Multi-joint self-balancing adjusting platform based on inspection unmanned vehicle and use method thereof

Abstract

The invention relates to a self-adaptive landing platform based on a six-wheel independent drive inspection unmanned vehicle and a use method, and the self-adaptive landing platform comprises the six-wheel independent drive inspection unmanned vehicle, an adjustable landing platform, three double-joint supporting arms, a multi-sensor fusion system and other devices. The invention further discloses a multi-source data fusion analysis and adaptive adjustment method in the landing process of the unmanned aerial vehicle. The landing platform is provided with three double-joint supporting arms, and horizontal maintenance of the platform is achieved through posture adjustment of the supporting arms. The system fuses platform six-axis sensors, unmanned aerial vehicle remote sensing topographic data, cameras and unmanned aerial vehicle attitude feedback data, performs analysis and processing by using a deep learning algorithm, and realizes real-time adaptive adjustment of a landing platform through a control system. A stable and safe landing place is provided for the unmanned aerial vehicle in complex environments such as grassland, multi-stage smooth undertaking is achieved, and powerful technical support is provided for application of the unmanned aerial vehicle in complex terrains.

Description

Technical Field

[0001] The present invention relates to the fields of multi-joint self-balancing adjustment, multi-sensor data fusion, deep learning neural network algorithm and UAV precision landing technology, and in particular to a multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle and a use method thereof. Background Art

[0002] With the rapid development of drone technology, its application in industrial inspection, emergency rescue and scientific investigation is becoming more and more extensive. Especially in complex terrain and harsh environment, drones have become a tool with great potential due to their flexibility and efficiency. However, traditional drone landing systems often have difficulty in achieving accurate and safe landing when facing uneven terrain and changing environment, which seriously limits the application effect of drones in complex environments. At the same time, the combination of drone technology and artificial intelligence technology has become a key force in promoting the progress of many industries. The high-definition camera, laser rangefinder and high-performance computing platform carried by drones realize real-time data acquisition and analysis, providing unprecedented possibilities for precise landing and environmental perception.

[0003] Traditional drone landing processes usually rely on a preset landing point and a simple visual navigation system. However, this method often suffers from positioning errors or unstable attitudes when faced with complex terrain. Uneven ground may cause the drone to overturn or be damaged, while bad weather conditions may affect the accuracy of the visual system. These problems not only increase the risk of drone use, but also limit its application scope in special environments.

[0004] In addition, most existing drone landing platforms adopt fixed structures and lack the ability to adapt to complex terrain. Although some studies have tried to use simple adjustable mechanisms, it is still difficult to achieve real-time and accurate attitude adjustment when facing large-angle inclination or rapidly changing terrain. At the same time, how to effectively integrate multi-source sensor data and use deep learning neural network technology for efficient and accurate analysis to improve the landing accuracy and stability of drones in complex environments is still a problem that needs to be solved in the current technological development.

[0005] Therefore, developing a landing platform that can adapt to complex terrain, has real-time self-balancing capabilities, and can intelligently collaborate with drones is of great significance for improving the efficiency and safety of drones in various complex environments. This requires not only solving challenges in hardware design, but also innovations in software algorithms, data fusion, and real-time control to achieve accurate and safe landing of drones in various complex environments. Summary of the invention

[0006] The purpose of the present invention is to provide a multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle and a method of using the same, so as to solve the various problems faced in the above operation scenarios.

[0007] To achieve the above purpose, this application provides the following technical solutions: A multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle, characterized in that it includes: an unmanned vehicle chassis, an adjustable landing platform, a double-joint support arm, and a multi-sensor system. An adjustable landing platform is installed above the unmanned vehicle chassis, and the adjustable landing platform is connected by a fixed bottom plate and the unmanned vehicle chassis. There are three limit slides above the fixed bottom plate, and three double-joint support arms arranged in an equilateral triangle are respectively installed above the slides. The upper ends of the double-joint support arms are fixed to the transparent platform by strong suction cups. The unmanned vehicle chassis is equipped with a lithium battery pack, a high-performance industrial computer, and a main controller; the adjustable landing platform is equipped with a six-axis attitude sensor, a high-definition camera, and a laser rangefinder.

