conversion between the first and second interfaces. The parsed vehicle operating status information and drive control information are used by users to develop autonomous driving paths for the vehicle in the vehicle's development application system. The information processing module stores the vehicle's operating status information and drive control information, filters out invalid information from the vehicle's operating status information and drive control information, and obtains the valid information from the vehicle's operating status information and drive control information. The simulation testing module is used to simulate the autonomous driving path of the vehicle after development and to test the simulated autonomous driving path of the vehicle.

[0021] The second aspect or any implementation thereof is a step implementation of the apparatus corresponding to the first aspect or any implementation thereof. The description in the second aspect or any implementation thereof applies to the first aspect or any implementation thereof, and will not be repeated here.

[0022] Thirdly, this application provides a computing device cluster including at least one computing device, each computing device including a processor and a memory. The processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the methods disclosed in the first aspect and any possible implementation thereof.

[0023] Fourthly, this application provides a computer program product containing instructions that, when executed by a cluster of computer devices, cause the cluster of computer devices to implement the method disclosed in the first aspect and any possible implementation of the first aspect.

[0024] Fifthly, this application provides a computer-readable storage medium including computer program instructions that, when executed by a cluster of computing devices, cause the cluster of computing devices to perform the method disclosed in the first aspect and any possible implementation thereof. Attached Figure Description

[0025] Figure 1 is a schematic diagram of an architecture of the autonomous driving development platform according to an embodiment of the present invention;

[0026] Figure 2 is a schematic diagram of another architecture of the autonomous driving development platform according to an embodiment of the present invention;

[0027] Figure 3 is a flowchart illustrating an autonomous driving development method according to an embodiment of the present invention;

[0028] Figure 4a is a schematic diagram of the message module of the first interface of an autonomous driving development method according to an embodiment of the present invention.

[0029] Figure 4b is a schematic diagram of the control module of the first interface of an autonomous driving development method according to an embodiment of the present invention.

[0030] Figure 5a is a schematic diagram of the second interface of an autonomous driving development method according to an embodiment of the present invention;

[0031] Figure 5b is a schematic diagram of the message module of the second interface of an autonomous driving development method according to an embodiment of the present invention.

[0032] Figure 5c is a schematic diagram of the control module of the second interface of an autonomous driving development method according to an embodiment of the present invention.

[0033] Figure 6a is a schematic flowchart of a simple task orchestration method for an autonomous driving development method according to an embodiment of the present invention;

[0034] Figure 6b is a flowchart illustrating the complex task orchestration of an autonomous driving development method according to an embodiment of the present invention;

[0035] Figure 7 is a schematic diagram of an autonomous driving development platform according to an embodiment of the present invention;

[0036] Figure 8 is a schematic diagram of the computing device structure of the autonomous driving development method according to an embodiment of the present invention;

[0037] Figure 9 is a schematic diagram of the structure of the computing device cluster of the autonomous driving development method according to an embodiment of the present invention;

[0038] Figure 10 is a schematic diagram of the structure of a computing device cluster in another autonomous driving development method according to an embodiment of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0040] To facilitate understanding of the embodiments of the present invention, some of the terms involved in the present invention will first be explained.

[0041] Autonomous Driving System: The autonomous driving system employs advanced communication, computer, network, and control technologies to achieve real-time, continuous control of the vehicle. Utilizing modern communication methods, it directly interacts with the vehicle, enabling two-way data communication between the vehicle and the ground. This results in high transmission speeds and large data volumes, allowing the tracking vehicle and control center to promptly obtain the vehicle's precise location. This makes operation management more flexible, control more effective, and better suited to the needs of autonomous driving.

[0042] The car chassis, a crucial component of a vehicle, bears the engine and other important parts, shaping the overall form of the car. It receives power from the engine to propel the car, ensuring smooth driving. The chassis mainly consists of four systems: the transmission system, the running system, the steering system, and the braking system. The transmission system, including the clutch, gearbox, universal joint, final drive, differential, and half-shafts, is responsible for smoothly and efficiently transmitting the engine's power to the wheels. The clutch engages and disengages power, ensuring smooth starting and gear shifting; the gearbox changes the gear ratio, enabling neutral and reverse functions; the universal joint transmits power between intersecting shafts with varying relative positions; the final drive changes the direction of power transmission and provides a uniform gear ratio for each gear; the differential adjusts the speed difference between the left and right wheels; and the half-shafts transmit the differential's power to the drive wheels. The running system consists of the frame, axles, wheels, and suspension. The chassis, as the skeleton of a car, supports all assemblies and bears internal and external loads; the axles bear the weight of the car and maintain driving stability; the wheels bear the entire weight of the car and absorb vibrations and impacts during driving, protecting car parts from damage; the suspension connects the wheels and the chassis, transmitting torque and damping vibrations. The steering system, mainly composed of the steering wheel, steering shaft, and steering column, is responsible for controlling the car's direction of travel. The steering wheel converts the driver's torque into the rotation of the steering shaft, thus controlling the steering of the wheels; the steering shaft transmits the torque of the steering wheel; the steering column transmits steering force and angle, improving the car's handling and safety. The braking system, including brake discs, brake pads, master cylinder, wheel cylinders, and brake pedal, is responsible for reducing vehicle speed or stopping. The brake discs and brake pads reduce vehicle speed through friction; the master cylinder controls the overall operation of the braking system; the wheel cylinders use the force transmitted by the master cylinder to push the brake pads into contact with the brake discs, achieving the braking effect; the brake pedal is operated by the driver to control the car's deceleration and stopping.

[0043] Controller Area Network (CAN) bus: A serial communication protocol bus used for real-time applications. It uses twisted-pair cables to transmit signals and is one of the most widely used fieldbuses in the world. The CAN protocol is used for communication between various components in automobiles, replacing expensive and bulky wiring harnesses. Its robustness extends its applications to other automation and industrial applications. Features of the CAN protocol include complete serial data communication, real-time support, transmission rates up to 1 Mb / s, 11-bit addressing, and error detection capabilities.

