Automobile part assembly training method and system based on virtual reality

Abstract

The invention belongs to the field of automobile part assembly, and particularly relates to an automobile part assembly training method and system based on virtual reality, and the method comprises the steps: obtaining user personal data collected by the system and a training instruction inputted by a user after a training starting signal is received; according to a training instruction input by the user, calling guidance data corresponding to the training instruction, and generating a corresponding virtual training scene; the user training data and preset standard training data are processed and analyzed, and real-time scoring and correction are carried out; judging whether the current training instruction is completed or not, and if not, returning to the acquisition step; and if the scoring is completed, accumulating the scores in the previous step to obtain a test score. The automobile part assembling environment can be simulated, a safe, convenient and effective training mode is provided for a user, errors can be corrected in real time, feedback can be provided, and the accuracy and quality of the assembling process are improved.

Description

Technical Field

[0001] The invention belongs to the field of automobile parts assembly, and in particular relates to an automobile parts assembly training method and system based on virtual reality. Background Art

[0002] As an important part of the automobile manufacturing process, automobile parts assembly has gradually developed towards mechanization and automation with the development of industrial production technology. However, some automobile parts still need to be assembled manually or through manually operated equipment. This type of automobile parts assembly requires assemblers to have rich experience.

[0003] In the existing technology, new employees are often guided and trained by experienced technicians. However, this training method has high training costs, low efficiency, and poor training results. In addition, new employees often come into contact with equipment during field training, which puts them at greater safety risks. Summary of the invention

[0004] Based on the above-mentioned problems existing in the prior art, the purpose of the embodiments of the present invention is to provide a virtual reality-based automobile parts assembly training method, provide a simulated automobile assembly scene, provide users with a safe, convenient and effective training method, reduce training costs, improve training efficiency, and be able to correct errors and provide feedback in real time.

[0005] To achieve the above purpose, the technical solution adopted by the present invention to solve the technical problem is: the present invention discloses a virtual reality-based automobile parts assembly training method, comprising:

[0006] S1, after receiving the training start signal, obtaining the user's personal data collected by the system and the training instructions input by the user;

[0007] S2, according to the training instruction input by the user, calling the guidance data corresponding to the training instruction and generating a corresponding virtual training scene;

[0008] S3, collecting the user's hand motion data, hand pressure data and user limb data in reality and positioning them;

[0009] S4, binds the user's hand motion data, hand pressure data and user limb data to the virtual training scene

[0010] S5, pre-processing the hand motion data, the hand pressure data and the user limb data to obtain user training data;

[0011] S6, processing and analyzing the user training data and the preset standard training data, and performing real-time scoring and correction;

[0012] S7, determine whether the current training instruction is completed. If not, return to step S3; if completed, accumulate the scores in step S6 to obtain the test results.

[0013] Furthermore, in S1, the training instructions include practice operation guidance instructions and test simulation assembly instructions, the practice operation guidance instructions include VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions and parts free assembly operation guidance instructions, and the test simulation assembly instructions include simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

[0014] Furthermore, in S2, the training instructions input by the user are any one of VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions, parts free assembly operation guidance instructions, simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

[0015] Furthermore, in S3, the user's hand motion data and hand pressure data are collected in real time by using a handheld device or wearing data collection gloves; the user's limb data is collected in real time by setting a position tracking device.

[0016] Furthermore, in S3, the handheld device or data acquisition glove uses an inertial measurement unit, and the inertial measurement unit is used to collect the user's hand motion data. The inertial measurement unit includes an accelerometer, a gyroscope and a magnetometer.

[0017] Furthermore, in S4, the step of binding the user's hand motion data, hand pressure data, and user limb data to the virtual training scene includes:

[0018] Step S41, converting the coordinate system in reality into the coordinate system in the virtual scene;

[0019] Step S42, fusing and calibrating the user's hand motion data, hand pressure data, and user limb data;

[0020] Step S43, updating and feeding back the user's hand motion data, hand pressure data and user limb data in real time.