[0008] The lithium battery pack and high-performance industrial computer are fixed on the fixed base plate on the side and connected to the power supply through a power cord. The high-performance industrial computer is connected to the main controller at the edge of the large fixed base plate through a high-speed USB cable for power supply and data transmission. The top of the unmanned vehicle chassis is symmetrically connected and fixed horizontally and vertically by two side long bars and four supporting long bars on the lower side. The two front frame connecting arms are respectively connected and fixed to the two side long bars. The front supporting arm and the middle supporting arm are both connected and fixed to the front-middle arm connecting bar. Two seat bearings are connected and fixed above the front-middle arm connecting bar. The two seat bearings and steel sheet fasteners are penetrated by a steel shaft. The four steel sheet fasteners are respectively fixed to the two front frame connecting arms. Four vertical short bars, four side long bars and four supporting long bars are vertically staggered and fixed to form the overall frame of the back of the unmanned vehicle. The connection and fixation of the above structures are fastened and locked by trapezoidal nuts and the side groove structure of the profile.

[0009] The upper part of the rear support arm of the unmanned vehicle is connected to the long side bar, and the lower part is fixed through four screw holes on the motor support. The motor support and the M3508 motor are fixed through four screw holes on the other side of the motor support, and are connected to the obstacle-crossing tire through the bearing sleeve.

[0010] The double-joint support arm is composed of a high-precision servo motor, an active joint, a driven joint, a universal ball shaft, a force feedback sensor and a strong suction cup, wherein the high-precision servo motor is connected to the main controller and the lithium battery pack respectively through an internal data line to realize power supply and control connection; the high-precision servo motor controls the rotation angle of the active joint and the driven joint, and the connection between the active joint and the driven joint is connected and fixed by a high-precision steering gear, the force feedback sensor monitors the support force in real time and feeds back the data to the main controller through its internal Bluetooth module, the high-precision servo motor and the high-precision steering gear have a self-locking function, in the absence of signal transmission, the high-precision servo motor and the high-precision steering gear have a large torque, and cannot rotate at will, and can only be rotated by the pulse signal sent by the main controller. The universal ball shaft and the strong suction cup are fixed by the inlay of the rubber ball and the groove, and there is a certain pre-tightening force at the connection, which is sufficient to make the drone land smoothly and not shake, and in the default state of the movement of the double-joint support arm, the universal ball shaft remains in a vertical upward direction to follow the movement of the double-joint support arm. The rotation of the universal ball shaft is passively caused by the pull and push forces exerted on the transparent landing platform by the coordinated movement of the double-jointed support arms. The fixed base plate of the adjustable landing platform is a support plate modified from a PCB circuit board. The pins of the three high-precision servo motors, three high-definition cameras and three force feedback sensor electronic components are fixed to the fixed base plate by welding. The main controller, which is also welded on the fixed base plate, realizes power supply and data transmission for the above components and equipment.

[0011] The six-axis attitude sensor is installed at the center position below the adjustable landing platform to monitor the spatial attitude of the platform in real time; the high-definition camera is installed in the space gap between the three double-joint support arms of the platform, fixed in an equilateral triangle position, to capture visual information during the landing of the drone; the laser rangefinder is installed in the center of the platform to accurately measure the distance between the drone and the platform; the slide provides a variety of preset installation positions for the double-joint support arm to facilitate special application requirements. When the unmanned vehicle is moving, the relative position of the limit slide and the double-joint support arm will not change.

[0012] The high-performance industrial computer has a built-in multi-source data fusion algorithm that integrates deep learning and adaptive control algorithms. It processes data from six-axis attitude sensors, high-definition cameras, laser rangefinders, and drone feedback in real time to calculate the optimal platform attitude adjustment strategy.

