Underground unknown environment multi-target constraint ad hoc network positioning modeling system and method

Abstract

The application discloses a multi-target constraint self-organizing network positioning modeling system and method in an underground unknown environment, and relates to the technical field of positioning modeling in an underground unknown environment.

Description

Technical Field

[0001] This invention relates to the field of positioning technology, specifically to a multi-objective constrained self-organizing network positioning modeling system and method for unknown underground environments. Background Technology

[0002] Traditional tunnel and underground space positioning technologies generally rely on pre-established maps or pre-input target coordinate systems. The target then establishes a connection with these coordinate systems (either through communication or active observation) and calculates its own coordinates using algorithms. However, for exploration of unknown environments or emergency rescue scenarios, pre-modeling or setting target coordinate systems is often not feasible. This necessitates simultaneous modeling and positioning of the target. In such cases, due to accumulated sensor errors, the single-target modeling and positioning effect of fusing multi-source sensor data is not ideal. The technical problems to be solved include: 1. Uncontrollable error accumulation in multi-source data fusion for single-point positioning systems in complex environments; 2. Low efficiency and insufficient battery life for dynamic environment modeling in single-point positioning models in complex environments; 3. Poor system robustness: single-point failure can lead to system crashes; 4. Communication with the outside world in non-pre-deployed environments: Even with a communication module installed, the communication distance between the single target and the ground is limited, preventing deep penetration into unknown environments. Long-distance communication requires pre-establishing a communication network within the environment, which does not meet the needs of exploring unknown environments. Summary of the Invention

[0003] This invention provides a multi-objective constrained self-organizing network positioning modeling system and method for underground unknown environments, in order to solve the above-mentioned technical problems existing in traditional tunnel and underground space positioning technologies.

[0004] According to the first aspect, one embodiment provides a multi-target constrained self-organizing network positioning and modeling system for unknown underground environments, the system including multiple single-point target positioning devices, a central control system and a network transmission system;

[0005] The single-point target positioning device includes a SLAM module, a communication module, an edge computing unit, and a power supply module. The SLAM module includes multi-source sensors, all of which are connected to the edge computing unit. The multi-source sensors are used to perceive information about the unknown underground environment and transmit the information collected by the sensors to the edge computing unit for multi-source data processing and fusion, thereby achieving environmental modeling and positioning. The communication module is used to enable communication between single-point target positioning devices and between the single-point target positioning devices and the ground control system via a self-organizing network.

[0006] The central control system is used to transmit data bidirectionally with each single-point target positioning device through ground and underground communication networks, including acquiring modeling and positioning data sent by the single-point target positioning device, and sending control commands to the single-point target positioning device.

[0007] The network transmission system includes a ground transmission system and an underground transmission system. The ground transmission system includes a tunnel entrance base station and a transmission network from the tunnel entrance base station to the central control system. The underground transmission system includes a network system composed of communication modules on a single-point target positioning device.

[0008] Furthermore, the multi-source sensors include visual sensors, millimeter-wave radar, IMU sensors, and LiDAR.

[0009] Furthermore, the system also includes a single-point target positioning device carrier for transporting the single-point target positioning device to and moving it in an unknown underground environment.

[0010] Furthermore, the system also includes a handheld terminal for bidirectional communication with the single-point target positioning device via ground and underground communication networks, and for performing simple data processing.

[0011] According to a second aspect, one embodiment provides a positioning modeling method for a multi-objective constrained self-organizing network positioning modeling system in an unknown underground environment, the method comprising:

[0012] Multiple single-point target positioning devices enter an unknown underground environment. One or more vehicles are selected according to terrain requirements, the configuration of multi-source sensors is determined according to scene characteristics, and the number of single-point target positioning devices is determined according to the environmental area and the communication range of the single-point target positioning device's communication module.

[0013] Multiple single-point target positioning devices obtain their initial positions by communicating with the tunnel entrance base station. The multiple single-point target positioning devices communicate with each other and obtain their relative positions. Modeling is performed by moving forward.

[0014] During the process, the various point target positioning devices communicate with each other, and their relative positions and the data they collect serve as constraints for modeling and positioning. At the same time, each point target positioning device communicates with the tunnel entrance base station at all times to transmit real-time data.

[0015] During operation, the central control system or handheld terminal can view the status information and acquire data at any time, and can also make real-time adjustments to the work at each point as needed.