[0044] User Datagram Protocol (UDP) is a datagram-based protocol that provides packet-switched computer communication in an interconnected network environment. It assumes IP as the underlying protocol and operates at the transport layer according to the OSI model. UDP provides applications with a minimal protocol mechanism for sending messages to other programs. It is transaction-oriented and does not guarantee delivery or deduplication. Applications requiring ordered and reliable data streams should use Transmission Control Protocol (TCP).

[0045] Independent software vendors (ISVs) are companies that specialize in the development, production, sales, and service of software. They primarily target large-scale or niche markets. Such markets can be very broad, including real estate brokerage software, healthcare, barcode scanning, stock trading software, and even child health management software.

[0046] Odometry is a technique for calculating changes in the pose of a mobile robot or vehicle. It estimates the distance traveled and changes in direction by measuring wheel rotation or sensor data. The initial concept originated from the mechanical odometer in automobiles, used to accumulate the total distance traveled. In robotics and autonomous driving, odometry specifically refers to the continuous estimation of a robot's position and orientation relative to its starting point using sensors such as wheel encoders, LiDAR, and vision cameras. Wheel odometry is the most basic form, relying on wheel speed and vehicle geometry to calculate displacement, but it can drift due to uneven ground or tire slippage. LiDAR odometry uses LiDAR data to accurately measure environmental changes, thereby calculating pose, providing more accurate location information and assisting in building environmental maps, but it faces challenges in dynamic obstacle and occluded environments. In modern applications, different types of odometry (such as laser, vision, and inertial odometry) are often combined with SLAM (simultaneous localization and mapping) technology to reduce errors and achieve global consistency.

[0047] In this embodiment of the invention, the autonomous driving platform can provide users with general autonomous driving software for different vehicle models. Specifically, this embodiment of the invention provides an autonomous driving development method. The following describes relevant embodiments of the autonomous driving development method provided by this invention in conjunction with the above basic concepts.

[0048] Please refer to Figure 1 below. Figure 1 is a schematic diagram of the architecture of an autonomous driving development platform according to an embodiment of the present invention. In the embodiment shown in Figure 1, the autonomous driving development platform 10 includes an ISV vehicle-side application 11, a vehicle-side autonomous driving software runtime platform 12, a chassis drive-by-wire module 13, a perception module 14, and a positioning module 15. The ISV vehicle-side application 11, the vehicle-side autonomous driving software runtime platform 12, the chassis drive-by-wire module 13, the perception module 14, and the positioning module 15 all run in software form on the autonomous driving development platform 10. Specifically, the system base of the autonomous driving development platform is a Windows system base or a Linux system base.

[0049] Specifically, users can develop autonomous driving software on the autonomous driving development platform 10 through the ISV vehicle application 11; the vehicle chassis is connected to the chassis drive-by-wire module 13 through different chassis protocols. Specifically, different car manufacturers produce car chassis with different chassis protocols. Therefore, the vehicle chassis will connect to the chassis drive-by-wire module using the chassis protocol adapted to the car manufacturer. At the same time, the vehicle chassis communicates with the chassis drive-by-wire module 13 for data transmission using the communication protocol of the CAN bus 16.

[0050] Specifically, the sensing module 14 is connected to various sensors. Among them, the lidar communicates with the sensing module 14 via UDP protocol, the millimeter-wave radar communicates via millimeter-wave protocol, and the camera communicates via camera protocol. Both the millimeter-wave radar and the camera communicate with the sensing module 14 via the CAN bus 16 communication protocol. It should be noted that the sensors connected to the sensing module 14 described above are one possible embodiment of the present invention. In other embodiments, the sensors connected to the sensing module 14 can be other types of sensors. The present invention does not limit the type of sensors connected to the sensing module 14.

[0051] Specifically, the combined positioning device is connected to the positioning module 15 via a combined positioning protocol. Combined positioning integrates multiple positioning devices to achieve precise vehicle positioning. The combined positioning device can be a combination of a Global Navigation Satellite System (GNSS) and an Inertial Navigation System (INS). Global positioning is achieved through GNSS technology, and calibration is performed through INS. Combining these two navigation systems allows for maintaining a certain level of positioning accuracy even when GNSS signals are lost. It should be noted that the combined positioning device connected to the positioning module 15 described above is one possible embodiment of the invention. In other embodiments, the combined positioning device connected to the positioning module 15 can be other types of positioning devices, such as odometers, high-precision maps, etc. The present invention does not limit the type of combined positioning device connected to the positioning module 15.

[0052] Specifically, the autonomous driving development platform 10 provides a unified interface for vehicles of different models. Users can use this unified interface to collect vehicle operation data based on the chassis drive-by-wire module 13, perception module 14 and positioning module 15, and develop autonomous driving services on the autonomous driving development platform 10 through interface conversion.

[0053] Please refer to Figure 2 below. Figure 2 is a schematic diagram of another architecture of the autonomous driving development platform according to an embodiment of the present invention. In the embodiment shown in Figure 2, the autonomous driving development platform 20 includes an ISV vehicle-side application 21, a vehicle-side autonomous driving software runtime platform 22, a chassis drive-by-wire module 23, a perception module 24, a positioning module 25, a data storage device 26, and an ISV cloud application 27. The ISV vehicle-side application 21, the vehicle-side autonomous driving software runtime platform 22, the chassis drive-by-wire module 23, the perception module 24, and the positioning module 25 all run in software form on the autonomous driving development platform 20. Specifically, the system base of the autonomous driving development platform is a Windows system base or a Linux system base.

[0054] Specifically, users can collect vehicle operation data through the chassis drive-by-wire module 23, perception module 24, and positioning module 25, and store the operation data in the data storage device 26. During the development of autonomous driving services, historical vehicle operation data stored in the data storage device 26 can be retrieved, and this historical data can be used to simulate autonomous driving development based on the vehicle's autonomous driving services. The simulated autonomous driving services can then be tested, and the tested autonomous driving operation path can be sent to the vehicle. Specifically, the chassis drive-by-wire module 23 is connected to the vehicle's chassis, the perception module 24 is connected to various sensors, and the positioning module 25 is connected to the combined positioning device. The specific connection methods are similar to those in Figure 1 and will not be repeated here.