[0021] Furthermore, in S5, the hand motion data, hand pressure data and user limb data are preprocessed to obtain user training data, including: determining a reasonable value range according to the physical meaning of the hand motion data, hand pressure data and user limb data, and preprocessing the data according to the inherent logical relationship between the data, and for the suspected bad data that has been identified, deciding whether to screen it out according to the set threshold.

[0022] The automobile parts assembly training system based on virtual reality is applied to the automobile parts assembly training method based on virtual reality, and the system comprises:

[0023] A signal receiving module, used for receiving a training start signal;

[0024] An instruction acquisition module is used to acquire the user's personal data collected by the system and the training instructions input by the user;

[0025] A scene calling module is used to call the guidance data corresponding to the training instruction according to the training instruction input by the user, and generate a corresponding virtual training scene;

[0026] The data collection and positioning module is used to collect the user's hand motion data, hand pressure data and user limb data in reality and perform positioning;

[0027] Data binding module, used to bind the user's hand motion data, hand pressure data and user limb data to the virtual training scene

[0028] A data preprocessing module, used for preprocessing hand motion data, hand pressure data and user limb data to obtain user training data;

[0029] The data processing and analysis module is used to process and analyze user training data and preset standard training data, and to perform real-time scoring and correction;

[0030] The scoring module is used to determine whether the current training instruction is completed. If not,

[0031] The embodiment of the present invention further provides a network side server, including:

[0032] At least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned automobile parts assembly training method based on virtual reality.

[0033] The embodiment of the present invention further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned automobile parts assembly training method based on virtual reality is implemented.

[0034] The beneficial effects of the present invention are as follows: the automobile parts assembly training method based on virtual reality of the present invention comprises: after receiving the training start signal, obtaining the user's personal data collected by the system and the training instructions input by the user; according to the training instructions input by the user, calling the guidance data corresponding to the training instructions, generating the corresponding virtual training scene; collecting the hand motion data, hand pressure data and user limb data of the user in reality and positioning them; binding the hand motion data, hand pressure data and user limb data of the user to the virtual training scene; pre-processing the hand motion data, hand pressure data and user limb data to obtain user training data; processing and analyzing the user training data and the preset standard training data, and scoring and correcting them in real time; judging whether the current training instruction is completed, if not completed, returning to the collection step; if completed, accumulating the scores in the previous step to obtain the test results. The present invention can simulate the automobile parts assembly environment, provide users with a safe, convenient and effective training method, reduce training costs, improve training efficiency, and can correct errors and provide feedback in real time, thereby improving the accuracy and quality of the assembly process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0036] Figure 1 is a flow chart of a method for training automobile parts assembly based on virtual reality according to a first embodiment of the present invention;

[0037] Figure 2 is a structural schematic diagram of an automobile parts assembly training system based on virtual reality provided according to a second embodiment of the present invention;

[0038] Figure 3 It is a structural diagram of a network-side server provided according to a third embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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.

[0040] The first embodiment of the present invention relates to a method for automobile parts assembly training based on virtual reality. In this embodiment, after receiving a training start signal, the user's personal data collected by the system and the training instructions input by the user are obtained; according to the training instructions input by the user, the guidance data corresponding to the training instructions are called to generate a corresponding virtual training scene; the hand motion data, hand pressure data and user limb data of the user in reality are collected and positioned; the hand motion data, hand pressure data and user limb data of the user are bound to the virtual training scene; the hand motion data, hand pressure data and user limb data are pre-processed to obtain user training data; the user training data and the preset standard training data are processed and analyzed, and real-time scoring and correction are performed; it is judged whether the current training instruction is completed, if not completed, return to step S3; if completed, the scores in step S6 are accumulated to obtain a test score. The present invention can simulate the automobile parts assembly environment, provide users with a safe, convenient and effective training method, reduce training costs, improve training efficiency, and can correct errors and provide feedback in real time, thereby improving the accuracy and quality of the assembly process.