[0016] Furthermore, the method also includes:

[0017] When the communication capability between each single-point target positioning device and the base station at the cave entrance is insufficient, one single-point target positioning device is left in place as a relay point, or a single-point target positioning device containing only a power supply and communication module is brought along when entering the cave to serve as a dedicated relay point at necessary locations, while the remaining single-point target positioning devices continue to move forward. When the communication capability is insufficient again, another single-point target positioning device is left as a relay point, and so on.

[0018] Furthermore, the method also includes:

[0019] If a single point target positioning device malfunctions, first determine the location of the corresponding point and the type of malfunction. Based on the type of malfunction and the location, choose whether to abandon the corresponding single point target positioning device in place, continue to use the available functions of the corresponding single point target positioning device, dispatch other single point target positioning devices to the corresponding location to supplement the required functions of the corresponding location, or add a new single point target positioning device from the ground to supplement it.

[0020] Furthermore, the fault types include communication module faults, modeling and positioning faults, and vehicle faults.

[0021] Furthermore, modeling is performed by moving forward, specifically including:

[0022] Multiple single-point target positioning devices are not on the same straight line. They are modeled by forming a planar or three-dimensional shape and moving forward.

[0023] Furthermore, modeling is performed by moving forward, specifically including:

[0024] The advancement methods include: multiple single-point target positioning devices advancing simultaneously, or one or more single-point target positioning devices being fixed first, while other single-point target positioning devices advancing forward, and then the advancing single-point target positioning devices being fixed after stabilization, and then the previously fixed single-point target positioning devices advancing.

[0025] This invention provides a multi-objective constrained self-organizing network positioning and modeling system and method for underground unknown environments. The system includes multiple single-point target positioning devices, a central control system, and a network transmission system. Multi-point collaborative modeling is completed in underground unknown environments through multiple single-point target positioning devices. The multi-objective mutually constrained three-dimensional network-based modeling and positioning method proposed in this invention has higher accuracy than single-objective modeling and positioning. At the same time, multi-machine collaborative modeling also greatly improves efficiency compared to single-point target modeling and positioning. Attached Figure Description

[0026] Figure 1 This is an overall architecture diagram of a multi-objective constrained self-organizing network positioning and modeling system for unknown underground environments, provided in one embodiment of the present invention.

[0027] Figure 2This invention provides a structural diagram of a single-point positioning device in a multi-objective constrained self-organizing network positioning modeling system for unknown underground environments, as an embodiment of the present invention.

[0028] Figure 3 This invention provides a network transmission system diagram for a multi-objective constrained self-organizing network positioning modeling system in an unknown underground environment, as an embodiment of the present invention.

[0029] Figure 4 This is an overall workflow diagram of a multi-objective constrained self-organizing network localization modeling method for unknown underground environments provided in one embodiment of the present invention;

[0030] Figure 5 This is a schematic diagram of a multi-point combination propulsion method in a multi-objective constrained self-organizing network positioning modeling method for unknown underground environments provided in an embodiment of the present invention;

[0031] Figure 6 This is an operation and maintenance flowchart of a multi-objective constrained self-organizing network positioning modeling method for unknown underground environments provided in one embodiment of the present invention. Detailed Implementation

[0032] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0033] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0034] The first embodiment of this invention provides a multi-objective constrained self-organizing network positioning and modeling system for unknown underground environments, such as... Figure 1 As shown, the system includes multiple single-point target positioning devices, a central control system, and a network transmission system.

[0035] In this embodiment, as Figure 2 As shown, the single-point target localization device includes a SLAM module, a communication module, an edge computing unit, and a power supply module.

[0036] In this embodiment, the SLAM module includes multi-source sensors and a spatiotemporal synchronization controller. All multi-source sensors are connected to an edge computing unit, which is composed of a microcomputer and connected to the SLAM module and communication module at that point via wired connections. This edge computing unit is responsible for processing real-time information at that point. It uses multi-source sensors to perceive information about the unknown underground environment and transmits the information collected by the sensors to the edge computing unit for multi-source data processing and fusion, achieving environmental modeling and localization. In this embodiment, the communication module is used to enable communication between single-point target positioning devices and between the single-point target positioning devices and the ground-based central control system via a self-organizing network. The power supply module is responsible for meeting the power needs of the devices at that point.

[0037] In this embodiment, the multi-source sensors include, but are not limited to, visual sensors, millimeter-wave radar, IMU sensors, and LiDAR.