[0055] Specifically, when users develop autonomous driving services on the autonomous driving development platform 10, they can also utilize cloud resources, such as uploading vehicle operation data to the ISV cloud application 27 for autonomous driving service development. The ISV cloud application 27 can fully utilize cloud computing power to develop autonomous driving services through data storage, data mining, and data analysis, and then distribute the developed autonomous driving operation path to the vehicle.

[0056] It should be noted that the autonomous driving development platform 10 in Figure 1 can collect vehicle operation data in real time and use the collected data for real-time development. The autonomous driving development platform 20 in Figure 2 first stores the vehicle operation data in a data storage device, and then uses the autonomous driving development platform 20 or the ISV cloud application 27 to perform data simulation and testing for autonomous driving development. The autonomous driving business development method in Figure 1 is suitable for the development of vehicle autonomous driving services with low computing power requirements, simple tasks, and high requirements for vehicle operation timeliness. The autonomous driving business development method in Figure 2 is suitable for the development of vehicle autonomous driving services with high computing power requirements, complex tasks, and lower requirements for vehicle operation timeliness.

[0057] Based on the architecture of the autonomous driving development platform provided above, this embodiment of the invention further discloses an autonomous driving development method, as shown in Figure 3, which is a flowchart of an autonomous driving development method according to an embodiment of the invention. This embodiment of the invention provides an autonomous driving development method applied to an autonomous driving development platform. This platform is used by users to develop universal autonomous driving software for different vehicle models. The method includes:

[0058] S101: The autonomous driving development platform 10 provides a first interface and a second interface.

[0059] In step S101, the autonomous driving development platform 10 provides a first interface and a second interface. The first interface is used to connect with the vehicle's sensor system and chassis drive-by-wire system, and the second interface is used to connect with the vehicle's development application system. Because existing autonomous driving development platforms require customized development for different vehicle types, and because different vehicles have different chassis protocols for connecting their chassis drive-by-wire systems to the autonomous driving development platform, development difficulty increases. The autonomous driving development platform of this invention provides a unified first interface to the vehicle's chassis drive-by-wire system and a unified second interface to the vehicle's development application system, effectively solving the problem of customized development for different vehicle types.

[0060] S102: Sensor system 20 sends vehicle operating status information to the first interface, and chassis drive-by-wire system 30 sends vehicle drive control information to the first interface.

[0061] In step S102, the autonomous driving development platform 10 receives the vehicle's operating status information and drive control information based on the first interface. The vehicle's operating status information is collected by a variety of sensor systems 20 installed on the vehicle, and the vehicle's drive control information is collected by a chassis drive-by-wire system 30 installed on the vehicle.

[0062] Specifically, in the development of autonomous driving, it is necessary to collect vehicle operation data. This data includes two parts: vehicle operation status information and drive control information. The vehicle's motion status information is collected through various sensor systems 20 installed on the vehicle, such as one or more of LiDAR, millimeter-wave radar, and cameras. This motion status information includes a set of vehicle motion state variables. As shown in Figure 4a, which is a schematic diagram of the message module of the first interface of an autonomous driving development method according to an embodiment of the present invention, the first interface includes a standardized sensor message receiving module that can adapt to various sensors installed on the vehicle. As shown in Figure 4a, the first interface is configured to include a message module for receiving vehicle status quantities. The related modules of the message module include chassis, body, and faults. The sub-modules of the chassis module include longitudinal correlation and lateral correlation. In the longitudinal correlation sub-module, the vehicle message frequencies covered include vehicle gear position, electronic parking brake status, vehicle speed, and hydraulic emergency brake feedback. In the lateral correlation sub-module, the vehicle message frequencies covered include steering wheel angle and front wheel angle. The sub-modules of the body module include lighting-related modules. In the lighting-related sub-module, the vehicle message frequencies covered include left turn signal, right turn signal, and hazard lights. The sub-modules of the fault module include fault-related modules. In the fault-related sub-module, the fault level and fault code are covered. In the lifting sub-module, the vehicle message frequencies covered include cargo box angle. Each message frequency of the above vehicles corresponds to its own code parameter name. At the same time, since the vehicle motion state information collected by the sensors is transmitted through the CAN bus protocol, the parameters in each sub-module of the message module also correspond to information such as ID, start bit, bit width, precision, offset, meaning, and Hz in the CAN bus protocol.

[0063] For example, in the lateral related submodule of the chassis module related to the message module, the parameter name of the steering wheel angle is defined as steer_angle_status. Its corresponding ID in the CAN bus protocol is 0x28FED2A1, the start bit is 0, the bit width is 16, the precision is 0.1, the offset is -2000, the meaning is positive on the left and negative on the right, and the unit is deg.

[0064] It should be noted that the types of sensors mentioned here are merely examples. In other possible implementations, the sensors installed on the vehicle can be other types of sensors. There is no limitation on the types of sensors here.

[0065] Specifically, the vehicle's drive control information is collected through the chassis drive-by-wire system 30 installed on the vehicle. As shown in Figure 4b, which is a schematic diagram of the control module of the first interface of an autonomous driving development method according to an embodiment of the present invention, the first interface includes a standardized chassis drive-by-wire interface, which can adapt to the chassis of different vehicle models. As shown in Figure 4b, the first interface is set as a control module including control quantities. The sub-modules of the control module can include longitudinal, lateral, lighting, and lifting parameters. In the longitudinal sub-module, the vehicle parameters covered include electronic parking brake, target gear, accelerator pedal opening, deceleration, and emergency braking. In the lateral sub-module, the vehicle parameters covered include steering wheel angle and front wheel angle. In the lighting sub-module, the vehicle parameters covered include left turn signal, right turn signal, and hazard lights. In the lifting sub-module, the vehicle parameters covered include lifting, which includes raising, lowering, and holding of vehicle components. The various parameter names for the vehicle mentioned above correspond to their respective code parameter names. Furthermore, since the control information of the vehicle chassis is transmitted via the CAN bus protocol, the parameters within each submodule of the control module also correspond to information such as ID, start bit, bit width, precision, offset, meaning, and unit in the CAN bus protocol. For example, in the longitudinal submodule of the control module, the parameter defining the accelerator pedal opening is named `acc_pedal_percentage`. Its corresponding CAN bus protocol ID is 0x28FFD2A3, start bit is 16, bit width is 8, precision is 0.4, offset is 0, meaning is 0~100, and unit is %.

