Networking type way-finding cruising method and loading system

Abstract

The invention provides a networking type path-finding cruise method and a loading system, and the method comprises the steps: collecting target space information through multi-sensor information fusion space recognition positioning equipment, and transmitting the target space information to other loading devices; environment terrain and obstacle information are identified to generate a stereo image; the multi-loading device networking coordination control equipment determines an optimal cruise path according to the three-dimensional image and the position of each loading device; the loading trolley cruise device controls the networking type path-finding loading devices to cruise according to the optimal cruise path; the console updates the target location of each loading device, and determines the optimal cruise path of each loading device cruising to the new cruise target location according to the cruise information and the three-dimensional image; and the loading trolley cruise equipment controls each loading device to cruise according to the optimal cruise path. By the adoption of the method, waste of cruise resources, time resources and labor cost during space cruise is avoided, and meanwhile the cruise efficiency of space cruise is improved.

Description

Technical Field

[0001] The present invention relates to the field of space cruise technology, and in particular to a networked path-finding cruise method and a loading system. Background Art

[0002] With the rapid development of electronic technology, computer and sensor technology, the application and development of intelligent technology has penetrated into various fields. As an important part of the field of intelligent technology, intelligent loading devices are widely used in military and civilian affairs, logistics distribution, post-disaster search and rescue and other fields with their unique advantages, and are used to perform space cruise missions in space areas.

[0003] In the prior art, when a space cruise mission is performed by an intelligent loading device, the device operator usually observes the space environment, plans a cruise route for the intelligent loading device based on the inspection points that need to be passed and the target points that need to be reached according to his experience, and then manually controls the intelligent loading device to move through the remote control device to complete the space cruise mission.

[0004] However, the study found that when planning a cruise route for an intelligent loading device using the above method, the operator may not be able to accurately observe the space environment, analyze and judge the space environment accurately due to the limited observation ability of the operator; at the same time, the operator may be disturbed and affected by lack of experience or subjective factors, which may cause the planned cruise route to not be the optimal route for performing space cruise tasks in the current space environment, resulting in a waste of cruise resources and time resources during the cruise, reducing the cruise efficiency. In addition, since the operator needs to manually control the movement of the intelligent loading device through a remote control device, it will lead to a waste of manpower costs. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a networked path-finding cruise method and a loading system to avoid the waste of cruise resources, time resources and manpower costs during space cruise, while improving the cruise efficiency of space cruise.

[0006] In a first aspect, an embodiment of the present application provides a networked pathfinding cruise method, which is applied to a loading system, wherein the system includes a plurality of networked pathfinding loading devices, each of which includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading trolley cruise device, and a control console, and each of which is networked through its respective multi-loading device networking coordination control device to perform wireless network technology networking, and the method includes:

[0007] Each networked path-finding loading device collects multi-dimensional information of the target space through its multi-sensor information fusion spatial identification and positioning device, and sends the collected multi-dimensional information to other networked path-finding loading devices in the loading system; and performs spatial identification and positioning of the environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information through its multi-sensor information fusion spatial identification and positioning device, and generates a 3D stereoscopic image of the target space;

[0008] Each networked path-finding loading device determines, through its multi-loading device networking coordination control device, a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location according to the 3D stereoscopic image and the initial position of each networked path-finding loading device;

[0009] Each networked path-finding loading device controls the networked path-finding loading device to cruise according to its first optimal cruise path through its loading trolley cruise device, and collects the cruise information of each networked path-finding loading device in real time through its loading trolley cruise device during the cruise process;

[0010] Each networked path-finding loading device updates the first cruising target location of each networked path-finding loading device through its control console to obtain the second cruising target location of each networked path-finding loading device, and determines the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location according to its cruising information and the 3D stereoscopic image through its control console;

[0011] Each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its second optimal cruising path through its loading trolley cruising device.

[0012] Optionally, the multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information; the method further includes:

[0013] Each networked path-finding loading device collects radar information of the target space through its radar sensor;

[0014] Each networked path-finding loading device collects image information of the target space through its image sensor;

[0015] Each networked path-finding loading device collects ultrasonic information of the target space through its ultrasonic sensor;

[0016] Each networked path-finding loading device collects the sound source information of the target space through its sound source sensor.

[0017] Optionally, the performing spatial recognition and positioning of environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space includes:

[0018] Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning;

[0019] According to the environmental terrain and obstacle information in the target space, a 3D stereoscopic image of the target space is constructed using a multi-source information weight mathematical model.

[0020] Optionally, determining a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location according to the 3D stereoscopic image and the initial position of each networked path-finding loading device includes:

[0021] Initializing each cruise point that needs to be passed from the initial position to the first cruise target location;

[0022] According to each cruise point, a first optimal cruise path from the initial position to the first cruise target location is determined based on a global path planning algorithm.

[0023] Optionally, the cruise information includes real-time location information of the networked path-finding loading device and movement information of the networked path-finding loading device; during the cruise process, the method further includes:

[0024] Each networked path-finding loading device determines the obstacle distribution around each networked path-finding loading device through its control console according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image, and determines whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution;

[0025] When it is determined that obstacle avoidance is required, each networked path-finding loading device determines an obstacle avoidance strategy of each networked path-finding loading device through its control console according to its real-time position information and the obstacle distribution;

[0026] Each networked path-finding loading device controls each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy through its loading trolley cruising device.