[0041] The following is a detailed description of the implementation details of the automobile parts assembly training method based on virtual reality in this embodiment. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The specific process of this embodiment is as follows: Figure 1 As shown, this implementation is applied to the server on the network side.

[0042] Step S1, after receiving the training start signal, obtaining the user's personal data collected by the system and the training instructions input by the user.

[0043] Specifically, the training start signal in this case is usually authorized by the training teacher or superior leader to be received by the automobile parts assembly training system. The training start signal can be generated by the authorized training teacher or leader manually, or it can be generated according to the preset training schedule, or it can be generated by detecting the preset users around the system.

[0044] The user's personal data is usually manually input into the training system by the user or obtained by the training system through user facial image collection and comparison.

[0045] The training instructions include practice operation guidance instructions and test simulation assembly instructions, wherein the practice operation guidance instructions include VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions and parts free assembly operation guidance instructions; the test simulation assembly instructions include simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

[0046] After the system collects the user's personal data, it enters the training instruction selection interface, and the user selects any of the above training instructions for training.

[0047] Step S2: according to the training instruction input by the user, calling the guidance data corresponding to the training instruction, and generating a corresponding virtual training scene.

[0048] Specifically, the training instructions input by the user are any one of VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions, parts free assembly operation guidance instructions, simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

[0049] Among them, the guidance data corresponding to the VR basic operation guidance instructions are VR basic operation scene simulation data, VR basic operation video prompt data and VR basic operation text prompt data. When the user inputs the VR basic operation guidance instructions, the automobile parts assembly training system based on virtual reality calls out the VR basic operation scene simulation data, VR basic operation video prompt data and VR basic operation text prompt data. The user can learn how to perform basic operations in a virtual environment based on the VR basic operation scene simulation data, VR basic operation video prompt data and VR basic operation text prompt data, thereby making the user familiar with the virtual reality interface and control method, laying the foundation for subsequent training.

[0050] The guidance data corresponding to the parts assembly operation guidance instructions are parts assembly operation scene simulation data, parts assembly operation video prompt data, and parts assembly operation text prompt data. When the user inputs the parts assembly operation guidance instructions, the automobile parts assembly training system based on virtual reality calls out the parts assembly operation scene simulation data, parts assembly operation video prompt data, and parts assembly operation text prompt data to guide the assembly process of automobile parts step by step.

[0051] The guidance data corresponding to the parts disassembly operation instruction is the parts disassembly operation scene simulation data, the parts disassembly operation video prompt data and the parts disassembly operation text prompt data. When the user inputs the parts disassembly operation instruction, the automobile parts assembly training system based on virtual reality calls out the parts disassembly operation scene simulation data, the parts disassembly operation video prompt data and the parts disassembly operation text prompt data for learning how to disassemble automobile parts safely and effectively. Then, by simulating different disassembly scenes and techniques through the automobile parts assembly training system based on virtual reality, the operator can master the correct disassembly steps and methods to avoid damage to the equipment and improve maintenance efficiency.

[0052] The guidance data corresponding to the free assembly operation instruction of parts are free assembly operation scene simulation data, free assembly operation video prompt data and free assembly text prompt data of parts. When the user inputs the free assembly operation instruction of parts, the automobile parts assembly training system based on virtual reality calls out the free assembly operation scene simulation data of parts, free assembly operation video prompt data of parts and free assembly operation text prompt data of parts. By following the free assembly operation instruction of parts to learn, the user can freely explore and consolidate the knowledge learned, so as to be more flexible and adaptable to various situations in actual work.

[0053] The guidance data corresponding to the simulated part assembly instruction is the part assembly scene simulation data and the simulated part assembly text data. When the user inputs the simulated part assembly instruction, the automobile part assembly training system based on virtual reality calls out the part assembly scene simulation data, and the user performs the part assembly operation according to the simulated part assembly text data in the virtual part assembly scene.

