Radar vision fusion emergency deformation monitoring rapid deployment system and method

Abstract

The invention discloses a radar vision fusion emergency deformation monitoring rapid deployment system and method. The system comprises a clamp arm system, a crawler-type mobile chassis and a control system. The clamp arm system is used for automatically clamping and screwing monitoring equipment and accurately adjusting the angle and the direction of the equipment; the crawler-type mobile chassis has autonomous navigation capability and adapts to complex terrains; and the control system is used for automatically planning a path, identifying an optimal mounting point and remotely controlling an equipment deployment process. The method comprises the following steps: S1, path planning and navigation; s2, equipment transportation; s3, automatic installation is carried out; s4, remote monitoring and debugging are carried out; s5, adaptive adjustment is carried out; and S6, result calculation is carried out. According to the invention, intelligent transportation, precise installation and automatic debugging of the monitoring equipment are realized, and the deployment efficiency and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of landslide emergency monitoring and rescue, and particularly to a radar-vision fusion emergency deformation monitoring rapid deployment system and method. Background Art

[0002] After geological disasters such as landslides and collapses occur, it is necessary to quickly deploy monitoring equipment to obtain on-site deformation data and evaluate disaster risks.

[0003] At present, the "radar-vision integration" monitoring technology that combines radar SAR, millimeter-wave radar and optical vision LiDAR, industrial cameras has been widely used in landslide deformation monitoring. However, under complex terrain conditions, manual handling and installation of monitoring equipment are inefficient, inaccurate, and pose safety hazards.

[0004] The existing equipment deployment methods mainly rely on manual labor or simple machinery, and have the following problems:

[0005] (1) Low efficiency: Traditional manual installation of monitoring equipment takes a long time and is difficult to meet emergency requirements;

[0006] (2) Insufficient stability: The installation positions of monitoring equipment are unstable and are easily affected by factors such as terrain and climate, affecting data accuracy;

[0007] (3) Low degree of automation: The transportation, fixation, and debugging processes of equipment highly rely on manual labor and lack intelligent control;

[0008] Therefore, it is crucial to develop a monitoring system and method that can quickly and stably deploy the "radar-vision integration" landslide deformation. Summary of the Invention

[0009] In view of this, the present invention provides a radar-vision fusion emergency deformation monitoring rapid deployment system and method.

[0010] To solve the above technical problems, the present invention adopts the following technical solutions:

[0011] A radar-vision fusion emergency deformation monitoring rapid deployment system includes: a clamp arm system, a crawler mobile chassis, and a control system; wherein,

[0012] The clamp arm system is used to automatically clamp and tighten the monitoring equipment, and precisely adjust the angle and orientation of the equipment;

[0013] The crawler mobile chassis has autonomous navigation capabilities and can adapt to complex terrains;

[0014] The control system is used to automatically plan paths, identify the best installation points, and remotely control the equipment deployment process.

[0015] Preferably, the crawler mobile chassis includes an environmental perception system and an autonomous navigation module;

[0016] Among them, the environmental perception system is used to achieve obstacle avoidance and terrain adaptation.

[0017] Preferably, the environmental perception system integrates lidar, IMU, and ultrasonic sensors.

[0018] Preferably, the system further includes a torque measurement and control system, which is used to monitor the bolt tightening torque in real time to ensure the stable installation of the equipment and avoid loosening or over-tightening.

[0019] Preferably, the clamp arm system includes a hydraulic clamp head and a robotic arm.

[0020] Preferably, the control system is based on AI decision-making algorithms and 5G / LoRa communication.

