A remote intelligent car experimental platform and experimental method based on AI

Abstract

The present invention discloses a remote intelligent vehicle experimental platform and experimental method based on AI, wherein the experimental platform comprises a local experimental terminal, a remote intelligent vehicle platform and a communication medium, wherein the local experimental terminal comprises a local experimental tool and a local debugger, and the remote intelligent vehicle platform comprises an on-board debugger, an on-board controller, an on-board drive unit, an on-board signal acquisition unit, an intelligent vehicle body and a power supply system. The present invention separates the on-board controller and the local experimental tool of the body component of the intelligent vehicle, and the body component and the necessary training map can be placed in a large-area special laboratory with conditions. The experimenter only needs to carry a portable local experimental tool and a local debugger to debug and control the intelligent vehicle in any place with a network signal, and actually retains the original closed-loop control data link, and the local core controller can directly send and receive control instructions and feedback motion information and video data, with simple wiring and convenient operation, which is convenient for remote teaching and online experiments.

Description

Technical Field

[0001] The present invention relates to the field of remote control technology, and specifically to an AI-based remote intelligent vehicle experimental platform and an experimental method. Background Art

[0002] In computer science, artificial intelligence (AI), sometimes referred to as machine intelligence, is intelligence exhibited by machines, in contrast to the natural intelligence exhibited by humans and animals. In layman's terms, the term "artificial intelligence" is used to describe machines that mimic the "cognitive" functions that humans associate with other human minds, such as "learning" and "problem solving." The smart car is a typical motion control experimental device that has broad development prospects in many engineering and technical fields, combining fun and theoretical research.

[0003] In the prior art, the motion control experimental devices such as smart cars and aircraft can be controlled by remote control, but it is impossible for the experimenter to debug and solidify the program through online programming, so as to achieve the learning of the programming method and control method of the motion control device. Moreover, the current experimental tools must be connected to the smart car and its components at a limited distance, and even the experimental programming tools, debuggers, and smart car controllers must be connected through data cables. Learners use experimental programming tools to write control programs, download them to the smart car controller, observe the motion effects, and complete the control tasks. Smart cars are large and inconvenient to carry. Learners must learn to purchase a full set of components to complete the learning, which is costly. Smart car motion training has certain environmental requirements, and often requires the construction of complex, non-portable plane or three-dimensional maps, which reduces the experimental efficiency of learners; the map area is large, and it is difficult for ordinary families, dormitories, and classroom environments to meet the requirements, and special environmental support is required. Moreover, this integrated structure is not convenient for remote teaching and online experiments. At the same time, during the existing experiment, although multiple sets of cameras can be used for shooting, the car can only be moved, so the fixed camera shooting still has blind spots and unclear situations. At the same time, the local debugger requires staff to conduct on-site mediation, and artificial intelligence technology cannot be used to remotely debug the local debugger. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above-mentioned background technology, the purpose of the present invention is to provide an AI-based remote smart car experimental platform and experimental method, which can formally separate the experimenter from the on-board controller, smart car body, training map and related components, and actually retain the original closed-loop control data link. The experimenter only needs to carry experimental programming tools and local debuggers to learn the debugging and control technology of smart cars anywhere with network conditions, directly send and receive debugging instructions and feedback motion information through the local debugger, and view laboratory monitoring video data through the network. It is easy to operate and convenient for remote teaching and online experiments, so as to realize real remote programming, debugging, program solidification and control of smart cars, and save learning costs.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A remote smart car experiment platform based on AI, comprising a local experiment terminal, a remote smart car platform and a communication medium, wherein the local experiment terminal comprises a local experiment tool and a local debugger, the remote smart car platform comprises an on-board debugger, an on-board controller, an on-board drive unit, an on-board signal acquisition unit, a smart car body and a power supply system, and the on-board signal acquisition unit comprises a body motion speed acquisition unit, an acceleration acquisition unit, a direction acquisition unit, a posture acquisition unit, an on-board power supply information acquisition unit and an on-board camera acquisition unit;

[0007] The communication medium realizes two-way data interaction between the local debugger and the vehicle debugger, between the local experimental tool and the laboratory monitoring equipment, and between the local experimental tool and the vehicle controller. The local debugger follows the established communication protocol to complete communication docking with the remote vehicle debugger to realize programming, debugging and monitoring of the vehicle controller.