[0054] The guidance data corresponding to the simulated part disassembly instruction are the part disassembly scene simulation data and the simulated part disassembly text data. When the user inputs the simulated part disassembly instruction, the automobile part assembly training system based on virtual reality calls out the part disassembly scene simulation data, and the user performs the part disassembly operation according to the simulated part disassembly text data in the virtual part disassembly scene.

[0055] The guidance data corresponding to the simulated parts free assembly instruction are the parts free assembly scene simulation data and the simulated parts free assembly text data. When the user inputs the simulated parts free assembly instruction, the automobile parts assembly training system based on virtual reality calls out the parts free assembly scene simulation data, and the user performs the parts free assembly operation according to the simulated parts free assembly text data in the virtual parts free assembly scene.

[0056] In this embodiment, the guidance data is displayed using a wearable helmet or a head-mounted display, thereby providing the user with an immersive visual experience.

[0057] Step S3, collecting the user's hand motion data, hand pressure data and user limb data in reality and performing positioning.

[0058] Specifically, the user's hand motion data and hand pressure data are collected in real time by handheld devices or wearing data collection gloves; the user's limb data is collected in real time by setting up a position tracking device.

[0059] Specifically, the handheld device or data acquisition glove uses an inertial measurement unit, which is used to collect the user's hand motion data. The inertial measurement unit includes an accelerometer, a gyroscope, and a magnetometer. Among them, the accelerometer measures the acceleration of the object on the x-axis, y-axis, and z-axis, and is used to detect linear changes in motion, such as the swinging speed of the hand; the gyroscope is used to measure angular velocity and can accurately capture the rotation of the object; the magnetometer can sense the earth's magnetic field and assist in determining the direction of the device. A pressure sensor is also provided inside the handheld device or data acquisition glove to collect the user's hand pressure data.

[0060] Specifically, position tracking devices usually have built-in optical sensors to collect user limb data. Optical sensors are based on optical motion capture systems that use multiple cameras to capture markers or body contours on the user from different angles. For example, the user wears special clothing with reflective markers, and the camera captures the position changes of these markers and accurately calculates the position and motion trajectory of the joints through the principle of triangulation.

[0061] In some other embodiments, the position tracking device uses a depth camera-based device to collect user limb data, which can directly obtain the depth information of the scene and identify the user's bone structure and movements.

[0062] Preferably, the hand motion data, hand pressure data and user limb data of the user in reality are located, including placing specific markers on the user's body parts and handheld devices or data acquisition gloves in advance. In the virtual scene, the virtual objects or interaction points corresponding to these markers are pre-set. Several luminous marking points are set on the handheld device or data acquisition gloves, and the positions of these marking points in space are identified by an external optical tracking system, and then the position and posture of the handle in reality are mapped to the corresponding interactive tools in the virtual scene. For example, in this example, auto parts or tools for assembling auto parts.

[0063] Step S4, binding the user's hand motion data, hand pressure data and user limb data to the virtual training scene.

[0064] Specifically, the user's hand motion data, hand pressure data, and user limb data are bound to the virtual training scene, including:

[0065] Step S41, converting the coordinate system in reality into the coordinate system in the virtual scene.

[0066] Specifically, since the reality and the virtual scene have their own coordinate systems. When binding the collected user's hand motion data, hand pressure data and user limb data to the virtual scene, it is necessary to convert the coordinate system, including establishing a mapping relationship to convert the spatial coordinates in reality into coordinates in the virtual scene, such as converting the length in meters and the angle in degrees. In this embodiment, the user's movements in a real activity space of 1 cubic meter are mapped to a virtual space of 10 cubic meters in the virtual scene according to a certain ratio, thereby reducing the venue required for training and reducing training costs.

[0067] Step S42, fusing and calibrating the user's hand motion data, hand pressure data, and user limb data.