[0027] In the second aspect, the embodiment of the present application provides a loading system, the system includes a plurality of networked path-finding loading devices, each of which includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading trolley cruising device and a control console, and each networked path-finding loading device is networked by its respective multi-loading device networking coordination control device through wireless network technology:

[0028] The multi-sensor information fusion spatial identification and positioning equipment of each networked path-finding loading device is used to collect multi-dimensional information of the target space and send the collected multi-dimensional information to other networked path-finding loading devices in the loading system; it is also used to perform spatial identification and positioning of the environmental terrain and obstacle information in the target space based on the collected multi-dimensional information and the received multi-dimensional information, and generate a 3D stereoscopic image of the target space;

[0029] A multi-loading device networking coordination control device of each networked path-finding loading device is used to determine a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device;

[0030] The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to cruise according to its first optimal cruise path, and collect the cruise information of each networked path-finding loading device in real time through its loading trolley cruising device during the cruising process;

[0031] The control console of each networked path-finding loading device is used to update the first cruising target location of each networked path-finding loading device to obtain the second cruising target location of each networked path-finding loading device; and is also used to determine the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location according to its cruising information and the 3D stereoscopic image;

[0032] Each group of networked path-finding loading devices may be equipped with a loading trolley cruising device, which is used to control each group of networked path-finding loading devices to cruise according to its second optimal cruising path.

[0033] Optionally, the multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information:

[0034] Each networked path-finding loading device is used to collect radar information of the target space through its radar sensor;

[0035] Each networked path-finding loading device is used to collect image information of the target space through its image sensor;

[0036] Each group of networked path-finding loading devices is used to collect ultrasonic information of the target space through its ultrasonic sensor;

[0037] Each networked path-finding loading device is used to collect the sound source information of the target space through its sound source sensor.

[0038] Optionally, the performing spatial recognition and positioning of environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space includes:

[0039] Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning;

[0040] According to the environmental terrain and obstacle information in the target space, a 3D stereoscopic image of the target space is constructed using a multi-source information weight mathematical model.

[0041] Optionally, determining a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location according to the 3D stereoscopic image and the initial position of each networked path-finding loading device includes:

[0042] Initializing each cruise point that needs to be passed from the initial position to the first cruise target location;

[0043] According to each cruise point, a first optimal cruise path from the initial position to the first cruise target location is determined based on a global path planning algorithm.

[0044] Optionally, the cruise information includes real-time location information of the networked path-finding loading device and movement information of the networked path-finding loading device;

[0045] The control console of each networked path-finding loading device is used to determine the obstacle distribution around each networked path-finding loading device according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image during the cruising process, and determine whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution;

[0046] The control console of each networked path-finding loading device is used to determine the obstacle avoidance strategy of each networked path-finding loading device according to its real-time position information and the distribution of the obstacles when it is determined that obstacle avoidance is required;

[0047] The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy.

[0048] The technical solution provided by this application includes but is not limited to the following beneficial effects:

[0049] The present application is a loading system composed of several networked path-finding loading devices that performs space cruising tasks. Each networked path-finding loading device collects multi-dimensional information of the target space through its multi-sensor information fusion space identification and positioning equipment, sends the collected multi-dimensional information to other networked path-finding loading devices in the loading system, and uses its multi-sensor information fusion space identification and positioning equipment to perform spatial identification and positioning of the environmental terrain and obstacle information in the target space based on the collected multi-dimensional information and the received multi-dimensional information, and generates a 3D stereoscopic image of the target space. It can accurately collect and analyze spatial environmental information to obtain quantitative data for cruising path planning.

[0050] Then, each networked path-finding loading device determines the first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device through its multi-loading device networking coordination control device, and can determine the optimal cruising path based on objective and quantified spatial environment data.

[0051] Next, each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its first optimal cruising path through its loading trolley cruising device, and collects the cruising information of each networked path-finding loading device in real time through its loading trolley cruising device during the cruising process. Each networked path-finding loading device updates the first cruising target location of each networked path-finding loading device through its control console to obtain the second cruising target location of each networked path-finding loading device, and determines the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location through its control console according to its cruising information and the 3D stereoscopic image. The cruising status of the loading device can be monitored in real time when the device is performing a space cruising mission, and when a new cruising mission needs to be performed, its cruising path can be adjusted in time according to the cruising status of the loading device.

[0052] Finally, each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its second optimal cruising path through its loading trolley cruising equipment, so that one or more cruising tasks can be completed without the intervention of operators, avoiding the waste of cruising resources, time resources and manpower costs in space cruising, and improving the cruising efficiency of space cruising.

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 A flow chart of a networked path-finding cruise method provided by the first embodiment of the present invention is shown;

[0056] Figure 2 A schematic diagram of a wireless network technology networking provided by the first embodiment of the present invention is shown;

[0057] Figure 3 The schematic diagram of the structure of the multi-sensor information fusion spatial identification and positioning device is shown;

[0058] Figure 4 A flow chart of a method for generating a stereoscopic image provided by the first embodiment of the present invention is shown;

[0059] Figure 5 A flow chart of a first optimal cruise path determination method provided by Embodiment 1 of the present invention is shown;

[0060] Figure 6 A flowchart of an obstacle avoidance control method provided by Embodiment 1 of the present invention is shown;

[0061] Figure 7 A complete structural schematic diagram of a loading system provided by the first embodiment of the present invention is shown;

[0062] Figure 8 A schematic structural diagram of a loading system provided in the second embodiment of the present invention is shown. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0064] Embodiment 1

[0065] To facilitate understanding of this application, Figure 1 The flowchart of a networked path-finding cruise method provided by the first embodiment of the present invention is shown to describe the contents of the first embodiment of the present application in detail.