[0008] The local experimental tool interacts with the local debugger in a two-way manner, and the on-board controller interacts with the on-board debugger, the on-board drive unit, and the on-board signal acquisition unit in a two-way manner.

[0009] Preferably, the local experiment tool includes a PC, a notebook, a PAD or other electronic devices capable of constructing a programming download environment.

[0010] Preferably, the on-board debugger, on-board controller, on-board drive unit, on-board signal acquisition unit and power supply system in the remote smart car platform are integrated with the smart car body, and the remote smart car platform and laboratory monitoring equipment are arranged in a laboratory where a smart car operation map can be laid out.

[0011] Preferably, the on-board controller downloads the on-board controller debugging program, and after running it, observes the data sent back by the smart car to view the control effect, and views the motion image of the smart car through laboratory monitoring. If the control task is not achieved, find the error and continue to write the program. The on-board controller debugging program includes single-step and breakpoint debugging programs.

[0012] Preferably, the local experimental platform further comprises a control cabinet, an AI intelligent terminal is fixedly installed on the top of the control cabinet, a local debugger is installed on the right side of the top of the control cabinet, and the monitoring device comprises a mounting plate, a guide rail is fixedly installed on the bottom of the mounting plate, a cover is mounted on the outer wall of the guide rail, a connecting plate is fixedly connected to the bottom of the cover, a lifting plate is fixedly connected to the bottom of the connecting plate, a fixing plate is connected to the bottom of the lifting plate, and a camera and an infrared module are fixedly installed on both sides of the bottom of the fixing plate;

[0013] The AI ​​intelligent terminal includes an artificial intelligence server, a data transmission module and a data acquisition module. The signal output end of the artificial intelligence server is connected to the signal input end of the local debugger through the data transmission module.

[0014] Preferably, motors are fixedly mounted on both side walls of the housing, a drive shaft of the motor passes through the housing and is fixedly connected to a rubber wheel, wheel grooves matching the rubber wheels are provided on both sides of the top of the guide rail, and the rubber wheels are inserted into the wheel grooves.

[0015] Preferably, the lifting plate includes a first plate body and a second plate body, the top of the first plate body is fixedly connected to the connecting plate, a limiting slide groove is provided on the right side of the first plate body, a limiting slider is inserted in the limiting slide groove, the outer wall of the limiting slider is fixedly connected to the second plate body, an electric push rod is fixedly connected to the top of the limiting slider, the top of the electric push rod is fixedly connected to the top of the inner cavity of the limiting slide groove, and the bottom of the second plate body is fixedly connected to the fixed plate.

[0016] Preferably, the signal output end of the infrared module is connected to the signal input end of the artificial intelligence server, and the signal output end of the artificial intelligence server is connected to the signal input end of the motor.

[0017] An AI-based remote intelligent car experimental method includes the following steps:

[0018] S1: The experimenter uses his own local experimental tools to write the motion control logic, algorithm and data forwarding program of the smart car in the integrated development environment;

[0019] S2: Compile the program and check if there are any compilation errors;

[0020] S3: Generate an executable file that can be used by the vehicle controller and transfer it to the local debugger through the USB interface;

[0021] S4: The local debugger transmits the executable file to the vehicle controller via a network medium using a specific communication protocol;

[0022] S5: The on-board debugger communicates with the on-board controller through the wire using the debugging interface protocol of the on-board controller, and loads the executable file into the on-board controller;

[0023] S6: If the vehicle controller runs the program directly after loading it, jump to S13. If it is a debugging program, jump to S7.