[0068] In this embodiment, not only an inertial measurement unit but also a sensor is used to collect the user's motion data. If there are more than two sensors collecting the same data, data fusion is required. The data fusion includes using filtering, weighted averaging and other calculation algorithms to improve the accuracy of the data. In addition, the acquisition equipment and the virtual scene need to be calibrated in the initial stage. For example, when the system starts, the user may need to stand in a specific position or perform some specific actions so that the system can determine that the user's origin position and posture in the real space correspond to the initial state in the virtual scene.

[0069] Step S43, updating and feeding back the user's hand motion data, hand pressure data and user limb data in real time.

[0070] Specifically, the user's hand motion data, hand pressure data, and user limb data need to be bound to the objects in the virtual scene in real time to achieve a smooth interactive experience. For example, when the user's hand is raised in reality, the virtual hand in the virtual scene should also be raised at the same time, and the objects in the virtual scene should respond accordingly based on the user's actions, such as grabbing, pushing, etc. At the same time, the system will also give the user feedback based on the situation in the virtual scene, such as tactile simulation of virtual objects, vibration of the handle, etc., to enhance the user's immersion in the virtual environment.

[0071] Step S5, pre-processing the hand motion data, hand pressure data and user limb data to obtain user training data.

[0072] Specifically, determine a reasonable value range based on the physical meaning of the hand motion data, hand pressure data, and user limb data. For example, when collecting the user's hand motion speed data in the system, if the speed is in meters per second, based on the performance of the device and the physiological limits of human motion, the speed value should be between 0 and a reasonable maximum value, such as 0-10 meters per second. Check each data point in the hand motion data, hand pressure data, and user limb data to see if it is within a predetermined reasonable range. If it is not within the range, mark it as suspected bad data.

[0073] Furthermore, the data is preprocessed based on the internal logical relationship between the data. In the user's limb data, if the position coordinates (x, y, z) of the user's hand and the length of the hand are recorded, where the hand length data is calculated based on the skeleton model, then the coordinates of the hand should be within a reasonable spatial range, which is constrained by the hand length and the overall position of the body. Specifically, logical rules are written in the system to check the relationship between the data, and data points that do not conform to the logical relationship are marked as possible bad data.

[0074] Specifically, for the suspected bad data that has been identified, decide whether to screen it out based on the set threshold. For data points that deviate from the normal range by more than a certain threshold, such as data points that deviate from the mean by more than 3 times the standard deviation, it can be determined as bad data and screened out. Specifically, it includes calculating the statistics of data features, such as the mean, standard deviation, etc., and then writing screening code or using data analysis tools to perform screening operations based on the threshold conditions.

[0075] Step S6, processing and analyzing the user training data and the preset standard training data, and performing real-time scoring and correction.

[0076] Specifically, the user's action position is processed and analyzed, and the position information of the human joints in the user's training data is extracted to calculate the joint angles. For arm movements, the angle relationship between the shoulder joint, elbow joint and wrist joint is calculated. These angles change as the action proceeds, forming an angle feature vector of a time series. For the feature vector corresponding to the joint angle extracted from the user data and the feature vector corresponding to the joint angle in the corresponding preset standard training data, the two data are compared using methods such as cosine similarity, and the similarity is measured by calculating the cosine value of the angle between the two vectors. The closer the cosine value is to 1, the more similar it is. According to the calculated similarity value, scoring can be performed according to certain rules. For example, the similarity value is mapped to a score range of 0-10, and 10 points are given when the distance is 0, indicating complete similarity. When the scoring score is lower than 5 points, the system prompts and corrects the user.

[0077] Furthermore, the user's motion trajectory is processed and analyzed. When the trajectory data of the action in three-dimensional space is collected, the moving trajectory of the hand in the system can be used to extract features of the trajectory. Including features such as the starting point, end point, length of the trajectory, and curvature of the trajectory. The trajectory can also be discretized and represented as a series of spatial coordinate point sequences. Specifically, for trajectory features, a dynamic time warping algorithm can be used to compare the similarity between the trajectory in the user training data and the trajectory in the preset standard training data. The dynamic time warping algorithm can handle situations with different lengths of time series. By finding the optimal matching path between the two trajectories, a distance value is calculated to represent the similarity. And score according to the similarity result, for example, when the similarity is higher than 90%, it is scored above 8 points, and between 60% and 90%, it is scored 3-8 points. When the score is lower than 5 points, the system prompts and corrects the user.