[0066] See also Figure 1 As shown, Figure 1 A flowchart of a networked pathfinding and cruising method provided by the first embodiment of the present invention is shown, wherein the method is applied to a loading system, wherein the system includes a plurality of networked pathfinding and loading devices, each of which includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading trolley cruising device, and a control console, see Figure 2 As shown, Figure 2 A schematic diagram of a wireless network technology networking provided by the first embodiment of the present invention is shown, wherein each networked path-finding loading device performs wireless network technology networking through its respective multi-loading device networking coordination control device; the method comprises steps S101 to S105:

[0067] S101: Each networked path-finding loading device collects multi-dimensional information of the target space through its multi-sensor information fusion spatial identification and positioning equipment, and sends the collected multi-dimensional information to other networked path-finding loading devices in the loading system; and performs spatial identification and positioning of the environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information through its multi-sensor information fusion spatial identification and positioning equipment, so as to generate a 3D stereoscopic image of the target space.

[0068] Specifically, with the acceleration of urbanization and the variability of the natural environment, outdoor spatial terrain environment information has become increasingly complex. In addition, there are many interference factors in the complex outdoor natural environment, such as the change of seasons and weather changes. These changes will affect many environmental conditions such as lighting conditions and road conditions, making environmental perception more difficult. Especially under extreme weather conditions, such as heavy rain and fog, the working efficiency and accuracy of sensors will be greatly reduced. This puts higher demands on the spatial terrain environment perception capability of the loading device. In order to effectively collect spatial terrain and environmental information, multi-sensor information fusion spatial recognition and positioning equipment is used to identify spatial terrain environment and obstacle information in complex environments.

[0069] Through the principle of multi-source information complementation and the use of multi-type sensor information fusion mathematical models, comprehensive information such as spatial environment terrain obstacles of the networked path-finding loading device is obtained. At the same time, the multi-sensor random weighted fusion theory is introduced to adaptively adjust the weight of each information source to further improve the accuracy of the loading device's collection of information about surrounding terrain obstacles. This multi-information fusion technology not only expands the loading device's effective identification and positioning of surrounding environment information to a greater extent, but also fully considers the influence of various interference factors in complex environments, and conducts comprehensive design and optimization.

[0070] The spatial identification and positioning of the environmental terrain and obstacle information in the target space can be gradually realized by automatically judging the spatial images collected by the image acquisition device, and judging according to the background of the spatial image and the environmental information characteristics contained. For images with simple backgrounds and rich terrain obstacle feature information, YOLOv7-Tiny is directly used to perform real-time recognition of the loading device image, which improves the speed and flexibility of loading device recognition, and can also maintain a very high frame rate while correctly identifying multiple targets; at the same time, for loading devices in a fast-moving state under complex backgrounds, it is difficult for the image acquisition device mounted on the loading device to ensure that each frame of the image contains clear and visible effective information such as spatial environment, terrain, obstacles, etc., and there may be problems such as blurring, stretching, and blurred contours of the loading device image caused by slow shutter time and abnormal exposure, which greatly weakens the image characteristics of the target. Therefore, the bidirectional long short-term memory network (Bidirectional LSTM) is used to accurately screen the obstacles, icon signals and other information obtained by the recognition; the continuous video frame sequence is used as the recognition object to enhance the recognition effect of moving targets. Recognition of small targets at a distance based on super-resolution convolutional neural networks is a difficult problem in the field of image recognition. The farther the target is, the smaller the proportion of the frame it occupies. For image acquisition devices that acquire images at a fixed resolution, this will cause problems such as low resolution and poor clarity of the target to be detected. Super-resolution convolutional neural networks can reconstruct images of small targets at a distance with super-resolution. The automatic recognition algorithm for loading device images mainly includes three parts: preliminary recognition of loading device targets in images based on the YOLOv7-Tiny target detection method; accurate screening of the identified loading device targets based on the bidirectional long short-term memory network (Bidirectional LSTM); and super-resolution reconstruction of images containing small targets at a distance based on super-resolution convolutional neural networks. Generate a 3D stereo image based on the position and size of the identified environmental terrain and obstacles.

[0071] The algorithm process of radar environment information recognition of the entire loading device can be simply described as follows: start the radar and start scanning the surrounding environment; the radar outputs these data in the form of point clouds or scan lines, which contain the position, speed and angle information of the object; filter the radar data to remove noise and outliers; for example, perform coordinate conversion to convert the radar data from the polar coordinate system to the Cartesian coordinate system for subsequent processing. According to the scanning mode of the radar, interpolate and fill the data to improve the resolution and integrity of the map; extract useful features from the radar data, such as the edges, corners, surface shapes, etc. of the object, and use clustering algorithms (such as DBSCAN, K-means, etc.) to segment the radar point cloud into different objects or areas; use SLAM (simultaneous localization and mapping) technology or occupancy grid method to build a 3D stereo map of the environment.

[0072] S102: Each networked path-finding loading device determines, through its multi-loading device networking coordination control device, a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device.

[0073] Specifically, the Socket protocol is used to realize the signal transmission between the microcomputer and the computer high-level language, and the microcomputer of the multi-loading device networking coordination control device in each networked path-finding loading device controls the cruising of each networked path-finding loading device. The multi-loading device networking coordination control device also includes an execution unit, which is mainly composed of a control unit and a drive unit. The microcomputer determines the first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereo image and the initial position of each networked path-finding loading device, and then outputs the calculation result to the execution unit, which is converted into a motor drive signal to realize the control of the operating state of the loading device, including the forward, backward, left turn, right turn and other operations of the loading device. The microcomputer uses a control algorithm to process the deviations that occur during the operation of the loading device, calculates the deviation value between the arrival coordinates of the loading device and the calculated coordinates and the deviation value of the optimal path of the target position, and then performs PID control according to the deviation, outputs a drive signal, and controls the operation of the loading device more accurately, so that the loading device can cruise more efficiently and run more accurately on the optimal path route.