[0066] It should be noted that the above configuration of the first interface for collecting vehicle operation data is only one example in this application. In other possible implementations, the module settings of the first interface, the parameter settings of the sub-modules in the related modules, and the information settings corresponding to the CAN bus protocol may be other. Here, the content of the standardized interface settings of the first interface is not limited.

[0067] S103: The autonomous driving development platform 10 parses the vehicle's operating status information and drive control information, and sends the parsed vehicle operating status information and drive control information to the development application system 40. The development application system 40 uses the vehicle's operating status information and drive control information to develop the vehicle's autonomous driving path.

[0068] In step S103, the autonomous driving development platform 10 parses the vehicle's operating status information and drive control information to achieve unified information conversion between the first interface and the second interface. Specifically, this includes: generating a set of vehicle motion states based on the operating status information, and generating a set of vehicle first interface information based on the drive control information; generating a first mapping relationship between the set of motion states and the set of first interface information; and generating a third mapping relationship between the second interface information set and the first interface information set based on a predefined second mapping relationship between the second interface information set and the set of motion states, so as to achieve unified information conversion between the first interface and the second interface.

[0069] Specifically, in step S102, the autonomous driving development platform 10 captures the vehicle's motion state through sensors installed on the vehicle via the first interface. In step S103, the motion state is abstracted to include longitudinal velocity v, longitudinal acceleration a, steering angle α, and vehicle body movement. and the set of motion states at Greenwich Mean Time t Simultaneously, the autonomous driving development platform 10 collects and parses CAN messages, generating a CAN interface set F(can,T) = 0, where T is Greenwich Mean Time. Here, the CAN message refers to the vehicle chassis control information transmitted to the autonomous driving platform 10 in step S102 via the CAN bus protocol. Further, the autonomous driving development platform 10 generates a mapping relationship between the CAN interface set and the motion state set. Meanwhile, the autonomous driving platform 10 also provides a second interface for connecting with the vehicle's development application system. This predefined second interface includes the relationship between the autonomous driving platform 10 and the vehicle's motion state set. Therefore, the mapping relationship between the CAN message interface and the motion state set can be used... Generate a mapping relationship between the second interface and the CAN message interface to realize the mapping conversion between the second interface and the CAN message interface, that is, to realize the unified conversion of information between the first interface and the second interface.

[0070] The autonomous driving platform 10 predefined second interface information set includes the vehicle's longitudinal control interface, lateral control interface, and single-point control interface. The longitudinal control interface is used to control the vehicle's driving and / or stopping operations, the lateral control interface is used to control the vehicle's driving direction operations, and the single-point control interface is used to control the operation of vehicle-related accessories. Specifically, as shown in Figure 5a, it is a schematic diagram of the second interface of an autonomous driving development method according to an embodiment of the present invention. To facilitate users in developing autonomous driving paths for vehicles on the vehicle development application system 40, the autonomous driving platform 10 provides a second interface, which includes a standardized vehicle development application system 40 interface, as shown in Figure 5a, abstracting vehicle control into longitudinal and lateral control, and single-point control of vehicle components.

[0071] The longitudinal control interface includes:

[0072] int32_t SetCarGear(uint8_t nCarGear); int32_t SetAEBDemand(uint8_t nDemand);

[0073] int32_t SetAcceleratedVelocity(uint8_t nAcceleratedVelocity);

[0074] The lateral control interface includes:

[0075] int32_t SetAngularVelocity(uint16_t nAngularVelocity); int32_t SetAngular(uint16_t nAngular);

[0076] Single-point control interfaces include:

[0077] int32_tSetLampOutSideSwitch(uint8_tnArea,uint8_tnSwitch); int32_tSetHornSwitch(uint8_tnSwitch); int32_tSetLiftCmd(uint8_t nLift);

[0078] Specifically, the vehicle's longitudinal control interface is used to control the vehicle's forward, reverse, and stop operations, while the vehicle's lateral control interface is used to control the vehicle's steering operations. The vehicle's single-point control interface includes the vehicle's body control interface and the external device control interface. The vehicle's body control interface is used to control the vehicle's ignition, lifting, lights, and horn, while the vehicle's external device control interface is used to control the vehicle's sensors and remote controls.

[0079] As shown in Figure 5b, which is a schematic diagram of the message module of the second interface of an autonomous driving development method according to an embodiment of the present invention, the second interface is configured to include a message module for receiving vehicle state quantities. The related modules of the message module include chassis, body, and fault information. The chassis module includes sub-modules for longitudinal and lateral correlation. The longitudinal correlation sub-module covers vehicle message frequencies including electronic parking brake status, throttle opening, vehicle speed, wheel speed array, hydraulic emergency brake feedback, and vehicle gear position. The lateral correlation sub-module covers vehicle message frequencies including lateral enable status, steering wheel angle, and front wheel angle. The body module includes sub-modules for lighting-related information, covering vehicle message frequencies including left turn signal, right turn signal, hazard lights, and horn. The fault module includes sub-modules for fault-related information, covering fault level and fault code. The lifting sub-module covers vehicle message frequencies including lifting status and cargo box angle. Each vehicle message frequency corresponds to its own code parameter name, unit, type, and remarks.

[0080] As shown in Figure 5c, which is a schematic diagram of the control module of the second interface of an autonomous driving development method according to an embodiment of the present invention, the second interface is configured as a control module including control quantities. The sub-modules of the control module may include longitudinal, lateral, lighting, and lifting parameters. In the longitudinal sub-module, vehicle parameters include electronic parking brake, target gear, deceleration, accelerator pedal opening, and emergency braking. In the lateral sub-module, vehicle parameters include steering wheel angle and front wheel angle. In the lighting sub-module, vehicle parameters include left turn signal, right turn signal, and hazard lights. In the lifting sub-module, vehicle parameters include lifting, which includes raising, lowering, and holding vehicle components. Each of the vehicle parameter names corresponds to its respective code parameter name, unit, type, and remarks.

