A vision-based robot intelligent guidance system and method

Abstract

The present invention relates to the field of path planning technology, and specifically discloses a vision-based robot intelligent guidance system and method, the system includes a processing end, which is used to locate a work area; generate a motion trajectory containing a loading position according to the work area, and send the motion trajectory to a vehicle-mounted terminal; receive evaluation information fed back by the vehicle-mounted terminal, and correct the motion trajectory according to the evaluation information; the vehicle-mounted terminal is used to receive the motion trajectory sent by the processing end; obtain loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information. The present invention identifies the workshop image, determines the work area, generates the motion trajectory of the mobile terminal according to the work area, and continuously performs detection during the working process of the mobile terminal, and adjusts the motion trajectory according to the detection results, so that the mobile terminal with problems continues to work at the next work station, and the stop time is minimized as much as possible, thereby improving work efficiency in disguise.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a vision-based robot intelligent guidance system and method. Background Art

[0002] With the popularization of smart devices, many tasks in existing workshops will be completed by smart devices. Some of these smart devices are located at fixed workstations, while others are mobile. Mobile smart devices are generally used for loading and unloading. Due to the complexity of the work, the large number of work instructions, and the high error rate, developers often set up some risk detection modules during its working process, and then build a mobile work framework with detection functions. However, the existing mobile work framework often lacks clear processing procedures after detecting a problem. After detecting a problem, the mobile terminal often stops and remains in a state of pending repair, affecting work efficiency. If the detected problem is caused by external reasons, the stop time of the mobile terminal is a disguised waste of resources. Summary of the invention

[0003] The purpose of the present invention is to provide a vision-based robot intelligent guidance system and method to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A vision-based robot intelligent guidance system, the system comprising:

[0006] The processing end is used to obtain a bird's-eye view image of the workshop, perform content recognition on the bird's-eye view image, and locate the work area; generate a motion trajectory containing a loading position according to the work area, and send the motion trajectory to the vehicle terminal; receive evaluation information fed back by the vehicle terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle terminal;

[0007] The vehicle-mounted terminal is used to receive the motion trajectory sent by the processing end, generate a motion instruction according to the motion trajectory; obtain position information in real time, and generate a stop instruction when the position information coincides with the loading position; establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain the loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information; and upload the evaluation information to the processing end.

[0008] As a further solution of the present invention: the processing end includes:

[0009] A work area positioning module is used to obtain a top view image of the workshop, perform content recognition on the top view image, and locate the work area;

[0010] A trajectory generation and transmission module, used for generating a motion trajectory containing a loading position according to the working area, and transmitting the motion trajectory to the vehicle-mounted terminal;

[0011] The trajectory correction module is used to receive the evaluation information fed back by the vehicle-mounted terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle-mounted terminal.

[0012] As a further solution of the present invention: the vehicle-mounted terminal includes:

[0013] A motion instruction generating module, used for receiving the motion trajectory sent by the processing end, and generating a motion instruction according to the motion trajectory;

[0014] A stop instruction generating module, used for acquiring position information in real time, and generating a stop instruction when the position information coincides with the loading position;

[0015] An evaluation information generation module, used to establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information;

[0016] The data uploading module is used to upload the evaluation information to the processing end.

[0017] As a further solution of the present invention: the work area positioning module includes:

[0018] A contour recognition unit, used to obtain a top view image of the workshop, perform contour recognition on the top view image, and determine the contour of the equipment;

[0019] An image segmentation unit, used to segment the top view image according to the device outline to determine the area to be inspected;

[0020] A color value recognition unit, used for scaling the area to be inspected, performing color value recognition on the scaled area to be inspected, and determining a label outline according to the color value recognition result; wherein the labels are pre-set in the workshop and the color value type of each label is a preset finite value;

[0021] The text recognition unit is used to perform text recognition on the label outline and locate each work area according to the text recognition result.