[0074] S103: Each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its first optimal cruising path through its loading trolley cruising device, and collects the cruising information of each networked path-finding loading device in real time through its loading trolley cruising device during the cruising process.

[0075] Specifically, for each networked path-finding loading device, the networked path-finding loading device controls the networked path-finding loading device to cruise according to its first optimal cruise path through its loading trolley cruise device to perform the original cruise task. During the cruise process, the loading trolley cruise device collects the cruise information of the networked path-finding loading device in real time through the sensor set on the networked path-finding loading device to monitor the cruise state of the networked path-finding loading device.

[0076] S104: Each networked path-finding loading device updates the first cruising target location of each networked path-finding loading device through its control console to obtain the second cruising target location of each networked path-finding loading device, and determines the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location based on its cruising information and the 3D stereoscopic image through its control console.

[0077] Specifically, when a user issues a cruise target modification instruction to a networked routing loading device through the console, the console of the networked routing loading device modifies the first cruise target location of the networked routing loading device to the second cruise target location indicated by the cruise target modification instruction, so as to subsequently re-plan the cruise path for the networked routing loading device.

[0078] In view of the shortcomings of the loading device path planning on the market, such as small range, low efficiency, and poor effect, this system uses multi-sensor information fusion to collect spatial terrain environment and obstacle information characteristics, and constructs a more accurate 3D map with richer environmental spatial terrain and obstacle information characteristics, so that the loading device can perform large-scale mobile inspections within the set range. In view of the path planning problem of the loading device, a corresponding mathematical model is established, and improved path optimization algorithms such as ant colony algorithm and A* algorithm are used to plan the optimal path for the loading device during operation.

[0079] S105: Each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its second optimal cruising path through its loading trolley cruising device.

[0080] Specifically, for each networked path-finding loading device, the networked path-finding loading device controls the networked path-finding loading device to cruise according to its second optimal cruise path through its loading trolley cruising device to perform a new cruise task, thereby achieving the ability to execute multiple cruise tasks in a coherent manner.

[0081] In an optional embodiment, the multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information; the method further includes:

[0082] Each networked path-finding loading device collects radar information of the target space through its radar sensor; each networked path-finding loading device collects image information of the target space through its image sensor; each networked path-finding loading device collects ultrasonic information of the target space through its ultrasonic sensor; each networked path-finding loading device collects sound source information of the target space through its sound source sensor.

[0083] For details, see Figure 3 As shown, Figure 3 A schematic diagram of the structure of a multi-sensor information fusion spatial identification and positioning device is shown, wherein a plurality of radar sensors 1, image sensors 2, ultrasonic sensors 3 and sound source sensors 4 are arranged inside the multi-sensor information fusion spatial identification and positioning device, and their installation positions are shown in the top view of the networked path-finding loading device on the right.

[0084] In an alternative embodiment, see Figure 4 As shown, Figure 4 A flow chart of a stereoscopic image generation method provided by the first embodiment of the present invention is shown, wherein the environmental terrain and obstacle information in the target space are spatially identified and located according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space, including steps S401 to S402:

[0085] S401: Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning.

[0086] S402: Constructing a 3D stereoscopic image of the target space using a multi-source information weight mathematical model according to the environmental terrain and obstacle information in the target space.

[0087] Specifically, for radar sensors, their working principle is mainly based on the emission, reflection and reception of electromagnetic waves. The radar sensor carried by the loading device is one of the main sensors for the loading device to scan the surrounding environment information characteristics, and is usually composed of a transmitter, a receiver and an information processor. First, the radar sensor transmits electromagnetic waves of specific frequency and wavelength to the surrounding environment of the loading device through the transmitter. Then, when the electromagnetic waves encounter the undulating ground, the number of people and pedestrians and other spatial environment terrain obstacle information, they will be reflected to form echoes. The characteristics of these echoes, such as frequency, wavelength and phase, will vary depending on the shape, size and material of the perceived environmental feature information. Subsequently, the receiver will capture these reflected electromagnetic waves and convert them into electrical signals. After amplification, filtering and other processing, these electrical signals will be converted into digital signals for subsequent processing and analysis. Finally, through the signal processing unit, the radar sensor can accurately calculate the distance between the static obstacle and the sensor, as well as the speed and direction of the dynamic obstacle based on the received electromagnetic wave information, and construct a 3D stereo image of the loading device's spatial environment information. In order to determine the distance to the target, the radar accurately measures the delay time t from the moment the electromagnetic wave is emitted to the moment the echo is received. d , this delay time is the propagation time of the electromagnetic wave from the transmitter to the target and then from the target back to the radar receiver. The target distance can be obtained according to the propagation speed of the electromagnetic wave. As the core of the positioning system, the surrounding space environment information can be collected in a variety of ways, such as using millimeter-wave radar (MMW Radar) to build a 3D stereo map of the environment. Optimize the constructed 3D map, such as using filtering algorithms (such as Gaussian filtering, bilateral filtering, etc.) to smooth the map surface. Perform semantic annotation of the map, and mark different areas in the map as roads, buildings, obstacles, etc., so that the intelligent loading device can perform path planning and navigation. As the intelligent loading device moves and the environment changes, the 3D map is updated in real time to maintain its accuracy and integrity.