[0038] In this embodiment, the central control system is used to conduct bidirectional data transmission with each single-point target positioning device through ground and underground communication networks. This includes acquiring modeling and positioning data sent by the single-point target positioning devices and sending control commands to them. Specifically, the central control system consists of an integrated server, a scheduling platform, and user terminals. Alternatively, a portable workstation can serve as the central control system. The central control system can conduct bidirectional data transmission with each single-point device through ground and underground communication networks. The single-point devices transmit real-time modeling and positioning data to the central control system. The central control system can further process the data and issue commands to the single-point target devices and vehicles, such as performing focused modeling and image capture at key locations, or stopping at a certain location.

[0039] In this embodiment, as Figure 3 As shown, the network transmission system includes a ground transmission system and an underground transmission system. The ground transmission system includes a base station at the tunnel entrance and a transmission network (either wired or wireless) from the base station to the central control system. The underground transmission system includes a network system composed of communication modules on a single-point target positioning device.

[0040] In this embodiment, the system also includes a single-point target positioning device carrier for transporting the single-point target positioning device to and moving it within an unknown underground environment. Specifically, the carrier can be composed of one or more of the following: manual labor, vehicles, and mobile robots, depending on actual needs. Vehicles include, but are not limited to, construction vehicles, rescue vehicles, maintenance vehicles, and miniature vehicles; mobile robots include, but are not limited to, robot dogs, drones, tracked robots, wheeled robots, and multi-legged robots. The carrier is connected to the single-point edge computing unit via a wired connection and can be controlled by the central control system.

[0041] In this embodiment, the system also includes a handheld terminal, which functions similarly to the central control system. It is used to communicate bidirectionally with the single-point target positioning device through ground and underground communication networks and to perform simple data processing.

[0042] The working process of a single-point target positioning device: When the single-point target positioning device enters a tunnel or underground space, 1) it first communicates with the target base station at the tunnel entrance to obtain its initial position. 2) After entering the unknown underground environment, multi-source sensors use their advantages to perceive the surrounding environment, such as IMU capturing motion status in real time (acceleration, angular velocity), lidar generating high-precision 3D point clouds, and visual cameras extracting texture features. 3) The data information acquired by the multi-source sensors is transmitted to the edge computing node for data preprocessing (denoising filtering, time synchronization, coordinate system transformation). 4) The edge computing node uses algorithms to extract features and model the environment. 5) Through multi-source data fusion algorithms, positioning strategy matching, dynamic weight adjustment, and error compensation are performed to achieve positioning and optimization. 6) The single-point target positioning device's own communication module and communication modules at appropriate distances (including the tunnel entrance base station) form a transmission network. Positioning and modeling information are transmitted to the ground control system and handheld terminals on the ground and underground through the transmission network.

[0043] Based on the aforementioned disclosed multi-objective constrained self-organizing network positioning modeling system for unknown underground environments, this invention also discloses a positioning modeling method for the same system. Figure 4 As shown, the method includes:

[0044] S1. Multiple single-point target positioning devices (including target positioning devices and vehicles) enter an unknown underground environment. One or more vehicles are selected according to terrain requirements. For example, wheeled or tracked vehicles can be selected in flat areas, while multi-legged robots or drones can be selected in complex environments. The configuration of multi-source sensors is determined according to scene characteristics. For example, visual sensors are selected for environments with good lighting conditions, while lidar sensors are selected for environments with clear structural textures. The number of single-point target positioning devices is determined according to the environmental area and the communication range of the single-point target positioning device's communication module, generally not less than 3.

[0045] S2, multiple single-point target positioning devices obtain their initial positions by communicating with the tunnel entrance base station. These devices also communicate with each other to obtain relative positions, and modeling is performed by forward propagation. For example... Figure 5 As shown, multiple single-point targets are not on the same straight line. They are modeled by forming a planar or three-dimensional shape and moving forward. The moving method can be selected as follows: a) multiple targets move forward simultaneously; b) one or more targets are fixed first, and other targets move forward. After the moving targets are stable, they are fixed, and the previously fixed targets move forward again.

[0046] S3, during the advancement process, each single-point target positioning device communicates with each other, and the relative positions between them and the data collected by each other serve as constraints for modeling and positioning. At the same time, each single-point target positioning device communicates with the tunnel entrance base station at all times to transmit real-time data back.

[0047] S4, during operation, the central control system or handheld terminal can view the status information and acquire data at any time (it can acquire the location of a single target, whether the equipment on the single target, including the vehicle, is operating well, the remaining current of the power supply module, the connection status and signal strength of the communication module, information collected by multi-source sensors, data processed by edge nodes, etc.), and can also make real-time adjustments to the work of each point according to the needs.