[0081] Specifically, the autonomous driving development platform 10 parses the vehicle's operating status information and drive control information based on a unified standardized implementation of the first and second interfaces on the autonomous driving platform 10. The parsed vehicle operating status information and drive control information are then used by users to develop autonomous driving paths for the vehicle on the vehicle's development application system.

[0082] It should be noted that the above-described method for setting the second interface for developing the autonomous driving path of the vehicle on the development application system 40 is only one example in this invention application. In other possible implementations, the module settings of the second interface and the parameter settings of the sub-modules in the related modules may be other. Here, the content of the standardized interface settings of the second interface is not limited.

[0083] S104: The autonomous driving development platform 10 stores the vehicle's operating status information and drive control information, and obtains the effective information from the vehicle's operating status information and drive control information.

[0084] In step S104, the autonomous driving development platform 10 filters the vehicle's operating status information and drive control information, removes invalid information from the vehicle's operating status information and drive control information, obtains valid information from the vehicle's operating status information and drive control information, parses the valid information from the vehicle's operating status information and drive control information, realizes unified information conversion between the first interface and the second interface, and uses the parsed valid information from the vehicle's operating status information and drive control information for users to develop the vehicle's autonomous driving path on the vehicle's development application system 40.

[0085] Specifically, the autonomous driving development platform 10 can process the vehicle's motion status information and drive control information in real time, sending the information to the development application system 40 for users to develop autonomous driving paths. Alternatively, it can store the vehicle's motion status information and drive control information first, filtering out invalid information. For example, in the development of an autonomous driving path, the autonomous driving development platform 10 stores the vehicle's motion status information and drive control information collected over a year. Due to changes in the vehicle's operating environment, it is necessary to filter out invalid information from the vehicle's motion status information and drive control information collected over that year. Or, the autonomous driving development platform 10 stores the motion status information and drive control information of various vehicle models. If some vehicle models have been discontinued or scrapped, it is also necessary to filter out invalid information from the motion status information and drive control information of vehicles that have been discontinued or scrapped.

[0086] Meanwhile, the autonomous driving development platform 10 sends the vehicle's motion status information and drive control information to the development application system 40 in real time for users to develop the vehicle's autonomous driving path. This is suitable for the development of autonomous driving services for vehicles with low computing power requirements, simple tasks, and high timeliness requirements for vehicle operation. The autonomous driving development platform 10 also stores the vehicle's operating status information and drive control information in advance, which is suitable for the development of autonomous driving services for vehicles with high computing power requirements, complex tasks, and low timeliness requirements for vehicle operation.

[0087] S105: Send the parsed vehicle motion state information and valid information from the drive control information to the development application system 40. The development application system 40 uses the vehicle's operating state information and valid information from the drive control to develop the vehicle's autonomous driving path.

[0088] In step S105, the autonomous driving development platform 10 sends the parsed vehicle motion state information and valid information from the drive control information to the development application system 40. The development application system 40 uses the vehicle's operating state information and valid information from the drive control to develop the vehicle's autonomous driving path, which can make the information used in the development of the vehicle's autonomous driving path more accurate and reduce the generation of errors.

[0089] S106: The autonomous driving development platform 10 simulates the autonomous driving path of a vehicle after development is completed, and tests the simulated autonomous driving path of the vehicle.

[0090] In step S106, because the autonomous driving development platform 10 adopts a development method that stores the vehicle's operating status information and drive control information in advance, the platform can first simulate the autonomous driving path of the vehicle after the user has completed the development of the application system 40, and then test the simulated autonomous driving path. This makes the developed autonomous driving path more accurate after simulation and testing. At the same time, new problems may be discovered during the simulation process, allowing users to better identify and improve these problems, accumulating experience in autonomous driving development. Autonomous driving paths that fail the test will not be issued to the vehicle, preventing problematic paths from being sent and causing vehicle task failure or damage to the vehicle itself.

[0091] S107: The autonomous driving development platform 10 receives the task execution information of the side vehicle sent by the development application system 40.

[0092] S108: The autonomous driving development platform 10 parses the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0093] In steps S107-S108, in one possible scenario: the autonomous driving development platform 10 receives the vehicle's task execution information. This information is obtained by the user through task orchestration on the vehicle's development application system. The task orchestration is based on the vehicle's task type and task flow. The task type indicates the type of task the vehicle is performing, and the task flow indicates the complexity of the task. The autonomous driving development platform 10 then parses the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0094] In steps S107-S108, in another possible scenario: the autonomous driving development platform 10 receives the vehicle's task execution information. This information is obtained by the user through task orchestration on the vehicle's development application system. The task orchestration is based on the vehicle's hardware capability information, which includes chassis information and sensor information. The chassis information indicates the vehicle's performance in executing tasks, and the sensor information indicates its sensitivity. The autonomous driving development platform 10 then parses the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0095] During the development of autonomous driving paths for vehicles, users also need to consider the tasks that the vehicles need to perform. Based on a simple task scenario, the task arrangement of the vehicle in the development of autonomous driving paths is shown in Figure 6a. Figure 6a is a flowchart illustrating a simple task arrangement of an autonomous driving development method according to an embodiment of the present invention. As shown in Figure 6a, when a vehicle performs a sweeping task, the task arrangement first needs to consider available online idle vehicles, and then sort the order of the vehicle's operation path according to the sweeping task and route. After the sweeping action starts, the navigation installed on the vehicle is used to detect the trajectory generated by the vehicle when performing the task and to evaluate the vehicle's task execution status. At the same time, if it is detected that the task has not been completed, it is also necessary to trigger a mechanism for the vehicle to repeatedly perform the sweeping task. After it is detected that the vehicle has completed the sweeping task, an instruction is issued to the vehicle to stop the task.