[0022] As a further solution of the present invention: the trajectory generation and sending module includes:

[0023] A loading position determination unit, used to obtain the text recognition results corresponding to each workspace and determine the loading position according to the file recognition results;

[0024] A starting and ending point determination unit, used to obtain the parking position of the vehicle-mounted terminal, calculate the distance between the parking position and each loading position, and take the loading position with the smallest distance as the movement starting point and the device position with the largest distance as the movement end point;

[0025] A first execution unit is used to input the movement starting point as a source point and the movement end point as an end point into a Dijkstra algorithm model to obtain a movement trajectory;

[0026] Wherein, the loading position and the parking position are both coordinate data.

[0027] As a further solution of the present invention: the evaluation information generation module includes:

[0028] A load prediction unit is used to obtain input information of each detection node in the loading side equipment in real time, input the input information into a trained theoretical loading model, and obtain the load;

[0029] a deviation rate calculation unit, used to compare the loading amount with the actual cargo amount to determine the equipment operation deviation rate;

[0030] an abnormal value calculation unit, used to obtain an audio signal in real time, perform stability analysis on the audio signal, and determine an abnormal value of equipment operation according to the stability analysis result;

[0031] An evaluation score calculation unit, used for inputting the equipment operation deviation rate and the equipment operation abnormality value into a preset evaluation formula to obtain an evaluation score;

[0032] The second execution unit is used to obtain the evaluation score, comparison result and stability analysis result to obtain evaluation information.

[0033] As a further solution of the present invention: the abnormal value calculation unit includes:

[0034] A cutting subunit, used for cutting the audio signal according to a preset progressive audio amplitude to obtain a separation point;

[0035] a conversion subunit, configured to convert the audio signal into an audio segment group according to the separation point;

[0036] A feature extraction subunit, used to obtain a feature value of each audio segment in the audio segment group, and obtain a feature value group corresponding to the audio segment group;

[0037] A comparison subunit, used to compare the characteristic value group with historical data, and determine the abnormal value of equipment operation according to the comparison result;

[0038] The updating subunit is used to update the historical data according to the characteristic value group when the abnormal value of the equipment operation is within a preset abnormal range.

[0039] The technical solution of the present invention also provides a vision-based robot intelligent guidance method, which is applied to a processing end and includes:

[0040] Acquire a bird's-eye view image of the workshop, perform content recognition on the bird's-eye view image, and locate the work area;

[0041] generating a motion trajectory containing a loading position according to the work area, and sending the motion trajectory to the vehicle-mounted terminal;

[0042] Receive evaluation information fed back by the vehicle-mounted terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle-mounted terminal.

[0043] As a further solution of the present invention: the step of obtaining a top view image of a workshop, performing content recognition on the top view image, and locating the work area comprises:

[0044] Acquire a top view image of the workshop, perform contour recognition on the top view image, and determine the contour of the equipment;

[0045] Segment the top view image according to the device outline to determine the area to be inspected;

[0046] Scaling the area to be inspected, performing color value recognition on the scaled area to be inspected, and determining the label outline according to the color value recognition result; wherein the labels are pre-set in the workshop and the color value type of each label is a preset finite value;

[0047] Text recognition is performed on the label outline, and each workspace is located according to the text recognition result.

[0048] As a further solution of the present invention: generating a motion trajectory containing a loading position according to the working area and sending the motion trajectory to the vehicle-mounted terminal comprises:

[0049] Obtain the text recognition results corresponding to each workspace, and determine the loading location based on the file recognition results;

[0050] Obtain the parking position of the vehicle-mounted terminal, calculate the distance between the parking position and each loading position, take the loading position with the smallest distance as the movement starting point, and the device position with the largest distance as the movement end point;

[0051] The starting point of the movement is used as a source point, and the end point of the movement is used as an end point to input into the Dijkstra algorithm model to obtain a movement trajectory;

[0052] Wherein, the loading position and the parking position are both coordinate data.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention identifies the workshop image, determines the work area, generates the motion trajectory of the mobile terminal according to the work area, continuously performs detection during the working process of the mobile terminal, and adjusts the motion trajectory according to the detection results, so that the mobile terminal with problems can continue to work at the next workstation, minimizing the stop time and improving the work efficiency in disguised form; it can be imagined that if there is a problem with the mobile terminal itself, it will perform trial work at each workstation in turn, and as long as there is work that it can complete, the work efficiency is improved in disguised form. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0055] Figure 1 This is a structural block diagram of the processing end in the vision-based robot intelligent guidance system.