[0088] In order to improve the accuracy and robustness of environmental perception, millimeter wave radar can be fused with other sensors. Through multi-sensor fusion technology, the advantages of different sensors can be fully utilized to make up for the shortcomings of a single sensor. The constructed 3D map is verified and tested in the actual environment to ensure its accuracy and reliability. The algorithm and parameters are adjusted and optimized according to the test results. In view of the fact that there are many influencing factors in the cruising process of the loading device, the signal is affected by the non-line-of-sight error, and the ranging error of some base stations is large. In this regard, this application designs an adaptive triangulation positioning scheme based on base stations, which can select several base stations with the smallest measurement distance error according to the location of the loading device, and use the three-side positioning algorithm to achieve positioning. When the loading device is in the cruising process, it will match and select the reflector in real time, and achieve positioning according to the distance between the matched reflectors. In the process of calculating the positioning coordinates, the radar must scan and identify the reflector, and use the current position of the reflector as the center of the circle. The radius of the circle is the distance between the loading device and the reflector. Under the premise of knowing the radius and the center of the circle, a circle can be uniquely determined, and the intersection of multiple circles is the current position of the moving train. In the positioning process, by introducing the average difference as the criterion for base station selection, several base stations with the smallest average distance difference are selected, and the position relationship of the two circles in the three-sided positioning algorithm is judged by the Euclidean distance, and the radius of the circle with a large error possibility is corrected in combination with the position judgment coefficient and the average difference. Through the above method, the intersection area of ​​the three circles can be obtained, and the intersection area will not be too large. In order to obtain the specific position of the tag, this application uses the center of the circumscribed circle of the intersection of the three circles as the positioning position of the target. A1, A2, and A3 are the intersection points of the three circles, and point O is the center of the circumscribed circle of A1, A2, and A3. Assuming that the coordinates of A1, A2, and A3 are (x1, y1), (x2, y2), and (x3, y3), respectively, the coordinates of the center of the circumscribed circle are (a, b), where the calculation formula is as follows:

[0089]

[0090] By using sound detection technology, the sound signals emitted during the cruising process of the loading device can be used to effectively identify the spatial terrain environment and obstacle information around the loading device. This method has unique advantages in spatial terrain environment and obstacle information, and provides important value for the research on loading device cruising. Using a microphone array, sound signals in the surrounding environment can be collected to obtain sound source information and spatial information. This information helps to accurately obtain the spatial terrain environment information and obstacle information around the loading device. The core technology of the present invention is to design and implement non-contact ranging and obstacle avoidance using the characteristics of ultrasound for the loading device. First, the ultrasonic sensor emits an ultrasonic pulse signal through the internal transmitter. When the ultrasonic signal encounters an obstacle in front, part of the energy will be reflected back by the obstacle to form a reflected echo. The receiver of the ultrasonic sensor receives the echo signal and converts it into an electrical signal. The built-in microcomputer control system of the loading device records the time difference between the emission of the ultrasonic wave and the reception of the reflected wave. According to the time difference and the propagation speed of the ultrasonic wave, the microcomputer control system can calculate the distance between the sensor and the obstacle, and make obstacle avoidance decisions and provide basic data for building map information and basic data for path planning based on this distance information. At the same time, the ultrasonic sensor will continuously emit ultrasonic waves and receive reflected waves, thereby updating the distance information to obstacles in real time. This enables the loading device to continuously perceive the surrounding environment, realizes non-contact distance measurement and obstacle avoidance functions of the surrounding environment, and improves the safety and reliability of the loading device's cruising.

[0091] The spatial environment terrain and obstacle detection based on the acoustic array is to determine whether there is a loading device and its actual position by collecting sound signals. The sound source positioning system of the loading device based on the microphone array can be composed of multiple subsystems, such as a dual subsystem: Subsystem 1 can use several intelligent microphones to integrate advanced DSP algorithms, including acoustic echo cancellation, beamforming, reverberation, noise suppression and gain control, which can be used to solve the coordinate positioning of the sound source of dynamic moving obstacles and target trajectory tracking; the microphone array of subsystem 2 can be composed of multiple digital microphones, distributed in different directions around, so as to facilitate the identification of sound sources in various directions. You can also add multiple prompt devices similar to LED indicators to indicate the location of the sound source. The PyAI-K210 embedded development platform is a development board designed and developed by 01Studio based on the edge computing chip K210 (RSIC-V architecture, 64-bit dual-core) solution. Connect the microphone array module to the PyAI-K210 using the FPC 10P cable. Through Python programming, the detected sound source information can be displayed in real time on the LCD screen. According to the sound intensity map of the sound source, the displacement and posture attributes of the dynamic obstacle can be determined. The MEMS MIC microphone array and the K210 embedded platform are mainly used to determine the posture attributes of the movement of the obstacle according to the sound intensity map of the detected obstacle. This system combines multiple subsystems and adopts different models of dual-system microphone arrays and different sound source sensors to identify the spatial environment terrain and obstacles, making the system function more comprehensive and complete, and effectively improving the information accuracy of the spatial environment terrain and obstacles, preparing for the next path planning.

[0092] In an alternative embodiment, see Figure 5 As shown, Figure 5 A flowchart of a method for determining a first optimal cruising path provided in the first embodiment of the present invention is shown, wherein the method determines the first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device, including steps S501 to S502:

[0093] S501: Initializing each cruise point that needs to be passed from the initial position to the first cruise target location.

[0094] S502: According to each cruise point, determine a first optimal cruise path from the initial position to the first cruise target location based on a global path planning algorithm.

[0095] Specifically, a corresponding mathematical model is established for the path planning problem of the loading device, and an improved path optimization algorithm such as the ant colony algorithm and the A* algorithm is used to plan a better path for the loading device during operation.

[0096] In an alternative embodiment, see Figure 6 As shown, Figure 6 A flowchart of an obstacle avoidance control method provided by the first embodiment of the present invention is shown, wherein the cruising information includes real-time position information of the networked path-finding loading device and movement information of the networked path-finding loading device; during the cruising process, the method further includes steps S601 to S603:

[0097] S601: Each networked path-finding loading device determines the obstacle distribution around each networked path-finding loading device through its control console according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image, and determines whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution.