[0078] Step S7, determine whether the current training instruction is completed. If not, return to step S3; if completed, accumulate the scores in step S6 to obtain the test results.

[0079] Specifically, one is when the user manually inputs the training completion instruction, the training instruction is completed, and the scores in step S6 are accumulated to obtain the test results. The other is when the system recognizes that the automobile parts assembly in the current training scene has been completed, the system automatically recognizes that the training has been completed, and the scores in step S6 are accumulated to obtain the test results. Otherwise, it continues to return to step S3.

[0080] The scores in step S6 are accumulated, including assigning a preset weight value to each evaluation indicator according to the relative importance of the actions in the system virtual scene; multiplying the score of each indicator by its corresponding weight to obtain a weighted score; adding the weighted scores of all indicators to obtain a cumulative total score, which is the test score.

[0081] The first embodiment of the present invention generates virtual training scenarios through the system for training, thereby reducing the resources and equipment required for training and saving the costs of training venues, tools and equipment. By training users in a simulated environment, the training efficiency is improved without being restricted by time and space, and the safety risks during operation are reduced, reducing the occurrence of accidents caused by operational errors. By processing and analyzing user training data and preset standard training data, and performing real-time scoring, employees are helped to correct and improve operations, thereby improving the accuracy and quality of the assembly process and being able to enhance the training effect.

[0082] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the process or introducing insignificant designs without changing the core design of its algorithm and process are all within the scope of protection of this patent.

[0083] like Figure 2 As shown, the second embodiment of the present invention relates to a virtual reality-based automobile parts assembly training system, including: a signal receiving module 201, an instruction acquisition module 202, a scene calling module 203, a data acquisition and positioning module 204, a data binding module 205, a data preprocessing module 206, a data processing and analysis module 207, and a judgment and scoring module 208.

[0084] Specifically, the signal receiving module 201 is used to receive the training start signal; the instruction acquisition module 202 is used to obtain the user's personal data collected by the system and the training instructions input by the user; the scene calling module 203 is used to call the guidance data corresponding to the training instructions according to the training instructions input by the user, and generate the corresponding virtual training scene; the data acquisition and positioning module 204 is used to collect the user's hand movement data, hand pressure data and user limb data in reality and locate them; the data binding module 205 is used to bind the user's hand movement data, hand pressure data and user limb data to the virtual training scene; the data preprocessing module 206 is used to preprocess the hand movement data, hand pressure data and user limb data to obtain user training data; the data processing and analysis module 207 is used to process and analyze the user training data and the preset standard training data, and to score and correct them in real time; the judgment and scoring module 208 is used to judge whether the current training instruction is completed. If not, return to the collection step; if completed, accumulate the scores in the previous step to obtain the test score.

[0085] It is not difficult to find that this embodiment is a system embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0086] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0087] A third embodiment of the present invention relates to a network side server, such as Figure 3 As shown, it includes at least one processor 302; and a memory 301 that is communicatively connected to the at least one processor 302; wherein the memory 301 stores instructions that can be executed by the at least one processor 302, and the instructions are executed by the at least one processor 302 so that the at least one processor 302 can execute the above-mentioned data processing method.

[0088] The memory 301 and the processor 302 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 302 and the memory 301 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 302 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor 302.

[0089] The processor 302 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 301 can be used to store data used by the processor 302 when performing operations.

[0090] The fifth embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the automobile parts assembly training method based on virtual reality in the first embodiment when executed by a processor.