[0056] Figure 2 This is a structural block diagram of the vehicle-mounted terminal in the vision-based robot intelligent guidance system.

[0057] Figure 3 This is a structural block diagram of the workspace positioning module in the processing end.

[0058] Figure 4 This is a structural block diagram of the trajectory generation and sending module in the processing end.

[0059] Figure 5 This is a structural block diagram of the evaluation information generation module in the vehicle terminal.

[0060] Figure 6 This is a flowchart of the vision-based robot intelligent guidance method.

[0061] Figure 7 This is the first sub-process flowchart of the vision-based robot intelligent guidance method. DETAILED DESCRIPTION

[0062] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] Example 1

[0064] In an embodiment of the present invention, a vision-based robot intelligent guidance system comprises:

[0065] The processing end is used to obtain a bird's-eye view image of the workshop, perform content recognition on the bird's-eye view image, and locate the work area; generate a motion trajectory containing a loading position according to the work area, and send the motion trajectory to the vehicle terminal; receive evaluation information fed back by the vehicle terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle terminal;

[0066] The vehicle-mounted terminal is used to receive the motion trajectory sent by the processing end, generate a motion instruction according to the motion trajectory; obtain position information in real time, and generate a stop instruction when the position information coincides with the loading position; establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain the loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information; and upload the evaluation information to the processing end.

[0067] The technical solution of the present invention is a system with two ends interacting, namely a processing end and a vehicle-mounted terminal. The function of the processing end is to obtain a workshop image and generate a motion trajectory of the vehicle-mounted terminal based on the workshop image; the function of the vehicle-mounted terminal is to complete its own work under the motion trajectory; during the operation of the vehicle-mounted terminal, loading information is continuously obtained, and the processing end corrects the motion trajectory based on the loading information; the correction process mainly updates the motion trajectory. For example, an unstable loading position can be eliminated from the motion trajectory, and work is first performed at a stable loading position, and finally loading and unloading work based on manual control is uniformly performed at an unstable loading position.

[0068] Figure 1 The structure diagram of the processing end in the vision-based robot intelligent guidance system is shown in FIG. 1 . The processing end 10 includes:

[0069] The work area positioning module 11 is used to obtain a top view image of the workshop, perform content recognition on the top view image, and locate the work area;

[0070] A trajectory generation and transmission module 12, used for generating a motion trajectory containing a loading position according to the working area, and transmitting the motion trajectory to the vehicle-mounted terminal;

[0071] The trajectory correction module 13 is used to receive the evaluation information fed back by the vehicle-mounted terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle-mounted terminal.

[0072] The above content modularizes the various functions of the processing end 10. First, the overhead image of the workshop is obtained through the work area positioning module 11, and the content of the overhead image is recognized. According to the content recognition result, the work area can be located, that is, the area where loading and unloading or other actions need to be performed; the motion trajectory can be determined according to the work area, and the motion trajectory is sent to the vehicle-mounted terminal, and the information obtained by the vehicle-mounted terminal on the motion trajectory is received. Finally, the vehicle-mounted terminal can be corrected based on the obtained information.

[0073] Figure 2 The structure diagram of the vehicle terminal in the vision-based robot intelligent guidance system is shown in FIG. 20 . The vehicle terminal 20 includes:

[0074] A motion instruction generating module 21 is used to receive the motion trajectory sent by the processing end and generate a motion instruction according to the motion trajectory;

[0075] A stop instruction generating module 22, used for acquiring position information in real time, and generating a stop instruction when the position information coincides with the loading position;

[0076] An evaluation information generating module 23 is used to establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information;

[0077] The data uploading module 24 is used to upload the evaluation information to the processing end.