[0098] S602: When it is determined that obstacle avoidance is required, each networked path-finding loading device determines an obstacle avoidance strategy for each networked path-finding loading device through its control console according to its real-time position information and the obstacle distribution.

[0099] S603: Each networked path-finding loading device controls each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy through its loading trolley cruising device.

[0100] Specifically, when the loading device runs along the planned path, the sensing device of the loading device will scan the surrounding environment of the loading device in real time and transmit the acquired data to the control system. If there is an obstacle in front of the loading device, the control system will get feedback and determine whether it needs to be avoided based on the distance and position information between the loading device and the obstacle. If it needs to be avoided, the control system will calculate the appropriate direction and speed and send instructions to the execution system. The execution system controls the loading device to make appropriate actions such as turning, braking, moving forward, and moving backward through the instructions of the control system, thereby realizing the function of avoiding obstacles. The mathematical model of the path planning problem of the loading device is shown in Formula (1) to Formula (5).

[0101]

[0102] x ij ∈{0,1},i,j=1,2,…,n,i≠j(5)

[0103] It is assumed that the unmanned vehicle needs to pass through n cruising points. In order to improve the cruising efficiency of the vehicle, each cruising point can only be passed once. The optimal cruising path, that is, the shortest cruising path of the vehicle, needs to be found through the established mathematical model and the corresponding algorithm. Formula (1) represents the objective function of the cruising distance of the unmanned vehicle path planning, where D is the shortest distance to be sought, d ijrepresents the distance between point i and point j in the trajectory of the car, d ij ≥0,d ii = 0; if point i and point j in the motion trajectory are on the desired cruising path, then x ij =1, otherwise x ij =0. ; Formula (2) and Formula (3) indicate that any cruising point in the cruising path of the car can only have one path to enter and exit during a cruising circle; Formula (4) indicates that there is no sub-loop in the generated path, which ensures that each cruising point will not pass through twice during a cruising circle, thereby improving the cruising efficiency of the car. Where {1,2,…,n} represents the set of cruising points, S is a proper subset of {1,2,…,n}, and |S| represents the number of cruising points contained in the set S; Formula (5) represents the variable x ij The value range of x is: If the cruise point (i, j) is on the required cruise path, then x ij =1, otherwise x ij =0.

[0104] In addition, the complete structure of the loading system provided by the present application is described here. Figure 7 As shown, Figure 7 A complete structural schematic diagram of a loading system provided by the first embodiment of the present invention is shown, wherein the networked path-finding device in the loading system includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading cart cruising device and a control console. The multi-sensor information fusion space identification and positioning device includes a laser radar, a high-definition camera, a sound source array and an ultrasonic sensor. The multi-loading device networking coordination control device includes a microcomputer, an execution unit, a communication unit and a battery management unit. The loading cart cruising device includes a GPS module, a path planning, an optimization algorithm unit and an inertial measurement unit. The console includes a data processing module, a display module and a control module. Other power supply equipment and communication equipment can respectively communicate energy and information with each unit module.

[0105] The system involves multiple aspects such as communication technology, network architecture, hardware equipment and software programming. Through the core network, wireless access network, terminal equipment and modulation technology, a wireless network technology communication platform is constructed to realize real-time communication between various networked path-finding loading devices. The core network is responsible for data routing and control, and the wireless access network is responsible for communicating with the terminal equipment and loading devices. It can also use low-cost high-speed optical transmission to reduce interference, reduce power and improve spectrum efficiency. Modulation technology can meet different business needs, improve spectrum utilization, and has the advantages of high efficiency, flexibility and reliability. The wireless network technology communication module in the networked path-finding loading device is configured internally. As a wireless network technology communication module, it mainly includes a radio frequency front-end module, a radio frequency transceiver module and a baseband signal processor, which is responsible for receiving and sending wireless network technology signals, and has high-speed data transmission capabilities and low latency to support real-time communication and remote control between loading devices. At the same time, the networked path-finding loading device is equipped with a vehicle-mounted antenna: used to receive and send wireless signals, it needs to have the characteristics of high sensitivity and low noise to ensure stable signal transmission. This system also uses Raspberry Pi or other microcomputer control platforms to achieve obstacle avoidance, path finding and PID control of the loading device, and drives four motors to control the running status of the loading device, including forward, backward, left turn, right turn and other operations of the loading device. This system adopts a combination of near-end, remote and mobile control to achieve multi-terminal collaborative control. Through wireless network technology networking, multi-terminal data real-time cloud sharing is achieved, management efficiency is improved, and resource waste is reduced. The system can meet the requirements of multi-dimensional integrated identification, detection, positioning, and cruising of loading devices, providing a new means for emergency response to emergencies.

[0106] In terms of system communication networking and cloud sharing, wireless network technology is used to achieve remote control of the loading device and wireless network technology networking between multiple loading devices, building an efficient, flexible and geographically-insensitive communication environment, so that the transmission and sharing of information are no longer restricted by geographical location. At the same time, the connection between the far, near and mobile ends expands the convenience of loading device control, improves the working efficiency of loading, expands the working scene of the console, and can better monitor the operating status of the loading device, making the application scenario of the loading device more flexible and mobile, and making the network planning and adjustment of the loading device more convenient, easy to expand, and convenient and fast. In order to meet the needs of different application scenarios and different user groups in cities, forests and mountainous areas in real environments, this system uses a combination of near-end, far-end and mobile control to achieve the effect of multi-end collaborative control. This system adopts a combination of near-end, far-end and mobile detection, making communication more diversified, receiving richer data, and further improving real-time performance. The near end can detect and observe the changes of various system data in real time and at close range, so as to respond to problems in the system itself; the remote control can communicate through multi-terminal PC connections, analyze and process the collected data by algorithms, issue instructions, and return the output signal to the control end for control operations; the mobile end can check the working status of the system at any time, and the system will also transmit the monitored images to the mobile end in real time, without the need for manual monitoring by the user, thus improving management efficiency, reducing waste of resources, meeting the requirements of multi-dimensional integration and multi-terminal control of loading devices, and adding new means for emergency response to emergencies.