[0013] During the landing of the drone, the control system first compares the surrounding terrain information with the pre-loaded drone remote sensing data to determine the current terrain. The high-performance industrial computer combined with the six-axis attitude sensor reads and identifies the body attitude data, performs attitude calculation through dynamic weighted fusion, and outputs command information to the main controller, which converts it into PWM pulse information and transmits it to the high-precision servo motor and high-precision steering gear for preliminary attitude adjustment; then, the high-definition camera and laser rangefinder are used to track the landing trajectory of the drone in real time, fine-tune the platform attitude, and when the drone contacts the platform and begins to gradually reduce the rotor speed, the unmanned vehicle control system calculates the spatial motion trajectory of the double-joint support arm based on the force feedback sensor data and the horizontal offset azimuth information of the drone landing, and performs a smooth acceptance of the drone to minimize the landing impact of the drone.

[0014] The high-performance industrial computer is equipped with a real-time fusion analysis algorithm for multi-source data, integrating convolutional neural networks and recursive neural networks to form an end-to-end adaptive control model. It processes data streams from various sensors in real time, predicts the motion trajectory of the UAV, and optimizes the landing platform attitude adjustment strategy to ensure accurate and safe landing of the UAV under complex terrain conditions.

[0015] The end-to-end adaptive control model is implemented using the PyTorch deep learning framework. When extracting features, a multimodal fusion network is used to process data from different sensors: the IMU data of the six-axis attitude sensor is processed through a D convolutional neural network; the high-definition camera image is extracted through a ResNet50 backbone network; the laser rangefinder data is extracted through PointNet++ for point cloud features; and the telemetry data fed back by the drone is processed through an LSTM network. All features are fused through the attention mechanism (SelfAttention) to form a unified feature representation.

[0016] A method for using a multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle comprises the following steps: S1, use the OpenCV library to pre-process the images taken by the three high-definition cameras, including denoising, histogram equalization and normalization; use the PCL library to filter and downsample the laser rangefinder point cloud data; use the Pandas library to perform time synchronization and interpolation processing on the IMU and telemetry data; S2, target detection and tracking: The YOLOv5 algorithm is used to detect drone landings in real time using three HD camera video streams, and the DeepSORT algorithm is used for multi-target tracking. The model is optimized using TensorRT to achieve a real-time processing speed of 30FPS on NVIDIA Jetson AGX Xavier; S3, trajectory prediction: The image parsing data of YOLOv5 and the depth distance data of the laser rangefinder are integrated and input into the sequence-to-sequence model (Seq2Seq with Attention) of the Transformer architecture to predict the trajectory of the drone in the next 5 seconds. The model input is the position and posture data of the past 30 frames, and the output is the predicted 3D coordinate sequence; S4, platform attitude optimization: build a PyTorch-based reinforcement learning environment and use the PPO (Proximal Policy Optimization) algorithm to train the attitude adjustment strategy. The reward function takes into account the transparent landing platform, high-precision servo motor and high-precision steering gear energy consumption and adjustment speed as factors of the reward function; S5, Adaptive Fusion Strategy: Design a dynamic weight allocation mechanism based on Softmax to adaptively adjust the weights of target detection, trajectory prediction, and reinforcement learning strategies according to detection confidence, trajectory prediction error, and current system status; S6, safety constraints: Using the model predictive control method in control theory, the MATLAB Simscape Multibody tool is used to establish a high-precision dynamic model of the platform, and the extended Kalman filter EKF is used to fuse multi-source sensor data to estimate the complete state of the transparent landing platform in real time, including position, attitude, velocity and acceleration. ACADO Toolkit is used to achieve real-time NMPC solution, including the weighted sum of the horizontal error, energy consumption and motion smoothness indicators of the transparent landing platform, set the motion constraints of the high-precision servo motor and high-precision steering gear, ensure that the generated control instructions are within the capabilities of the high-precision servo motor and high-precision steering gear, and make the transparent landing platform motion safe and reliable; S7, real-time optimization: convert the PyTorch model into TensorRT format and deploy it on the Jetson AGX Xavier main control platform; use half-precision (F16P) quantization technology to improve inference speed while ensuring accuracy, use CUDA programming to achieve GPU acceleration of key point cloud processing and matrix operations, use multi-threaded parallel processing strategy to parallelize data preprocessing, target detection, trajectory prediction and control instruction generation tasks, and use ROS2 (Robot Operating System 2) as the software framework to achieve efficient communication and data distribution synchronization between the unmanned vehicle's high-performance industrial computer and the drone's main control module.