[0078] When the vehicle-mounted terminal 20 receives the motion trajectory sent by the processing end 10, it determines its own motion instructions based on the motion trajectory; when it detects that the vehicle-mounted terminal passes the loading position, it generates a stop instruction. When stopping, the automatic loading robot starts working. While working, it obtains the data generated during the work process in real time. After the vehicle-mounted terminal optimizes the obtained information, it can obtain an evaluation information. The processing end 10 adjusts the motion trajectory based on this evaluation information.

[0079] Figure 3 The following is a structural block diagram of the workspace positioning module in the processing terminal. The workspace positioning module 11 includes:

[0080] The contour recognition unit 111 is used to obtain a top view image of the workshop, perform contour recognition on the top view image, and determine the contour of the equipment;

[0081] An image segmentation unit 112 is used to segment the top view image according to the device outline to determine the area to be inspected;

[0082] A color value recognition unit 113 is used to scale the area to be inspected, perform color value recognition on the scaled area to be inspected, and determine the label outline according to the color value recognition result; wherein the labels are pre-set in the workshop and the color value type of each label is a preset finite value;

[0083] The text recognition unit 114 is used to perform text recognition on the label outline and locate each work area according to the text recognition result.

[0084] The above content describes the process of determining the work area in detail. First, the outline of the overhead image is recognized to determine the equipment outline. The equipment area in the workshop can be determined based on the equipment outline. The corresponding equipment area is eliminated in the overhead image to obtain the area to be inspected. After the area to be inspected, the area to be inspected can be magnified for inspection. The target of the inspection is the preset label. In the workshop, each work area will have a related logo, which is the label. The label is generally a binary label, such as black text on a white background, or blue text on a yellow background. Therefore, the above color value recognition and text recognition processes are not difficult.

[0085] Figure 4 FIG. 1 is a structural block diagram of a trajectory generation and transmission module in a processing terminal. The trajectory generation and transmission module 12 includes:

[0086] The loading position determining unit 121 is used to obtain the text recognition results corresponding to each workspace and determine the loading position according to the file recognition results;

[0087] The starting and ending point determination unit 122 is used to obtain the parking position of the vehicle-mounted terminal, calculate the distance between the parking position and each loading position, and use the loading position with the smallest distance as the movement starting point and the device position with the largest distance as the movement end point;

[0088] A first execution unit 123 is used to input the movement starting point as a source point and the movement end point as an end point into a Dijkstra algorithm model to obtain a movement trajectory;

[0089] Wherein, the loading position and the parking position are both coordinate data.

[0090] The above content describes the trajectory generation process in detail. The principle is to generate the motion trajectory with the help of the Dijkstra algorithm model. The Dijkstra algorithm was proposed by the Dutch computer scientist Dijkstra in 1959, so it is also called the Dijkstra algorithm. It is the shortest path algorithm from one vertex to the rest of the vertices, and solves the shortest path problem in a weighted graph.

[0091] Figure 5 The evaluation information generation module 23 in the vehicle terminal is a structural block diagram of the evaluation information generation module. The evaluation information generation module 23 includes:

[0092] The load prediction unit 231 is used to obtain input information of each detection node in the loading side equipment in real time, input the input information into the trained theoretical loading model, and obtain the load;

[0093] The deviation rate calculation unit 232 is used to compare the loading amount with the actual cargo amount to determine the equipment operation deviation rate;

[0094] An abnormal value calculation unit 233 is used to obtain an audio signal in real time, perform stability analysis on the audio signal, and determine an abnormal value of device operation according to the stability analysis result;

[0095] An evaluation score calculation unit 234, used for inputting the equipment operation deviation rate and the equipment operation abnormality value into a preset evaluation formula to obtain an evaluation score;

[0096] The second execution unit 235 is used to obtain the evaluation score, comparison result and stability analysis result to obtain evaluation information.

[0097] The above content describes the generation process of evaluation information in detail. First, based on the input signals of each node in the loading side, a theoretical load capacity can be calculated, that is, the load capacity of the loading side. By comparing this load capacity with the actual cargo volume, the state of the loading side itself can be determined. On this basis, an audio signal judgment process is added to determine whether abnormal sounds are emitted during the working process of the loading side, and further analyze the state of the loading side; combining the above two dimensions, the state of the loading side can be accurately identified.