[0107] The loading system provided by the present application can realize networking communication and information sharing between multiple loading devices through 5G and other wireless network technology communications, solve the problem of lack of networking and coordinated communication between multiple loading devices on the platform loading device, and the problem of lack of multi-terminal monitoring of the intelligent loading platform through mobile terminals, near terminals, and remote terminals. It achieves multi-dimensional and comprehensive perception of spatial terrain data and environmental characteristics by carrying multiple types of sensors. At the same time, deep learning is used to solve the problems of unclear sensor information such as image transmission of the loading device in a fast-moving state and poor map construction effect in a complex environment due to the single method of collecting spatial terrain data and environmental characteristics. The loading device can collect spatial terrain data and environmental characteristics under complex backgrounds in multiple aspects and dimensions, obtain more effective environmental information through the built-in weighted algorithm unit, and improve the spatial map construction capability of the intelligent loading device under complex backgrounds; based on this background data, the optimal path to the target position is found through the built-in algorithm unit technology of the optimal path finding function, so that the loading device execution unit can reach the target position accurately and efficiently, solve the problem that the loading device path finding effect is poor and difficult to meet expectations, and greatly improve the mobility and anti-interference of the intelligent loading device in a complex environment, as well as the robustness of the intelligent loading device.

[0108] Embodiment 2

[0109] See also Figure 8 As shown, Figure 8 The schematic diagram of the structure of a loading system provided by the second embodiment of the present invention is shown, wherein the system includes a plurality of networked path-finding loading devices 801, each of which includes a multi-sensor information fusion space identification and positioning device 8011, a multi-loading device networking coordination control device 8012, a loading vehicle cruising device 8013 and a control console 8014, and each of which is networked using a wireless network technology through its respective multi-loading device networking coordination control device:

[0110] The multi-sensor information fusion spatial identification and positioning equipment of each networked path-finding loading device is used to collect multi-dimensional information of the target space and send the collected multi-dimensional information to other networked path-finding loading devices in the loading system; it is also used to perform spatial identification and positioning of the environmental terrain and obstacle information in the target space based on the collected multi-dimensional information and the received multi-dimensional information, and generate a 3D stereoscopic image of the target space;

[0111] A multi-loading device networking coordination control device of each networked path-finding loading device is used to determine a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device;

[0112] The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to cruise according to its first optimal cruise path, and collect the cruise information of each networked path-finding loading device in real time through its loading trolley cruising device during the cruising process;

[0113] The control console of each networked path-finding loading device is used to update the first cruising target location of each networked path-finding loading device to obtain the second cruising target location of each networked path-finding loading device; and is also used to determine the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location according to its cruising information and the 3D stereoscopic image;

[0114] Each group of networked path-finding loading devices may be equipped with a loading trolley cruising device, which is used to control each group of networked path-finding loading devices to cruise according to its second optimal cruising path.

[0115] In an optional embodiment, the multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information:

[0116] Each networked path-finding loading device is used to collect radar information of the target space through its radar sensor;

[0117] Each networked path-finding loading device is used to collect image information of the target space through its image sensor;

[0118] Each group of networked path-finding loading devices is used to collect ultrasonic information of the target space through its ultrasonic sensor;

[0119] Each networked path-finding loading device is used to collect the sound source information of the target space through its sound source sensor.

[0120] In an optional implementation, the spatial identification and positioning of the environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space includes:

[0121] Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning;

[0122] According to the environmental terrain and obstacle information in the target space, a 3D stereoscopic image of the target space is constructed using a multi-source information weight mathematical model.

[0123] In an optional embodiment, determining the first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device includes:

[0124] Initializing each cruise point that needs to be passed from the initial position to the first cruise target location;

[0125] According to each cruise point, a first optimal cruise path from the initial position to the first cruise target location is determined based on a global path planning algorithm.

[0126] In an optional embodiment, the cruise information includes real-time location information of the networked path-finding loading device and movement information of the networked path-finding loading device;

[0127] The control console of each networked path-finding loading device is used to determine the obstacle distribution around each networked path-finding loading device according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image during the cruising process, and determine whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution;

[0128] The control console of each networked path-finding loading device is used to determine the obstacle avoidance strategy of each networked path-finding loading device according to its real-time position information and the distribution of the obstacles when it is determined that obstacle avoidance is required;

[0129] The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0131] The loading system provided in the embodiment of the present invention can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the system provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the system embodiment can refer to the corresponding contents in the aforementioned method embodiment. It can be clearly understood by those skilled in the art that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0132] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0136] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any technician familiar with the field of the present application can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A networked pathfinding cruise method, characterized in that: Applied to a loading system, the system includes a plurality of networked path-finding loading devices, each of which includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading trolley cruising device and a control console, and each of which is networked through its respective multi-loading device networking coordination control device to form a wireless network technology network. The method includes: Each networked path-finding loading device collects multi-dimensional information of the target space through its multi-sensor information fusion spatial identification and positioning device, and sends the collected multi-dimensional information to other networked path-finding loading devices in the loading system; and performs spatial identification and positioning of the environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information through its multi-sensor information fusion spatial identification and positioning device, and generates a 3D stereoscopic image of the target space; Each networked path-finding loading device determines, through its multi-loading device networking coordination control device, a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location according to the 3D stereoscopic image and the initial position of each networked path-finding loading device; Each networked path-finding loading device controls the networked path-finding loading device to cruise according to its first optimal cruise path through its loading trolley cruise device, and collects the cruise information of each networked path-finding loading device in real time through its loading trolley cruise device during the cruise process; Each networked path-finding loading device updates the first cruising target location of each networked path-finding loading device through its control console to obtain the second cruising target location of each networked path-finding loading device, and determines the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location according to its cruising information and the 3D stereoscopic image through its control console; Each networked path-finding loading device controls the cruising of each networked path-finding loading device according to its second optimal cruising path through its loading trolley cruising device.