[0024] S7: In the development environment of the experimental tool, the experimenter can perform debugging operations such as setting breakpoints, setting the data registers and instruction register codes of the vehicle controller to be viewed, setting the variable names to be viewed, and can also set the debugging execution mode of the program to single step, limited steps or full speed;

[0025] S8: The development environment transmits the experimenter's debugging commands to the local debugger through the USB interface;

[0026] S9: The local debugger sends the debugging command to the on-board debugger through the network medium according to the established communication protocol;

[0027] S10: The on-board debugger executes the experimenter’s debugging commands;

[0028] S11: If the debugging command includes debugging commands that require data to be returned, such as data registers and instruction registers related to the vehicle controller that need to be checked, variable values ​​that need to be checked, etc., the vehicle debugger accesses the data registers and instruction registers related to the vehicle controller according to the debugging interface protocol of the vehicle controller, obtains relevant data, and returns the data to the local debugger through the network medium according to the established communication protocol;

[0029] S12: The local debugger transmits the received data to the development environment through the USB interface to obtain the data that the experimenter is interested in;

[0030] S13: During the operation of the on-board controller, the control effect can be viewed by observing the data sent back by the smart car, or the motion image of the smart car can be viewed through the monitoring of the laboratory;

[0031] S14: If the control task is not achieved, the experimenter can return to S1 to continue to modify the program. Or he can return to S7 to debug the onboard controller online, debug the program step by step or at breakpoints, check errors based on the returned information, and then return to S1 to modify the program.

[0032] Beneficial effects of the present invention:

[0033] (1) The present invention separates the body components, on-board controller and local experimental tools of the smart car. The body components and necessary training maps can be placed in a large-scale dedicated laboratory with the necessary conditions. The experimenter only needs to carry portable local experimental tools and a local debugger to debug and control the smart car anywhere with a network signal. In fact, the original closed-loop control data link is retained. The local core controller can directly send and receive control instructions and feedback motion information and video data. The wiring is simple and the operation is convenient, which is convenient for remote teaching and online experiments, realizing true remote control of unmanned vehicles and saving learning costs.

[0034] (2) The architecture of the present invention is remote in form. The motion state data of the smart car is generally image environment image data, speed, acceleration, and posture information, which has a certain amount of data. The control of the smart car has relatively high requirements for real-time and stability. Therefore, the speed, real-time and stability of information transmission on "remote" are solved to ensure that the formal "remote" is essentially the same as "on-board".

[0035] (3) The present invention utilizes the two major technical characteristics of the communication medium, namely, fast transmission speed and low latency, to meet the requirements of the smart car for communication stability, real-time performance, and bandwidth, avoid control failure of the smart car, interruption or blurring of real-time images, and delayed state feedback, and ensure that the closed-loop real-time performance of the control signal, state data, and environmental image data remains unchanged, thus ensuring the possibility of remote debugging and control of the smart car. It provides sufficient support for the communication of the smart car, and also provides a guarantee for the remote communication and control of the smart car. After the communication medium is connected to the remote experiment platform of the smart car, it can not only perceive the motion status and environmental data of the key nodes in real time, but also actively respond to task changes and path obstacles, turning "remote" into "on-board". The communication medium greatly reduces latency and improves the efficiency and reliability of remote experiments.

[0036] (4) The present invention can realize artificial intelligence control of the camera to move through the AI ​​smart terminal, so that when the infrared module tracks the smart car, as the car moves, the height and position of the camera can change in real time, thereby tracking the smart car in real time, so that the image data of the smart car can be captured more accurately, truly achieving no blind spots, and ensuring that the viewing and research of the smart car are more accurate. At the same time, the AI ​​smart terminal can directly collect the instructions required by the staff for adjustment, and can automatically issue instructions by voice input, and transmit the instructions to the local debugger for debugging operations, so that the staff can remotely control local debugging. With the support of AI technology, the operation is simpler and faster. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The present invention will be further described below in conjunction with the accompanying drawings.

[0038] Figure 1 It is a framework diagram of the remote intelligent vehicle experimental platform of the present invention;

[0039] Figure 2 It is a method flow chart of the remote intelligent vehicle experimental platform of the present invention;

[0040] Figure 3 It is a schematic diagram of the monitoring equipment and control cabinet structure of the remote intelligent vehicle experimental platform of the present invention;

[0041] Figure 4 It is a schematic diagram of the connection structure of the guide rail and the cover of the remote intelligent vehicle experimental platform of the present invention;

[0042] Figure 5 It is a schematic diagram of the lifting plate structure of the remote intelligent vehicle experimental platform of the present invention;

[0043] Figure 6 It is a schematic diagram of the AI ​​intelligent terminal of the remote intelligent vehicle experimental platform of the present invention.