[0091] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0092] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the scope of the present invention through the above description. The technical scope of this invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A virtual reality-based automobile parts assembly training method, characterized in that: include: S1, after receiving the training start signal, obtaining the user's personal data collected by the system and the training instructions input by the user; S2, according to the training instruction input by the user, calling the guidance data corresponding to the training instruction and generating a corresponding virtual training scene; S3, collecting the user's hand motion data, hand pressure data and user limb data in reality and positioning them; S4, binding the user's hand motion data, hand pressure data, and user limb data to the virtual training scene; S5, pre-processing the hand motion data, the hand pressure data and the user limb data to obtain user training data; S6, processing and analyzing the user training data and the preset standard training data, and performing real-time scoring and correction; S7, judging whether the current training instruction is completed, if not completed, returning to step S3; If completed, the scores in step S6 are accumulated to obtain the test results.

2. The automobile parts assembly training method based on virtual reality according to claim 1 is characterized in that: In S1, the training instructions include practice operation guidance instructions and test simulation assembly instructions. The practice operation guidance instructions include VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions and parts free assembly operation guidance instructions. The test simulation assembly instructions include simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

3. The automobile parts assembly training method based on virtual reality according to claim 2 is characterized in that: In S2, the training instruction input by the user is any one of VR basic operation guidance instructions, parts assembly operation guidance instructions, parts disassembly operation guidance instructions, parts free assembly operation guidance instructions, simulated parts assembly instructions, simulated parts disassembly instructions and simulated parts free assembly instructions.

4. The automobile parts assembly training method based on virtual reality according to claim 1 is characterized in that: In S3, the user's hand motion data and hand pressure data are collected in real time by using a handheld device or wearing data collection gloves; the user's limb data is collected in real time by setting a position tracking device.

5. The automobile parts assembly training method based on virtual reality according to claim 3 is characterized in that: In S3, the handheld device or data acquisition glove uses an inertial measurement unit, which is used to collect hand motion data of the user. The inertial measurement unit includes an accelerometer, a gyroscope and a magnetometer.

6. The automobile parts assembly training method based on virtual reality according to claim 1 is characterized in that: In S4, the step of binding the user's hand motion data, hand pressure data, and user limb data to the virtual training scene includes: Step S41, converting the coordinate system in reality into the coordinate system in the virtual scene; Step S42, fusing and calibrating the user's hand motion data, hand pressure data, and user limb data; Step S43, updating and feeding back the user's hand motion data, hand pressure data and user limb data in real time.

7. The automobile parts assembly training method based on virtual reality according to claim 6 is characterized in that: In S5, the hand motion data, hand pressure data and user limb data are preprocessed to obtain user training data, including: determining a reasonable value range according to the physical meaning of the hand motion data, hand pressure data and user limb data, and preprocessing the data according to the inherent logical relationship between the data, and for the suspected bad data that has been identified, deciding whether to screen it out according to the set threshold.

8. The automobile parts assembly training system based on virtual reality is characterized by: Applied to the automobile parts assembly training method based on virtual reality described in claim 1, the system comprises: A signal receiving module, used for receiving a training start signal; An instruction acquisition module is used to acquire the user's personal data collected by the system and the training instructions input by the user; A scene calling module is used to call the guidance data corresponding to the training instruction according to the training instruction input by the user, and generate a corresponding virtual training scene; The data collection and positioning module is used to collect the user's hand motion data, hand pressure data and user limb data in reality and perform positioning; Data binding module, used to bind the user's hand motion data, hand pressure data and user limb data to the virtual training scene A data preprocessing module, used for preprocessing hand motion data, hand pressure data and user limb data to obtain user training data; The data processing and analysis module is used to process and analyze user training data and preset standard training data, and to perform real-time scoring and correction; The scoring module is used to determine whether the current training instruction is completed. If not, it returns to the collection step; if completed, the scores in the previous step are accumulated to obtain the test results.

9. A network side server, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the automobile parts assembly training method based on virtual reality according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the automobile parts assembly training method based on virtual reality described in any one of claims 1 to 7 is implemented.

Images