2. The method according to claim 1, characterized in that: The multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information; the method also includes: Each networked path-finding loading device collects radar information of the target space through its radar sensor; Each networked path-finding loading device collects image information of the target space through its image sensor; Each networked path-finding loading device collects ultrasonic information of the target space through its ultrasonic sensor; Each networked path-finding loading device collects the sound source information of the target space through its sound source sensor.

3. The method according to claim 1, characterized in that The step of spatially identifying and locating the environment terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space includes: Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning; According to the environmental terrain and obstacle information in the target space, a 3D stereoscopic image of the target space is constructed using a multi-source information weight mathematical model.

4. The method according to claim 1, characterized in that: The method of determining a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device comprises: Initializing each cruise point that needs to be passed from the initial position to the first cruise target location; According to each cruise point, a first optimal cruise path from the initial position to the first cruise target location is determined based on a global path planning algorithm.

5. The method according to claim 1, characterized in that The cruise information includes real-time location information of the networked path-finding loading device and movement information of the networked path-finding loading device; During the cruise, the method further includes: Each networked path-finding loading device determines the obstacle distribution around each networked path-finding loading device through its control console according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image, and determines whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution; When it is determined that obstacle avoidance is required, each networked path-finding loading device determines an obstacle avoidance strategy of each networked path-finding loading device through its control console according to its real-time position information and the obstacle distribution; Each networked path-finding loading device controls each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy through its loading trolley cruising device.

6. A loading system, characterized in that: The system includes a plurality of networked path-finding loading devices, each of which includes a multi-sensor information fusion space identification and positioning device, a multi-loading device networking coordination control device, a loading vehicle cruising device and a control console. Each networked path-finding loading device is networked by its own multi-loading device networking coordination control device using wireless network technology: The multi-sensor information fusion space identification and positioning equipment of each networked path-finding loading device is used to collect multi-dimensional information of the target space and send the collected multi-dimensional information to other networked path-finding loading devices in the loading system; It is also used to perform spatial recognition and positioning of environmental terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information, and generate a 3D stereoscopic image of the target space; A multi-loading device networking coordination control device of each networked path-finding loading device is used to determine a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device; The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to cruise according to its first optimal cruise path, and collect the cruise information of each networked path-finding loading device in real time through its loading trolley cruising device during the cruising process; The control console of each networked path-finding loading device is used to update the first cruising target location of each networked path-finding loading device to obtain the second cruising target location of each networked path-finding loading device; and is also used to determine the second optimal cruising path for each networked path-finding loading device to cruise to its second cruising target location according to its cruising information and the 3D stereoscopic image; Each group of networked path-finding loading devices may be equipped with a loading trolley cruising device, which is used to control each group of networked path-finding loading devices to cruise according to its second optimal cruising path.

7. The system according to claim 6, characterized in that The multi-sensor information fusion spatial identification and positioning device includes a radar sensor, an image sensor, an ultrasonic sensor and a sound source sensor; the multi-dimensional information includes radar information, image information, ultrasonic information and sound source information: Each networked path-finding loading device is used to collect radar information of the target space through its radar sensor; Each networked path-finding loading device is used to collect image information of the target space through its image sensor; Each group of networked path-finding loading devices is used to collect ultrasonic information of the target space through its ultrasonic sensor; Each group of networked path-finding loading devices is used to collect the sound source information of the target space through its sound source sensor.

8. The system according to claim 6, characterized in that The step of spatially identifying and locating the environment terrain and obstacle information in the target space according to the collected multi-dimensional information and the received multi-dimensional information to generate a 3D stereoscopic image of the target space includes: Based on the multi-dimensional information, the environmental terrain and obstacle information in the target space are determined using a mathematical model of multi-sensor information fusion positioning; According to the environmental terrain and obstacle information in the target space, a 3D stereoscopic image of the target space is constructed using a multi-source information weight mathematical model.

9. The system according to claim 6, characterized in that The method of determining a first optimal cruising path for each networked path-finding loading device to cruise to its first cruising target location based on the 3D stereoscopic image and the initial position of each networked path-finding loading device comprises: Initializing each cruise point that needs to be passed from the initial position to the first cruise target location; According to each cruise point, a first optimal cruise path from the initial position to the first cruise target location is determined based on a global path planning algorithm.

10. The system according to claim 6, characterized in that The cruise information includes real-time location information of the networked path-finding loading device and movement information of the networked path-finding loading device; The control console of each networked path-finding loading device is used to determine the obstacle distribution around each networked path-finding loading device according to the real-time position information of each networked path-finding loading device and the 3D stereoscopic image during the cruising process, and determine whether each networked path-finding loading device needs to avoid obstacles according to its movement information and the obstacle distribution; The control console of each networked path-finding loading device is used to determine the obstacle avoidance strategy of each networked path-finding loading device according to its real-time position information and the distribution of the obstacles when it is determined that obstacle avoidance is required; The loading trolley cruising device of each networked path-finding loading device is used to control each networked path-finding loading device to avoid obstacles according to its obstacle avoidance strategy.

Images