[0044] In the figure:

[0045] 1. Control cabinet; 2. AI intelligent terminal; 3. Mounting plate; 4. Guide rail; 5. Cover; 6. Connecting plate; 7. Lifting plate; 8. Fixing plate; 9. Camera; 10. Infrared module; 11. Motor; 12. Rubber wheel; 13. Wheel groove; 14. First plate; 15. Second plate; 16. Limiting slide groove; 17. Limiting slider; 18. Electric push rod; 19. Artificial intelligence server; 20. Data transmission module; 21. Data acquisition module. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "all around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0048] like Figure 1-6As shown, the present invention provides a technical solution: an AI-based remote intelligent vehicle experimental platform, including an experimental platform, the experimental platform including local experimental tools, monitoring software, a local debugger, a remote debugger, a remote intelligent vehicle platform, a laboratory monitoring device and a communication medium, the communication medium respectively realizes two-way data interaction between the local debugger and the vehicle debugger, and between the local PC and the laboratory monitoring device, wherein:

[0049] The local experiment terminal includes local experiment tools and local debuggers. The local experiment tools run the intelligent vehicle control program editing, compilation program, monitoring software and video monitoring program; the local debugger is used for two-way interaction between the local experiment tools and the vehicle debugger.

[0050] The remote smart car platform includes an on-board debugger, an on-board controller, an on-board drive unit, an on-board signal acquisition unit, a smart car body and a power supply system. The on-board controller interacts bidirectionally with the on-board debugger, the on-board drive unit and the on-board signal acquisition unit.

[0051] The vehicle-mounted signal acquisition unit includes a vehicle body speed, acceleration, direction, posture acquisition unit, a vehicle power information acquisition unit, and a vehicle camera acquisition unit; providing a data source for monitoring and software.

[0052] In this embodiment, the experimental operation process of the remote smart car experimental platform is as follows: the experimenter carries a local experimental terminal containing local experimental tools and a local debugger, and remotely debugs and controls the body of the smart car at any place with a network signal. The experimenter uses a programming tool to write the motion control logic, algorithm and data forwarding program of the smart car according to the experimental task and the established communication protocol, and generates executable code after compilation. The executable code is downloaded to the on-board controller in the remote smart car platform through the local debugger, communication medium and on-board debugger. The on-board controller generates a driving level of the smart car to the on-board drive unit, and the on-board drive unit provides the body of the smart car with a signal according to the received signal. The power signal changes the motion state of the smart car body; the experimenter can also debug the on-board controller online through the local debugger, communication medium, and on-board debugger, and access the relevant data registers and instruction registers of the on-board controller; the on-board signal acquisition unit collects the motion state information of the smart car body and transmits this information back to the monitoring software running in the local experimental tool through the on-board controller and communication medium in real time; the local experimental tool controls the laboratory monitoring equipment at the same time, and the laboratory monitoring equipment provides the experimenter with real-time on-site image video of the smart car operation, which can fully observe and understand the motion state and actual control effect of the smart car, forming a closed-loop control of the smart car.

[0053] Furthermore, the local experimental tools in the local experimental end include PCs, notebooks, PADs or other electronic devices that can build a programming download environment; the local debugger in the local experimental end follows the established communication protocol, completes communication docking with the remote on-board debugger, and realizes programming, debugging and monitoring of the on-board controller.

[0054] In this embodiment, the laboratory provides monitoring software that can be run by local experimental tools, and exchanges data with the vehicle controller through the network medium according to the established communication protocol to monitor the performance data of the smart car's movement.

[0055] Furthermore, the local debugger and the vehicle-mounted debugger form a two-way data interaction through the communication medium.

[0056] In this embodiment, the local debugger is connected to the local experimental tool through a USB interface and supports operating systems such as Windows 7, Windows 10, and Linux. When the experimenter debugs the program in the integrated development environment of the local experimental tool, there are operations such as breakpoint debugging, continuous debugging, single-step debugging, and downloading programs. The contents of the relevant data registers and instruction registers of the on-board controller can be viewed, and the numerical changes of program variables during program execution can be viewed. These operations can be performed by the local debugger communicating with the on-board debugger through a communication medium, converting these commands of the integrated development environment into control signals for the debugging interface of the on-board controller, and performing operations such as controlling the chip and reading and writing data.