[0021] A method for rapid deployment of radar-vision fusion emergency deformation monitoring includes the following steps:

[0022] Step S1: Path planning and navigation

[0023] The trolley autonomously identifies the landslide area through SLAM technology and plans the optimal travel path;

[0024] Step S2: Equipment transportation

[0025] Transport the radar-vision integrated monitoring equipment through a stable clamping structure and avoid obstacles;

[0026] Step S3: Automatic installation

[0027] The robotic arm adjusts the equipment posture according to the preset parameters;

[0028] The hydraulic clamp head accurately fixes the monitoring equipment;

[0029] The torque measurement and control system ensures that the bolt tightening torque meets the standard;

[0030] Step S4: Remote monitoring and debugging

[0031] Utilize 5G / LoRa wireless communication to remotely adjust the equipment angle, align it with the target monitoring area, and perform data transmission;

[0032] Step S5: Adaptive adjustment

[0033] The system intelligently adjusts the monitoring angle and parameters according to the deformation monitoring data to optimize the data acquisition effect;

[0034] Step S6: Perform result calculation.

[0035] Preferably, in the step S6, it includes deformation amount calculation and system deployment time calculation; among them,

[0036] The deformation amount Δ is obtained by weighted fusion of the radar ranging value and the visual displacement data:

[0037] Δ = α·Δ_radar + β·Δ_vision

[0038] Among them,

[0039] α and β are weight coefficients, α = 0.6, β = 0.4, based on the optimized result of baseline network adjustment;

[0040] Δ_radar = |d1 - d0|, d0 is the initial distance, and d1 is the real-time measurement value;

[0041] Δ_vision is calculated by the feature point matching algorithm, and the formula is:

[0042] Δ_vision = ∑(x_i - x_i') 2 / n

[0043] Among them, i ranges from 1 to n feature points;

[0044] The system deployment time T is related to the manipulator motion parameters:

[0045] T = t_calibration + (h_max / v_lift) + (θ / ω)

[0046] Among them, t_calibration is the sensor calibration time, with a default of 120s;

[0047] h_max is the target height, unit: meter;

[0048] v_lift is the lifting speed, 0.5m / s, referring to the lifting drive mechanism;

[0049] θ is the angle adjustment amount, unit: radian;

[0050] ω is the rotational angular velocity, 1.2rad / s.

[0051] The present invention has achieved the following technical effects compared with the prior art:

[0052] (1) The present invention can automatically identify the best installation point and achieve unmanned rapid deployment;

[0053] (2) The torsion measurement and control system of the present invention can ensure the stable installation of the equipment and improve the reliability of long-term monitoring;

[0054] (3) The tracked / wheeled mobile platform of the present invention combines AI navigation to achieve all-terrain operation;

[0055] (4) The present invention supports remote debugging and data transmission, improving the efficiency of disaster monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a system structure diagram of a rapid deployment system and method for radar-vision fusion emergency deformation monitoring according to the present invention;

[0057] Figure 2 It is a device deployment flowchart of a rapid deployment system and method for radar-vision fusion emergency deformation monitoring according to the present invention;

[0058] Figure 3 It is a schematic diagram of the torque measurement and control system of a rapid deployment system and method for radar-vision fusion emergency deformation monitoring according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0060] As Figure 1 shown, the present invention discloses a rapid deployment system for radar-vision fusion emergency deformation monitoring, including: a clamping arm system, a crawler mobile chassis, and a control system; wherein,

[0061] The clamping arm system uses a hydraulic chuck in cooperation with a robotic arm to automatically clamp and tighten monitoring devices such as millimeter-wave radars, LiDARs, etc., and precisely adjust the angles and orientations of the devices;

[0062] The crawler mobile chassis uses a crawler or wheeled chassis and has autonomous navigation capabilities to adapt to complex terrains;

[0063] The control system is based on an AI decision-making algorithm to automatically plan paths, identify the best installation points, and remotely control the device deployment process.

[0064] The crawler mobile chassis includes an environmental perception system and an autonomous navigation module;

[0065] Among them, the environmental perception system is used to achieve obstacle avoidance and terrain adaptation.

[0066] The environmental perception system integrates lidar, IMU, and ultrasonic sensors.