[0098] Furthermore, the outlier value calculation unit 233 includes:

[0099] A cutting subunit, used for cutting the audio signal according to a preset progressive audio amplitude to obtain a separation point;

[0100] a conversion subunit, configured to convert the audio signal into an audio segment group according to the separation point;

[0101] A feature extraction subunit, used to obtain a feature value of each audio segment in the audio segment group, and obtain a feature value group corresponding to the audio segment group;

[0102] A comparison subunit, used to compare the characteristic value group with historical data, and determine the abnormal value of equipment operation according to the comparison result;

[0103] The updating subunit is used to update the historical data according to the characteristic value group when the abnormal value of the equipment operation is within a preset abnormal range.

[0104] The above content specifically defines the analysis process of the audio signal. First, the audio signal is converted into multiple audio signals, and the conversion standard is amplitude. Then, the multiple audio signals are subjected to feature extraction. The feature extraction process can be performed with the aid of some commonly used waveform processing algorithms. The specific algorithm is not important, but the important thing is that they need to be unified. Finally, the characteristic value is compared with the historical data to obtain a difference value, that is, the abnormal value of the equipment operation. It is worth mentioning that the historical data is a collection of characteristic value groups. When a new characteristic value group is obtained, when its abnormal value is within a certain range, the historical data is updated; if it exceeds a certain range, the historical data is not updated.

[0105] Example 2

[0106] Figure 6 The flowchart of the vision-based intelligent guidance method of the robot is shown in FIG. 1 . In an embodiment of the present invention, a vision-based intelligent guidance method of the robot is applied to a processing end, and the method includes:

[0107] Step S100: obtaining a top view image of the workshop, performing content recognition on the top view image, and locating the work area;

[0108] Step S200: generating a motion trajectory containing a loading position according to the work area, and sending the motion trajectory to the vehicle-mounted terminal;

[0109] Step S300: receiving evaluation information fed back by the vehicle-mounted terminal, correcting the motion trajectory according to the evaluation information, and sending the corrected motion trajectory to the vehicle-mounted terminal.

[0110] Figure 7 This is a first sub-flow diagram of a vision-based robot intelligent guidance method, wherein the steps of acquiring a top view image of a workshop, performing content recognition on the top view image, and locating a work area include:

[0111] Step S101: obtaining a top view image of a workshop, performing contour recognition on the top view image, and determining the contour of equipment;

[0112] Step S102: segmenting the top view image according to the device outline to determine the area to be inspected;

[0113] Step S103: scaling the area to be inspected, performing color value recognition on the scaled area to be inspected, and determining the label outline according to the color value recognition result; wherein the labels are pre-set in the workshop and the color value type of each label is a preset finite value;

[0114] Step S104: performing text recognition on the label outline, and locating each workspace according to the text recognition result.

[0115] Further, generating a motion trajectory including a loading position according to the working area, and sending the motion trajectory to the vehicle-mounted terminal comprises:

[0116] Obtain the text recognition results corresponding to each workspace, and determine the loading location based on the file recognition results;

[0117] Obtain the parking position of the vehicle-mounted terminal, calculate the distance between the parking position and each loading position, take the loading position with the smallest distance as the movement starting point, and the device position with the largest distance as the movement end point;

[0118] The starting point of the movement is used as a source point, and the end point of the movement is used as an end point to input into the Dijkstra algorithm model to obtain a movement trajectory;

[0119] Wherein, the loading position and the parking position are both coordinate data.

[0120] The functions that can be achieved by the vision-based robot intelligent guidance method are all completed by a computer device, which includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the vision-based robot intelligent guidance method.

[0121] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.