[0048] S5. When the communication capability between each single-point target positioning device and the tunnel entrance base station is insufficient (the judgment of insufficient communication capability can be based on the pre-set interval distance or the signal reliability threshold, which can be dynamically judged by the system target itself. For example, multiple thresholds can be set to judge the communication strength, such as RSRP signal receiving power, signal quality indicators, capacity and load indicators, network structure indicators, etc., or additional thresholds can be added when the communication quality does not meet the requirements), then one single-point target positioning device is left in place as a relay point, or a single-point target positioning device containing only power supply and communication module is brought along when entering the tunnel to act as a dedicated relay point at the necessary location, and the other single-point target positioning devices continue to move forward. When the communication capability is insufficient again, another single-point target positioning device is left as a relay point, and so on.

[0049] S6. If a single-point target positioning device malfunctions, first determine the location of the corresponding point and the type of malfunction. Based on the malfunction type and location, choose whether to discard the corresponding single-point target positioning device in place, continue using the available functions of the corresponding single-point target positioning device, dispatch other single-point target positioning devices to the corresponding location to supplement the required functions, or add a new single-point target positioning device from the ground to supplement the location. See the maintenance flowchart for specific judgments and operations. Figure 6 As shown, the main content is as follows:

[0050] 1) When the central control or handheld terminal receives an alarm for a single point of failure, check the location of the single point of failure;

[0051] 2) If a single point is located at a relay point, check the fault type. ① Communication module failure and unknown faults require supplementing the communication equipment at that point. It can be manually determined based on the actual situation whether a new communication supplement point is entering from the ground entrance or whether a single point target from the already moving modeling and positioning combination is being relocated to act as a communication relay point. ② If the fault is caused by the positioning and modeling function or the vehicle function, since the relay point does not need to move or model and position temporarily, it can be left unattended.

[0052] 3) If a single point of failure is located at the position of the modeling, positioning, and propulsion assembly, since the assembly still needs to continue advancing and exploring, manual judgment is required based on the actual situation. The decision should be made by adding new equipment at the entrance or abandoning the existing equipment and having the remaining targets become a new assembly to continue advancing. The main criteria for this judgment include whether there are sufficient single-point targets available at the entrance, whether working time is limited and more machines are needed to complete the task quickly, and the expected environmental conditions at the location.

[0053] 4) After all tasks are completed, a manual assessment is made to determine whether to collect the faulty equipment, discard it, or allow the faulty equipment to be destroyed on its own.

[0054] Application example:

[0055] Five single-point targets simultaneously enter an unknown tunnel. Before entering, the five targets complete initial configuration on the central control system and obtain initial position coordinates from the tunnel entrance base station. After entering, the five single-point targets communicate with each other via communication modules and can also communicate in real time with the tunnel entrance base station to transmit information back to the central control system and handheld terminals. The SLAM function of multi-source data fusion for single-point targets models and locates simultaneously. However, since the error of single-point targets is prone to accumulation, the modeling and positioning information of multi-point targets can be mutually constrained through splicing and fusion algorithms, and the optimal result can be obtained by adjusting dynamic thresholds. The principle of mutual constraint among multiple targets is similar to a target entering an unknown environment and being able to locate itself only through its own observation. For example, when entering a room, knowing the coordinates of the door, it knows that it has moved 3 meters to the left and forward at a 45-degree angle and thus obtains its own location. This method is relatively accurate at the beginning, but errors will accumulate over time. When multiple targets enter a room at the same time and know the coordinates of the door, each target moves forward while observing the surrounding environment to obtain its own location. At the same time, it can also observe the positional relationship between other targets and the environment, and can communicate with each other to calculate the distance between them. With more data participating in the solution, and appropriate weights and adjustments, the error will be relatively smaller.

[0056] It should be noted that for a detailed description of the multi-objective constrained self-organizing network positioning and modeling system for unknown underground environments provided in the embodiments of the present invention, please refer to the relevant description of the multi-objective constrained self-organizing network positioning and modeling method for unknown underground environments provided in the embodiments of the present invention, which will not be repeated here.

[0057] Those skilled in the art will understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to achieve the above functions. For example, the program can be stored in the memory of a device, and when the program in the memory is executed by the processor, all or part of the above functions can be achieved. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the program can also be stored in a server, another computer, disk, optical disk, flash drive, or external hard drive, etc., and can be downloaded or copied to the memory of a local device, or the system of the local device can be updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be achieved.