[0057] Furthermore, the on-board debugger, on-board controller, on-board drive unit, on-board signal acquisition unit and power supply system in the remote smart car platform are integrated with the smart car body and arranged with the laboratory monitoring equipment in a laboratory capable of laying out a smart car operation map.

[0058] In this embodiment, the vehicle-mounted debugger is connected to the vehicle-mounted controller debugging interface via a wire, receives instructions and data from the local debugger, accesses relevant data registers and instruction registers of the vehicle-mounted controller, and returns relevant data to complete operations such as debugging, programming, and program solidification.

[0059] The debugging commands and fixed programs of the on-board debugger come from the local debugger, and the contents of the data registers and instruction registers related to the on-board controller that the experimenter is concerned about are sent to the local debugger. The data interaction between the two is transmitted through the communication medium.

[0060] Furthermore, the programmed executable file is downloaded to the on-board controller. After running, the data sent back by the smart car is observed to check the control effect, and the motion image of the smart car is viewed through the laboratory monitoring. If the control task is not achieved, find the error and continue to write the program.

[0061] Furthermore, the vehicle controller debugging program includes single-step and breakpoint debugging programs.

[0062] Furthermore, the local experimental platform also includes a control cabinet 1, an AI intelligent terminal 2 is fixedly installed on the top of the control cabinet 1, a local debugger is installed on the top right side of the control cabinet 1, and the monitoring device includes a mounting plate 3, a guide rail 4 is fixedly installed on the bottom of the mounting plate 3, a cover 5 is sleeved on the outer wall of the guide rail 4, a connecting plate 6 is fixedly connected to the bottom of the cover 5, a lifting plate 7 is fixedly connected to the bottom of the connecting plate 6, a fixing plate 8 is connected to the bottom of the lifting plate 7, and a camera 9 and an infrared module 10 are fixedly installed on both sides of the bottom of the fixing plate 8;

[0063] The AI ​​intelligent terminal 2 includes an artificial intelligence server 19, a data transmission module 20 and a data acquisition module 21. The signal output end of the artificial intelligence server 19 is connected to the signal input end of the local debugger through the data transmission module 20.

[0064] Furthermore, motors 11 are fixedly installed on both side walls of the cover shell 5, and the transmission shaft of the motor 11 passes through the cover shell 5 and is fixedly connected to a rubber wheel 12. Wheel grooves 13 adapted to the rubber wheel 1 are opened on both sides of the top of the guide rail 4, and the rubber wheel 12 is inserted into the wheel grooves 13.

[0065] Furthermore, the lifting plate 7 includes a first plate body 14 and a second plate body 15. The top of the first plate body 14 is fixedly connected to the connecting plate 6. A limiting groove 16 is provided on the right side of the first plate body 14. A limiting slider 17 is inserted into the limiting groove 16. The outer wall of the limiting slider 17 is fixedly connected to the second plate body 15. An electric push rod 18 is fixedly connected to the top of the limiting slider 17. The top of the electric push rod 18 is fixedly connected to the top of the inner cavity of the limiting groove 16. The bottom of the second plate body 15 is fixedly connected to the fixed plate 8.

[0066] Furthermore, the signal output end of the infrared module 10 is connected to the signal input end of the artificial intelligence server 19 , and the signal output end of the artificial intelligence server 19 is connected to the signal input end of the motor 11 .

[0067] Embodiment 1:

[0068] The present invention is further described in detail below with reference to the accompanying drawings and specific implementation examples.