[0096] Figure 6b illustrates the task orchestration process for vehicles in the development of autonomous driving paths for complex tasks, as shown in Figure 6b. Figure 6b is a flowchart illustrating the complex task orchestration process of an autonomous driving development method according to an embodiment of the present invention. As shown in Figure 6b, when a vehicle performs a port operation task, the task orchestration first considers available online idle vehicles. After receiving the unloading task instruction and information such as the target quay crane number and container number, the vehicle executes the unloading task. The navigation system installed on the vehicle detects the trajectory generated during task execution. If the target quay crane number is already occupied, the vehicle needs to wait outside the target quay crane. Simultaneously, during the unloading task, the alignment of the unloading actions needs to be calibrated. After receiving the task execution, a second task, such as a station locking task, needs to be executed. If the station locking is detected as occupied, the vehicle needs to wait outside the station. After the task execution is completed, a third task, such as yard operations, needs to be executed. After the yard operations are completed, all tasks are finished, and an instruction is issued to the vehicle to stop its operation.

[0097] It should be noted that the above user task orchestration process for vehicles is only one possible example of the present invention. The present invention does not limit the user's task orchestration methods for vehicles during autonomous driving development to the above two methods.

[0098] The autonomous driving development method provided by this invention provides a standardized first interface for downstream vehicles to receive vehicle operating status information and drive control information, and a standardized second interface for upstream vehicle development application systems. Simultaneously, the autonomous driving platform performs conversion between the information from the first interface and the information from the second interface. This allows users to develop autonomous driving paths for vehicles without considering business scenarios or vehicle model capabilities when developing application systems, enabling rapid development of autonomous driving software for different business scenarios and improving the efficiency of autonomous driving software development.

[0099] Based on the above-described autonomous driving development method, this embodiment of the invention further discloses an autonomous driving development platform. Figure 7 is a schematic diagram of an autonomous driving development platform 10 according to an embodiment of the invention. As shown in Figure 7, the autonomous driving development platform 10 is used by users to develop universal autonomous driving software for different vehicle models. The autonomous driving development platform 10 includes:

[0100] The interface providing module 101 is used to provide a first interface and a second interface. The first interface is used to connect with the vehicle's sensor system and chassis drive-by-wire system, and the second interface is used to connect with the vehicle's development and application system.

[0101] The information receiving module 102 is used to receive vehicle operating status information and drive control information based on the first interface. The vehicle operating status information is collected by a variety of sensor systems installed on the vehicle, and the vehicle drive control information is collected by a chassis drive-by-wire system installed on the vehicle.

[0102] The information conversion module 103 is used to parse the vehicle's operating status information and drive control information to achieve unified information conversion between the first interface and the second interface. The parsed vehicle operating status information and drive control information are used by users to develop the vehicle's autonomous driving path in the vehicle's development and application system.

[0103] The information processing module 104 is used to store the vehicle's operating status information and drive control information, filter the vehicle's operating status information and drive control information, filter out invalid information in the vehicle's operating status information and drive control information, and obtain the valid information in the vehicle's operating status information and drive control information.

[0104] The simulation test module 105 is used to simulate the autonomous driving path of the vehicle after development is completed, and to test the simulated autonomous driving path of the vehicle.

[0105] The information conversion module 103 is specifically used for: generating a set of vehicle motion states based on operating status information, generating a set of vehicle first interface information based on drive control information; generating a first mapping relationship between the set of motion states and the first interface information set; and generating a third mapping relationship between the second interface information set and the first interface information set based on a predefined second mapping relationship between the second interface information set and the set of motion states, so as to realize unified information conversion between the first interface and the second interface.

[0106] The information processing module 104 is also used to store the vehicle's operating status information and drive control information, filter the vehicle's operating status information and drive control information, filter out invalid information in the vehicle's operating status information and drive control information, and obtain the valid information in the vehicle's operating status information and drive control information.

[0107] The information conversion module 103 is also used to parse the effective information in the vehicle's operating status information and drive control information, realize the unified conversion of information between the first interface and the second interface, and use the parsed effective information in the vehicle's operating status information and drive control information for users to develop the vehicle's autonomous driving path in the vehicle's development and application system.

[0108] The information receiving module 102 is also used to receive vehicle task execution information. The vehicle task execution information is obtained by the user in the vehicle development application system through vehicle task arrangement. The vehicle task arrangement is based on the vehicle task type and the vehicle task flow. The vehicle task type is used to indicate the type of task performed by the vehicle, and the vehicle task flow is used to indicate the complexity of the task performed by the vehicle.

[0109] The information conversion module 103 is also used to parse the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0110] The information receiving module 102 is also used to receive vehicle task execution information. The vehicle task execution information is obtained by the user in the vehicle development application system through vehicle task arrangement. The vehicle task arrangement is based on the vehicle's hardware capability information. The vehicle's hardware capability information includes the vehicle's chassis information and the vehicle's sensor information. The vehicle's chassis information is used to indicate the vehicle's performance information in performing tasks, and the vehicle's sensor information is used to indicate the vehicle's sensitivity information in performing tasks.

[0111] The information conversion module 103 is also used to parse the vehicle's task execution information to obtain the vehicle's autonomous driving path.

[0112] It should be noted that the interface providing module 101, information receiving module 102, information conversion module 103, information processing module 104, and simulation testing module 105 can all be implemented in software or hardware. For example, the implementation of the interface providing module 101 will be described below. Similarly, the implementation of the information receiving module 102, information conversion module 103, information processing module 104, and simulation testing module 105 can refer to the implementation of the interface providing module 101.

[0113] When implemented in software, the interface providing module 101 can be an application or code block running on a computer device. The computer device can be at least one of a physical host, virtual machine, container, or other computing device. Furthermore, the aforementioned computer device can be one or more. For example, the interface providing module 101 can be an application running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the application can be distributed within the same availability zone (AZ) or in different AZs. The multiple hosts / virtual machines / containers used to run the application can be distributed within the same region or in different regions. Typically, a region can include multiple AZs.

[0114] Similarly, multiple hosts / virtual machines / containers used to run the application can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a region can include multiple VPCs, and a VPC can include multiple Availability Zones (AZs).