[0067] The system also includes a torque measurement and control system, which is used to monitor the bolt tightening torque in real time to ensure the stable installation of the device and avoid loosening or over-tightening.

[0068] The clamp arm system includes a hydraulic clamp head and a robotic arm.

[0069] The control system includes an AI decision-making algorithm and 5G / LoRa communication.

[0070] As Figure 2 shown, the present invention discloses a rapid deployment method for radar-vision fusion emergency deformation monitoring, including the following steps:

[0071] Step S1: Path planning and navigation

[0072] The trolley uses SLAM technology to autonomously identify the landslide area and plan the optimal travel path;

[0073] Step S2: Equipment transportation

[0074] Transport the radar-vision integrated monitoring equipment through a stable clamping structure and avoid obstacles;

[0075] Step S3: Automatic installation

[0076] The robotic arm adjusts the equipment posture according to preset parameters;

[0077] The hydraulic clamp head accurately fixes the monitoring equipment;

[0078] The torque measurement and control system ensures that the bolt tightening torque meets the standard;

[0079] Step S4: Remote monitoring and debugging

[0080] Use 5G / LoRa wireless communication to remotely adjust the equipment angle, align with the target monitoring area, and perform data transmission;

[0081] Step S5: Adaptive adjustment

[0082] The system intelligently adjusts the monitoring angle and parameters according to the deformation monitoring data to optimize the data acquisition effect;

[0083] Step S6: Perform result calculation;

[0084] Including the calculation of the deformation amount and the calculation of the system deployment time;

[0085] Among them,

[0086] The deformation amount Δ is obtained by weighted fusion of the radar ranging value and the visual displacement data:

[0087] Δ = α·Δ_radar + β·Δ_vision

[0088] Among them,

[0089] α and β are weight coefficients, α = 0.6, β = 0.4, based on the optimization result of baseline network adjustment;

[0090] Δ_radar = |d1 - d0|, where d0 is the initial distance and d1 is the real-time measured value;

[0091] Δ_vision is calculated by the feature point matching algorithm, and the formula is:

[0092] Δ_vision = ∑(x_i - x_i') 2 / n

[0093] where i ranges from 1 to n feature points;

[0094] The system deployment time T is related to the robotic arm motion parameters:

[0095] T = t_calibration + (h_max / v_lift) + (θ / ω)

[0096] where t_calibration is the sensor calibration time, with a default of 120 s;

[0097] h_max is the target height, unit: meter;

[0098] v_lift is the lifting speed, 0.5 m / s, referring to the lifting drive mechanism;

[0099] θ is the angle adjustment amount, unit: radian;

[0100] ω is the rotational angular velocity, 1.2 rad / s.

[0101] As Figure 3 shown, it is the schematic diagram of the torsion measurement and control system of the present invention.

[0102] Example 1:

[0103] After a landslide disaster occurs, the quick-deployment landslide monitoring equipment has the clamp arm trolley automatically go to the designated monitoring point, use the hydraulic clamp head to hold the millimeter-wave radar equipment, precisely adjust the installation position with the robotic arm, and fix the equipment through the torsion measurement and control system; after the deployment is completed, the equipment uploads the monitoring data in real time to provide support for landslide risk early warning.

[0104] Example 2:

[0105] For the real-time monitoring system installation in the collapse area, the clamp arm trolley transports the LiDAR monitoring equipment to the target position, automatically avoids obstacles and completes the equipment installation, and then remotely adjusts the equipment scanning angle to achieve three-dimensional deformation monitoring of the collapse area.

[0106] The present invention is applicable to scenarios such as geological disaster emergency monitoring, slope stability monitoring in mining areas, dam settlement monitoring, etc., and is particularly suitable for the rapid deployment of equipment in high-risk environments such as landslides and collapses, providing technical support for geological disaster early warning and emergency response.