[0069] See also Figure 1The remote intelligent vehicle experimental platform of the present invention includes a local experimental end, a remote intelligent vehicle platform, a laboratory monitoring device and a communication medium. The local experimental end includes a local experimental tool and a local debugger. The remote intelligent vehicle platform includes an on-board debugger, an on-board controller, an on-board drive unit, an on-board signal acquisition unit, an intelligent vehicle body and a power supply system, and is arranged with the laboratory monitoring equipment in a laboratory with conditions for laying an intelligent vehicle operation map. The monitoring software of the laboratory includes a camera 9, which can track the intelligent vehicle using an infrared module 10 after the AI ​​intelligent terminal 2 issues an instruction, so that the artificial intelligence server 19 will issue an instruction to make the motor 11 work, so that the rubber wheel 12 is driven to rotate in the wheel groove 13. The cover 5 drives the camera 9 to move, and the electric push rod 18 drives the second plate 15 to rise and fall, and adjusts the height of the camera 9, so as to realize intelligent tracking and shooting of the smart car, and transmit the data to the remote end, so as to ensure that the smart car is presented more clearly at the remote end. At the same time, when the remote staff needs to debug the local debugger, they can transmit the signal remotely, and then the data acquisition module 21 of the AI ​​smart terminal 2 can feed back the signal to the artificial intelligence server 19, so as to issue instructions to the local debugger and perform local debugging, thereby eliminating the need for manual debugging on site and providing more convenience.

[0070] Among them: the on-board controller can use the i.MX RT1021 processor of NXP's Cortex-M7 core as the core. The on-board controller needs to be connected to the on-board debugger by the laboratory manager or learner through a wire in advance. The on-board controller runs the smart car control logic, algorithm, peripheral component driver and related communication protocols. The on-board controller generates the smart car drive level to the on-board drive unit. The on-board drive unit provides power signals to the smart car according to the received signals, changes the motion state of the smart car, and drives the smart car to move forward, backward, turn left, turn right, single pulse and other movements according to the instructions. The on-board signal acquisition unit collects the motion state information, environmental information and image data of the smart car, and the on-board debugger returns them to the local core controller of the local experimental end through the communication medium. The on-board controller receives the motion information data of the smart car and the image information of the on-board camera (optional) sent by the on-board signal acquisition unit, and sends them to the learner through the on-board debugger, communication medium and local debugger. The monitoring equipment in the laboratory can provide the running status of the smart car in real time through the communication medium.

[0071] The experimenters carry programming tools and local debuggers and debug the remote smart car just like debugging a traditional smart car anywhere with a network signal.

[0072] The experimenter uses the remote intelligent vehicle experimental platform architecture to conduct the experiment process as follows: Figure 2 The steps are described as follows:

[0073] The experimenters use their own local experimental tools to write the motion control logic, algorithms and data forwarding programs of the smart car in the integrated development environment.

[0074] Compile the program and check for compilation errors.

[0075] Generate an executable file that can be used by the vehicle controller and transfer it to the local debugger through the USB interface.

[0076] The local debugger transmits the executable file to the on-board controller via a network medium using a specific communication protocol.

[0077] The on-board debugger communicates with the on-board controller's debugging interface protocol through a wire to load the executable file into the on-board controller.

[0078] If the vehicle controller runs the program directly after loading it, jump to S13. If it is debugging the program, jump to S7.

[0079] In the development environment of the experimental tool, the experimenter can perform debugging operations such as setting breakpoints, setting the relevant data registers and instruction register codes of the vehicle controller to be viewed, setting the variable names to be viewed, and can also set the debugging execution mode of the program to single step, limited steps or full speed.

[0080] The development environment transmits the experimenter's debugging commands to the local debugger through the USB interface.

[0081] The local debugger sends the debugging command to the on-board debugger via the network medium according to the established communication protocol.

[0082] The on-board debugger executes the experimenter's debugging commands.

[0083] If the debugging commands include debugging commands that require data to be returned, such as data registers and instruction registers related to the vehicle controller that need to be viewed, variable values ​​that need to be viewed, etc., the vehicle debugger accesses the relevant data registers and instruction registers of the vehicle controller according to the debugging interface protocol of the vehicle controller, obtains relevant data, and returns the data to the local debugger through the network medium according to the established communication protocol.

[0084] The local debugger passes the received data to the development environment through the USB interface to obtain the data of interest to the experimenter.

[0085] During the operation of the on-board controller, you can observe the data sent back by the smart car to view the control effect, or you can view the movement image of the smart car through laboratory monitoring.

[0086] If the control task is not achieved, the experimenter can return to S1 to continue to modify the program. Or he can return to S7 to debug the onboard controller online, debug the program step by step or at breakpoints, check errors based on the returned information, and then return to S1 to modify the program.