[0115] When implemented in hardware, the interface providing module 101 may include at least one computing device, such as a server. Alternatively, the cloud resource configuration interface providing module 101 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be implemented using a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0116] The multiple computing devices included in the interface providing module 101 can be distributed within the same Availability Zone (AZ) or in different AZs. Similarly, the multiple computing devices included in the cloud resource configuration interface providing module 101 can be distributed within the same region or in different regions. Likewise, the multiple computing devices included in the interface providing module 101 can be distributed within the same VPC or across multiple VPCs. These multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0117] It should be noted that the interface providing module 101, information receiving module 102, information conversion module 103, information processing module 104, and simulation testing module 105 can all be used to perform some or all of the steps in the neural map construction method.

[0118] The neural map construction device disclosed in this invention has a clear division of labor and close cooperation among its various modules. The modules work together to efficiently complete the construction of neural network maps.

[0119] The present invention also provides a computing device. Please refer to Figure 8 below, which is a schematic diagram of the computing device structure of the autonomous driving development method according to an embodiment of the present invention. The computing device 100 includes: a bus 106, a processor 108, a memory 107, and a communication interface 109. The processor 108, the memory 107, and the communication interface 109 communicate with each other via the bus 106. The computing device 100 can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 100.

[0120] Bus 106 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, only one line is used in Figure 8, but this does not imply that there is only one bus or one type of bus. Bus 106 can include pathways for transmitting information between various components of computing device 100 (e.g., memory 107, processor 108, communication interface 109).

[0121] The processor 108 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0122] Memory 107 may include volatile memory, such as random access memory (RAM). Processor 108 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0123] The memory 107 stores executable program code, which the processor 108 executes to implement the functions of the aforementioned interface providing module 101, information receiving module 102, information conversion module 103, information receiving module 104, and simulation testing module 105, thereby realizing the configuration method for cloud connectivity services based on public cloud. In other words, the memory 107 stores instructions from the cloud management platform for executing the configuration method for cloud connectivity services based on public cloud.

[0124] The communication interface 109 uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between the computing device 100 and other devices or communication networks.

[0125] This invention also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0126] Please refer to Figure 9 below, which is a schematic diagram of the structure of a computing device cluster in the autonomous driving development method according to an embodiment of the present invention. The computing device cluster includes at least one computing device 100. The memory 107 of one or more computing devices 100 in the computing device cluster may store the same instructions for executing the autonomous driving development method.

[0127] In some possible implementations, one or more computing devices 100 in the computing device cluster can also be used to execute some instructions of the autonomous driving development method. In other words, a combination of one or more computing devices 100 can jointly execute the instructions of the autonomous driving development method.

[0128] It should be noted that the memory 107 in different computing devices 100 within the computing device cluster can store different instructions for executing some functions of the autonomous driving development platform. That is, the instructions stored in the memory 107 of different computing devices 100 can implement the functions of one or more modules among the interface providing module 101, information receiving module 102, information conversion module 103, information processing module 104, and simulation testing module 105.

[0129] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc. Figure 10 illustrates one possible implementation. As shown in Figure 10, two computing devices 100A and 100B are connected via a network. Specifically, they are connected to the network through communication interfaces in each computing device. In this type of possible implementation, the memory 107 in computing device 100A stores instructions for performing the functions of the interface providing module 101. Simultaneously, the memory 107 in computing device 100B stores instructions for performing the functions of the information receiving module 102, the information conversion module 103, the information processing module 104, and the simulation testing module 105.

[0130] It should be understood that the functions of computing device 100A shown in Figure 10 can also be performed by multiple computing devices 100. Similarly, the functions of computing device 100B can also be performed by multiple computing devices 100.

[0131] This application also provides another computing device cluster. The connection relationship between the computing devices in this computing device cluster can be similarly referred to the connection method of the computing device clusters in Figures 9 and 10. The difference is that the memory 107 of one or more computing devices 100 in this computing device cluster can store the same instructions for executing autonomous driving development methods.

[0132] In some possible implementations, the memory 107 of one or more computing devices 100 in the computing device cluster may also store partial instructions for executing autonomous driving development methods. In other words, a combination of one or more computing devices 100 can jointly execute instructions for executing autonomous driving development methods.

[0133] This invention also provides a computer program product containing instructions. This computer program product may be a software or program product containing instructions, capable of running on a computing device or stored on any available medium. When this computer program product is run on at least one computer device, it causes the at least one computer device to perform the above-described method for developing autonomous driving.

[0134] This invention also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to execute the above-described method for developing autonomous driving systems.

[0135] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0136] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the raw data and executable code involved in this application were obtained with full authorization.

[0137] In the embodiments of this application, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The term "at least one" refers to one or more, and the term "multiple" refers to two or more, unless otherwise expressly defined.

[0138] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. An autonomous driving development method, characterized in that, The method is applied to an autonomous driving development platform, and the method includes: A first interface and a second interface are provided, wherein the first interface is used to connect to the vehicle's sensor system and chassis drive-by-wire system, and the second interface is used to connect to the vehicle's development and application system. The vehicle's operating status information and drive control information are received based on the first interface. The vehicle's operating status information is collected by a variety of sensor systems installed on the vehicle, and the vehicle's drive control information is collected by a chassis drive-by-wire system installed on the vehicle. The vehicle's operating status information and drive control information are parsed to achieve unified information conversion between the first interface and the second interface. The parsed vehicle operating status information and drive control information are used by the user to develop the vehicle's autonomous driving path on the vehicle's development application system.

2. The method according to claim 1, characterized in that, The step of parsing the vehicle's operating status information and drive control information to achieve unified information conversion between the first interface and the second interface specifically includes: A set of motion states of the vehicle is generated based on the operating status information, and a set of first interface information of the vehicle is generated based on the drive control information. Generate a first mapping relationship between the motion state set and the first interface information set; Based on the second mapping relationship between the predefined second interface information set and the motion state set, a third mapping relationship between the second interface information set and the first interface information set is generated to achieve unified information conversion between the first interface and the second interface.