[0058] The above examples illustrate the present invention only to aid in understanding it and are not intended to limit the scope of the invention. Those skilled in the art can make various simple deductions, modifications, or substitutions based on the principles of this invention.

Claims

1. A multi-objective constrained self-organizing network positioning modeling system for unknown underground environments, characterized in that, The system includes multiple single-point target positioning devices, a central control system, and a network transmission system; The single-point target positioning device includes a SLAM module, a communication module, an edge computing unit, and a power supply module. The SLAM module includes multi-source sensors, all of which are connected to the edge computing unit. The multi-source sensors are used to perceive information about the unknown underground environment and transmit the information collected by the sensors to the edge computing unit for multi-source data processing and fusion, thereby achieving environmental modeling and positioning. The communication module is used to enable communication between single-point target positioning devices and between the single-point target positioning devices and the ground control system via a self-organizing network. The central control system is used to transmit data bidirectionally with each single-point target positioning device through ground and underground communication networks, including acquiring modeling and positioning data sent by the single-point target positioning device, and sending control commands to the single-point target positioning device. The network transmission system includes a ground transmission system and an underground transmission system. The ground transmission system includes a tunnel entrance base station and a transmission network from the tunnel entrance base station to the central control system. The underground transmission system includes a network system composed of communication modules on a single-point target positioning device. The system also includes: a single-point target positioning device carrier for transporting the single-point target positioning device to and moving it in an unknown underground environment; multiple single-point target positioning devices entering the unknown underground environment, wherein one or more carriers are selected according to terrain requirements, the configuration of multi-source sensors is determined according to scene characteristics, and the number of single-point target positioning devices is determined according to the environmental area and the communication range of the single-point target positioning device communication module. Multiple single-point target positioning devices obtain their initial positions by communicating with the tunnel entrance base station. The multiple single-point target positioning devices communicate with each other and obtain their relative positions. Modeling is performed by moving forward. During the process, the various point target positioning devices communicate with each other, and their relative positions and the data collected from each other serve as constraints for modeling and positioning. At the same time, each point target positioning device communicates with the tunnel entrance base station at all times to transmit real-time data. During operation, the central control system or handheld terminal can view the status information and acquire data at each point at any time, and can also make real-time adjustments to the work of each point as needed. When the communication capability between each single-point target positioning device and the base station at the tunnel entrance is insufficient, one single-point target positioning device is left in place as a relay point, or a single-point target positioning device containing only power supply and communication modules is brought along when entering the tunnel to act as a dedicated relay point at necessary locations, while the remaining single-point target positioning devices continue to move forward. When the communication capability is insufficient again, another single-point target positioning device is left as a relay point. If a single-point target positioning device malfunctions, the location and fault type of the corresponding point are first determined. Based on the fault type and location, the following options are selected: abandon the corresponding single-point target positioning device in place, continue to use the available functions of the corresponding single-point target positioning device, dispatch other single-point target positioning devices to the corresponding location to supplement the required functions of the corresponding location, or add a new single-point target positioning device from the ground to supplement it.

2. The multi-objective constrained self-organizing network positioning modeling system for unknown underground environments as described in claim 1, characterized in that, The multi-source sensors include visual sensors, millimeter-wave radar, IMU sensors, and LiDAR.

3. The multi-objective constrained self-organizing network positioning modeling system for unknown underground environments as described in claim 1, characterized in that, The system also includes a handheld terminal for bidirectional communication with the single-point target positioning device via ground and underground communication networks, and for performing simple data processing.

4. The multi-objective constrained self-organizing network positioning modeling system for unknown underground environments as described in claim 1, characterized in that, The fault types include communication module faults, modeling and positioning faults, and vehicle faults.

5. The multi-objective constrained self-organizing network positioning modeling system for unknown underground environments as described in claim 1, characterized in that, Modeling is performed by moving forward, specifically including: Multiple single-point target positioning devices are not on the same straight line. They are modeled by forming a planar or three-dimensional shape and moving forward.

6. The multi-objective constrained self-organizing network positioning modeling system for unknown underground environments as described in claim 1, characterized in that, Modeling is performed by moving forward, specifically including: The advancement methods include: multiple single-point target positioning devices advancing simultaneously, or one or more single-point target positioning devices being fixed first, while other single-point target positioning devices advancing forward, and then the advancing single-point target positioning devices being fixed after stabilization, and then the previously fixed single-point target positioning devices advancing.

Images