[0087] Embodiment 2:

[0088] The experimenter used the remote intelligent vehicle experimental platform architecture to conduct the experiment method as follows Figure 1 As shown, there may be a second method:

[0089] The laboratory provides experimenters with smart car operation monitoring software and related communication protocols with smart cars.

[0090] The experimenter solidified the program for the vehicle controller according to the method of Example 1

[0091] The experimenter runs the monitoring software in the local experiment tool

[0092] The vehicle controller provides the monitoring software with the operating index information of the smart vehicle through the network medium in accordance with the established communication protocol, including but not limited to the vehicle body movement speed, acceleration, direction, posture, vehicle power supply information, and vehicle camera information;

[0093] If these motion index information do not meet the expected performance requirements, the experimenter continues to modify the program and continue debugging according to Example 1.

[0094] Embodiment 3:

[0095] Experimenters using the remote smart car experimental platform architecture can use the self-test program provided by the laboratory to test the smart car components:

[0096] The experimenter solidified the self-test program for the vehicle controller according to the method of Example 1

[0097] The vehicle controller provides the local experimental terminal with the operation index information of the smart vehicle through the network medium, including but not limited to the vehicle body movement speed, acceleration, direction, posture, vehicle power supply information, and vehicle camera information;

[0098] If there is any fault information prompt in these motion index information, the experimenter reports the smart car fault to the experimenter and requests laboratory assistance.

[0099] The local experimental tool can be a PC, notebook, PAD or other electronic device that can build a programming download environment, which is prepared by the user; the local debugger and the on-board debugger complete the debugging command and data docking through the communication medium, and the on-board controller sends the motion status and image data to the experimenter. The user uses the experimental tool to complete the programming according to the experimental task, which is downloaded to the on-board controller through the local debugger, communication medium, and on-board debugger, and the motion information and image data of the smart car are received at the same time, forming a closed-loop control.

[0100] The power system can be powered by batteries to provide the required power for the smart vehicle and its loading unit.

[0101] The present invention separates the learner from the body components of the smart car. The body components and necessary training maps can be placed in a large-scale dedicated laboratory with conditions, and the experimenter only needs to carry a portable local debugger to debug and control the smart car anywhere with a network signal.

[0102] The communication medium can be 5G network technology or other network technologies with better communication speed and network delay. The theoretical network bandwidth of 5G network technology specifications reaches 10Gbps, which is equivalent to a download speed of 1.25GB / s, and its ultra-low network delay can reach the level of 1ms.

[0103] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0104] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A remote intelligent vehicle experimental platform based on AI, characterized in that: It includes a local experiment terminal, a remote smart car platform and a communication medium. The local experiment terminal includes a local experiment tool and a local debugger. The remote smart car platform includes an on-board debugger, an on-board controller, an on-board drive unit, an on-board signal acquisition unit, a smart car body and a power supply system. The on-board signal acquisition unit includes a body motion speed acquisition unit, an acceleration acquisition unit, a direction acquisition unit, a posture acquisition unit, an on-board power supply information acquisition unit and an on-board camera acquisition unit. The communication medium realizes two-way data interaction between the local debugger and the vehicle debugger, between the local experimental tool and the laboratory monitoring equipment, and between the local experimental tool and the vehicle controller. The local debugger follows the established communication protocol to complete communication docking with the remote vehicle debugger to realize programming, debugging and monitoring of the vehicle controller. The local experimental tool and the local debugger interact bidirectionally, and the vehicle controller interacts bidirectionally with the vehicle debugger, the vehicle drive unit, and the vehicle signal acquisition unit; The on-board controller downloads the on-board controller debugging program, and after running it, observes the data sent back by the smart car to view the control effect, and views the motion image of the smart car through laboratory monitoring. If the control task is not achieved, find the error and continue to write the program. The on-board controller debugging program includes single-step and breakpoint debugging programs.

2. The AI-based remote intelligent vehicle experimental platform according to claim 1 is characterized in that: The local experiment tool includes a PC, a notebook, a PAD or other electronic devices capable of constructing a programming download environment.

3. The AI-based remote intelligent vehicle experimental platform according to claim 1 is characterized in that: The on-board debugger, on-board controller, on-board drive unit, on-board signal acquisition unit and power supply system in the remote smart car platform are integrated with the smart car body, and the remote smart car platform and laboratory monitoring equipment are arranged in a laboratory where a smart car operation map can be laid out.