[0122] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0123] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0124] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0125] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.); the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0126] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0127] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0128] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vision-based robot intelligent guidance system, characterized in that: The system comprises: The processing end is used to obtain a bird's-eye view image of the workshop, perform content recognition on the bird's-eye view image, and locate the work area; generate a motion trajectory containing a loading position according to the work area, and send the motion trajectory to the vehicle terminal; receive evaluation information fed back by the vehicle terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle terminal; The vehicle-mounted terminal is used to receive the motion trajectory sent by the processing end, generate a motion instruction according to the motion trajectory; obtain its own position information in real time, and generate a stop instruction when its own position information coincides with the loading position; establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain the loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information; and upload the evaluation information to the processing end; The processing end includes: A work area positioning module is used to obtain a top view image of the workshop, perform content recognition on the top view image, and locate the work area; A trajectory generation and transmission module, used for generating a motion trajectory containing a loading position according to the working area, and transmitting the motion trajectory to the vehicle-mounted terminal; A trajectory correction module, used to receive evaluation information fed back by the vehicle-mounted terminal, correct the motion trajectory according to the evaluation information, and send the corrected motion trajectory to the vehicle-mounted terminal; The workspace positioning module comprises: A contour recognition unit, used to obtain a top view image of the workshop, perform contour recognition on the top view image, and determine the contour of the equipment; An image segmentation unit, used to segment the top view image according to the device outline to determine the area to be inspected; A color value recognition unit, used for scaling the area to be inspected, performing color value recognition on the scaled area to be inspected, and determining a label outline according to the color value recognition result; wherein the labels are pre-set in the workshop and the color value type of each label is a preset finite value; The text recognition unit is used to perform text recognition on the label outline and locate each work area according to the text recognition result.

2. The vision-based robot intelligent guidance system according to claim 1, characterized in that: The vehicle-mounted terminal comprises: A motion instruction generating module, used for receiving the motion trajectory sent by the processing end, and generating a motion instruction according to the motion trajectory; A stop instruction generating module, used for acquiring its own position information in real time, and generating a stop instruction when its own position information coincides with the loading position; An evaluation information generation module, used to establish a connection channel based on the V2X vehicle-mounted terminal and the V2X loading side device, obtain loading information and environmental information in real time, and generate evaluation information according to the loading information and the environmental information; The data uploading module is used to upload the evaluation information to the processing end.

3. The vision-based robot intelligent guidance system according to claim 1, characterized in that: The trajectory generation and sending module comprises: A loading position determination unit, used to obtain text recognition results corresponding to each workspace, and determine the loading position according to the text recognition results; A starting and ending point determination unit, used to obtain the parking position of the vehicle-mounted terminal, calculate the distance between the parking position and each loading position, and take the loading position with the smallest distance as the movement starting point and the device position with the largest distance as the movement end point; A first execution unit is used to input the movement starting point as a source point and the movement end point as an end point into a Dijkstra algorithm model to obtain a movement trajectory; Wherein, the loading position and the parking position are both coordinate data.

4. The vision-based robot intelligent guidance system according to claim 2, characterized in that: The evaluation information generation module includes: A load prediction unit is used to obtain input information of each detection node in the loading side equipment in real time, input the input information into a trained theoretical loading model, and obtain the load; a deviation rate calculation unit, used to compare the loading amount with the actual cargo amount to determine the equipment operation deviation rate; an abnormal value calculation unit, used to obtain an audio signal in real time, perform stability analysis on the audio signal, and determine an abnormal value of equipment operation according to the stability analysis result; An evaluation score calculation unit, used for inputting the equipment operation deviation rate and the equipment operation abnormality value into a preset evaluation formula to obtain an evaluation score; The second execution unit is used to obtain the evaluation score, comparison result and stability analysis result to obtain evaluation information.

5. The vision-based robot intelligent guidance system according to claim 4, characterized in that: The outlier calculation unit comprises: A cutting subunit, used for cutting the audio signal according to a preset progressive audio amplitude to obtain a separation point; a conversion subunit, configured to convert the audio signal into an audio segment group according to the separation point; A feature extraction subunit, used to obtain a feature value of each audio segment in the audio segment group, and obtain a feature value group corresponding to the audio segment group; A comparison subunit, used to compare the characteristic value group with historical data, and determine the abnormal value of equipment operation according to the comparison result; The updating subunit is used to update the historical data according to the characteristic value group when the abnormal value of the equipment operation is within a preset abnormal range.

Images