[0107] Thus, through the integration of a clamp arm trolley, a radar-vision integrated monitoring device, AI intelligent control, and remote communication technology, the present invention realizes the rapid, stable, and intelligent deployment of geological disaster monitoring equipment, improving the response speed and data reliability of the monitoring system.

[0108] The above are only preferred embodiments of the present invention, and do not impose any limitation on the technical scope of the present invention. Therefore, any minor modifications, equivalent changes, and decorations made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A rapid deployment system for radar-vision fusion emergency deformation monitoring, characterized in that, It includes: A clamp arm system, a crawler mobile chassis, and a control system; among them, The clamp arm system is used to automatically clamp and tighten the monitoring device, and precisely adjust the angle and orientation of the device; The crawler mobile chassis has autonomous navigation capabilities and can adapt to complex terrains; The control system is used to automatically plan the path, identify the best installation point, and remotely control the device deployment process.

2. The rapid deployment system for emergency deformation monitoring by radar-vision fusion according to claim 1, wherein, The crawler mobile chassis includes an environmental perception system and an autonomous navigation module; Among them, the environmental perception system is used to achieve obstacle avoidance and terrain adaptation.

3. The rapid deployment system for radar-vision fusion emergency deformation monitoring according to claim 2, characterized in that, The environmental perception system integrates lidar, IMU, and ultrasonic sensors.

4. A rapid deployment system for radar-vision fusion emergency deformation monitoring according to claim 1, characterized in that The system also includes a torque measurement and control system, which is used to monitor the bolt tightening torque in real time, ensure the stable installation of the device, and avoid loosening or over-tightening.

5. A rapid deployment system for radar-vision fusion emergency deformation monitoring according to claim 1, characterized in that, The clamp arm system includes a hydraulic clamp head and a robotic arm.

6. The rapid deployment system for radar-vision fusion emergency deformation monitoring according to claim 1, wherein, The control system is based on AI decision-making algorithms and 5G / LoRa communication.

7. A rapid deployment method for radar-vision fusion emergency deformation monitoring, characterized in that, It includes the following steps: Step S1: Path planning and navigation The trolley uses SLAM technology to autonomously identify the landslide area and plan the optimal travel path; Step S2: Equipment transportation Transport the radar-vision integrated monitoring device through a stable clamping structure and avoid obstacles; Step S3: Automatic installation The robotic arm adjusts the device posture according to preset parameters; The hydraulic clamp head precisely fixes the monitoring device; The torque measurement and control system ensures that the bolt tightening torque meets the standard; Step S4: Remote monitoring and debugging Use 5G / LoRa wireless communication to remotely adjust the device angle, align with the target monitoring area, and perform data transmission; Step S5: Adaptive adjustment The system intelligently adjusts the monitoring angle and parameters according to the deformation monitoring data to optimize the data acquisition effect; Step S6: Perform result calculation.

8. A rapid deployment method for radar-vision fusion emergency deformation monitoring according to claim 7, characterized in that In the said step S6, it includes the calculation of the deformation amount and the calculation of the system deployment time; among them, The deformation amount Δ is obtained by weighted fusion of the radar ranging value and the visual displacement data: Δ = α·Δ_radar + β·Δ_vision Where, α and β are weight coefficients, α = 0.6, β = 0.4, based on the optimized results of baseline network adjustment; Δ_radar = |d1 - d0|, d0 is the initial distance, d1 is the real-time measurement value; Δ_vision is calculated by the feature point matching algorithm, and the formula is: Δ_vision = ∑(x_i - x_i') 2 / n Where, i = 1 to n feature points; The system deployment time T is related to the motion parameters of the robotic arm: T = t_calibration + (h_max / v_lift) + (θ / ω) Where, t_calibration is the sensor calibration time, default 120s; h_max is the target height, unit: meter; v_lift is the lifting speed, 0.5m / s, referring to the lifting drive mechanism; θ is the angle adjustment amount, unit: radian; ω is the rotational angular velocity, 1.2rad / s.

Images