4. The AI-based remote intelligent vehicle experimental platform according to claim 1 is characterized in that: The local experimental end also includes a control cabinet, an AI intelligent terminal is fixedly installed on the top of the control cabinet, the local debugger is installed on the right side of the top of the control cabinet, the monitoring device includes a mounting plate, a guide rail is fixedly installed on the bottom of the mounting plate, a cover is mounted on the outer wall of the guide rail, the bottom of the cover is fixedly connected to a connecting plate, the bottom of the connecting plate is fixedly connected to a lifting plate, the bottom of the lifting plate is connected to a fixing plate, and cameras and infrared modules are fixedly installed on both sides of the bottom of the fixing plate; The AI ​​intelligent terminal includes an artificial intelligence server, a data transmission module and a data acquisition module. The signal output end of the artificial intelligence server is connected to the signal input end of the local debugger through the data transmission module.

5. The AI-based remote intelligent vehicle experimental platform according to claim 4 is characterized in that: Motors are fixedly mounted on both side walls of the housing, a transmission shaft of the motor passes through the housing and is fixedly connected to a rubber wheel, wheel grooves matching the rubber wheel are provided on both sides of the top of the guide rail, and the rubber wheel is inserted into the wheel grooves.

6. The AI-based remote intelligent vehicle experimental platform according to claim 4 is characterized in that: The lifting plate includes a first plate body and a second plate body. The top of the first plate body is fixedly connected to the connecting plate. A limiting slide groove is arranged on the right side of the first plate body. A limiting slider is inserted into the limiting slide groove. The outer wall of the limiting slider is fixedly connected to the second plate body. An electric push rod is fixedly connected to the top of the limiting slider. The top of the electric push rod is fixedly connected to the top of the inner cavity of the limiting slide groove. The bottom of the second plate body is fixedly connected to the fixing plate.

7. The AI-based remote intelligent vehicle experimental platform according to claim 4 is characterized in that: The signal output end of the infrared module is connected to the signal input end of the artificial intelligence server, and the signal output end of the artificial intelligence server is connected to the signal input end of the motor.

8. A remote intelligent car experimental method based on AI, characterized in that: The steps include: S1: The experimenter uses his own local experimental tools to write the motion control logic, algorithm and data forwarding program of the smart car in the integrated development environment; S2: Compile the program and check if there are any compilation errors; S3: Generate an executable file that can be used by the vehicle controller and transfer it to the local debugger through the USB interface; S4: The local debugger transmits the executable file to the vehicle controller via the network medium using the communication protocol; S5: The on-board debugger communicates with the on-board controller through the wire using the debugging interface protocol of the on-board controller, and loads the executable file into the on-board controller; S6: If the vehicle controller runs the program directly after loading it, jump to S13. If it is a debugging program, jump to S7. S7: In the development environment of the experimental tool, the experimenter can perform debugging operations such as setting breakpoints, setting the data registers and instruction register codes of the vehicle controller to be viewed, and setting the variable names to be viewed. The debug execution mode of the program can also be set to single step, limited step or full speed. S8: The development environment transmits the experimenter's debugging commands to the local debugger through the USB interface; S9: The local debugger sends the debugging command to the on-board debugger through the network medium according to the established communication protocol; S10: The on-board debugger executes the experimenter’s debugging commands; S11: If the debugging command contains debugging commands for checking the relevant data registers and instruction registers of the on-board controller and the checked variable values ​​that require data to be returned, the on-board debugger accesses the relevant data registers and instruction registers of the on-board controller according to the debugging interface protocol of the on-board controller, obtains relevant data, and returns the data to the local debugger through the network medium according to the established communication protocol; S12: The local debugger transmits the received data to the development environment through the USB interface to obtain the data that the experimenter is interested in; S13: During the operation of the on-board controller, observe the data sent back by the smart car to check the control effect, and check the movement image of the smart car through the monitoring of the laboratory; S14: If the control task is not achieved, the experimenter returns to S1 to continue modifying the program, or returns to S7 to debug the vehicle controller online, debug the program step by step or at breakpoints, check for errors based on the returned information, and then returns to S1 to modify the program.

Images