3. The method according to claim 2, characterized in that, The predefined second interface information set includes the vehicle's longitudinal control interface, lateral control interface, and single-point control interface. The longitudinal control interface is used to control the vehicle's driving and / or stopping operations, the lateral control interface is used to control the vehicle's driving direction operations, and the single-point control interface is used to control the operation of the vehicle's related accessories.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: The vehicle's operating status information and drive control information are stored, and the vehicle's operating status information and drive control information are filtered to remove invalid information and obtain valid information. The valid information in the vehicle's operating status information and drive control information is parsed to achieve unified information conversion between the first interface and the second interface. The parsed valid information in the vehicle's operating status information and drive control information is used by the user to develop the vehicle's autonomous driving path on the vehicle's development application system. Simulate the autonomous driving path of the vehicle after development is completed, and test the simulated autonomous driving path of the vehicle.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: The system receives task execution information for the vehicle, which is obtained by the user through task orchestration of the vehicle on the vehicle's development application system. The task orchestration is based on the vehicle's task type and task flow. The vehicle's task type indicates the type of task the vehicle is performing, and the vehicle's task flow indicates the complexity of the task the vehicle is performing. The task execution information of the vehicle is parsed to obtain the autonomous driving path of the vehicle.

6. The method according to any one of claims 1-4, characterized in that, The method further includes: The system receives task execution information from the vehicle. This information is obtained by the user through task orchestration on the vehicle's development application system. The task orchestration is based on the vehicle's hardware capability information, which includes chassis information and sensor information. The chassis information indicates the vehicle's performance in performing tasks, and the sensor information indicates the vehicle's sensitivity in performing tasks. The task execution information of the vehicle is parsed to obtain the autonomous driving path of the vehicle.

7. The method according to any one of claims 1-6, characterized in that, The sensor includes one or more of lidar, millimeter-wave radar, and cameras.

8. An autonomous driving development platform, characterized in that, The autonomous driving platform includes: An interface providing module is used to provide a first interface and a second interface, wherein the first interface is used to connect to the vehicle's sensor system and chassis drive-by-wire system, and the second interface is used to connect to the vehicle's development and application system. The information receiving module is used to receive the vehicle's operating status information and drive control information based on the first interface. The vehicle's operating status information is collected by a variety of sensor systems installed on the vehicle, and the vehicle's drive control information is collected by a chassis drive-by-wire system installed on the vehicle. The information conversion module is used to parse the vehicle's operating status information and drive control information to achieve unified information conversion between the first interface and the second interface. The parsed vehicle operating status information and drive control information are used by the user to develop the vehicle's autonomous driving path on the vehicle's development application system.

9. The autonomous driving development platform according to claim 8, characterized in that, The information conversion module is specifically used for: A set of motion states of the vehicle is generated based on the operating status information, and a set of first interface information of the vehicle is generated based on the drive control information. Generate a first mapping relationship between the motion state set and the first interface information set; Based on the second mapping relationship between the predefined second interface information set and the motion state set, a third mapping relationship between the second interface information set and the first interface information set is generated to achieve unified information conversion between the first interface and the second interface.

10. The autonomous driving development platform according to claim 9, characterized in that, The predefined second interface information set includes the vehicle's longitudinal control interface, lateral control interface, and single-point control interface. The longitudinal control interface is used to control the vehicle's driving and / or stopping operations, the lateral control interface is used to control the vehicle's driving direction operations, and the single-point control interface is used to control the operation of the vehicle's related accessories.

11. The autonomous driving development platform according to any one of claims 8-10, characterized in that, Also includes: The information processing module is also used to store the vehicle's operating status information and drive control information, filter the vehicle's operating status information and drive control information, filter out invalid information in the vehicle's operating status information and drive control information, and obtain valid information in the vehicle's operating status information and drive control information. The information conversion module is also used to parse the valid information in the vehicle's operating status information and drive control information to realize unified information conversion between the first interface and the second interface. The valid information in the parsed vehicle's operating status information and drive control information is used by the user to develop the vehicle's autonomous driving path on the vehicle's development application system. The simulation test module is used to simulate the autonomous driving path of the vehicle after development is completed, and to test the simulated autonomous driving path of the vehicle.

12. The autonomous driving development platform according to any one of claims 8-11, characterized in that, Also includes: The information receiving module is also used to receive the vehicle's task execution information. The vehicle's task execution information is obtained by the user on the vehicle's development application system through task orchestration of the vehicle. The vehicle's task orchestration is based on the vehicle's task type and task flow. The vehicle's task type is used to indicate the type of task the vehicle is performing, and the vehicle's task flow is used to indicate the complexity of the task the vehicle is performing. The information conversion module is also used to parse the vehicle's task execution information to obtain the vehicle's autonomous driving path.

13. The cloud management platform according to any one of claims 8-11, characterized in that, The information receiving module is further configured to receive the vehicle's task execution information. The vehicle's task execution information is obtained by the user performing task orchestration on the vehicle's development application system. The vehicle's task orchestration is based on the vehicle's hardware capability information, which includes the vehicle's chassis information and the vehicle's sensor information. The vehicle's chassis information is used to indicate the vehicle's performance information in performing tasks, and the vehicle's sensor information is used to indicate the vehicle's sensitivity information in performing tasks. The information conversion module is also used to parse the vehicle's task execution information to obtain the vehicle's autonomous driving path.

14. The autonomous driving development platform according to any one of claims 8-13, characterized in that, The sensor includes one or more of lidar, millimeter-wave radar, and cameras.

15. A computing device cluster, characterized in that, It includes at least one computing device, each computing device including a processor and memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the cluster of computing devices to perform the method as described in any one of claims 1 to 7.

16. A computer program product containing instructions, characterized in that, When the instruction is executed by a cluster of computer devices, the cluster of computer devices causes the cluster of computer devices to perform the method as described in any one of claims 1 to 7.

17. A computer-readable storage medium, characterized in that, Includes computer program instructions, which, when executed by a cluster of computing devices, perform the method as described in any one of claims 1 to 7.

Images