[0017] When the drone enters the final landing stage, the control system switches to fine control mode. The high-definition camera and laser rangefinder continue to provide high-frequency position feedback, based on which the platform posture is continuously fine-tuned. The force feedback sensor monitors the contact force in real time, and the control system accurately adjusts the damping coefficient of the double-joint support arm to achieve smooth acceptance.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. High adaptability: The multi-joint self-balancing adjustment mechanism can adapt to various complex terrains, significantly improving the landing success rate of the drone in different environments. The mechanism can quickly adjust the height and angle of the double-joint support arm according to the real-time perceived terrain conditions, providing a stable landing platform for the drone, even in areas with large slopes or irregular terrain.

[0019] 2. Precise control: Through multi-sensor data fusion and deep learning algorithms, precise control of the drone landing process is achieved, greatly improving the safety and stability of landing. The control system can calculate the optimal landing path and posture in real time, and ensure that the drone can land accurately on the platform through visual guidance and wireless communication.

[0020] 3. High degree of intelligence: Using advanced artificial intelligence technology, the system can learn and optimize autonomously, and continuously improve its performance in complex environments. By analyzing historical data through machine learning algorithms, the control system can predict potential landing risks and formulate more reasonable landing strategies.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] Figure 1 It is a schematic diagram of the structure of an unmanned inspection vehicle and a multi-joint self-balancing adjustment platform in one embodiment of the present invention; Figure 2 A schematic diagram of the structure of a control system and related components in one embodiment of the present invention; Figure 3 This is a schematic structural diagram of a multi-joint self-balancing adjustment platform in one embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of the unmanned vehicle chassis in one embodiment of the present invention; Figure 5 A schematic diagram of a system operation technical flow in one embodiment of the present invention; The meaning of each symbol in the accompanying drawings: 1-Unmanned vehicle chassis. 2-Adjustable landing platform, 3-Dual joint support arm, 4-Multi-sensor system; 1-1 lithium battery pack, 1-2 industrial computer, 1-3 main controller, 1-4 side long bar, 1-5 rear support arm, 1-6 obstacle tire, 1-7 front frame connecting arm, 1-8 seat bearing, 1-9 steel shaft, 1-10 front-middle arm connecting bar, 1-11 steel sheet fastener, 1-12 motor support, 1-13 bearing sleeve, 1-14 middle support arm, 1-15 M3508 motor, 1-16 front support arm, 1-17 long support bar, 1-18 short vertical bar.

[0024] 2-1 fixed bottom plate, 2-2 limited slide, 2-3 strong suction cup, 2-4 transparent landing platform; 3-1 high-precision servo motor, 3-2 active joint, 3-3 driven joint, 3-4 universal ball shaft, 3-5 force feedback sensor, 3-5-1 Bluetooth module, 3-6 high-precision steering gear; 4-1- six-axis attitude sensor, 4-2- high-definition camera, 4-3- laser rangefinder. DETAILED DESCRIPTION

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0028] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0029] The technical solution of the embodiment of the present application will be described below in conjunction with the drawings in the embodiment of the present application.

[0030] A multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle, characterized in that it includes: an unmanned vehicle chassis 1, an adjustable landing platform 2, a double-joint support arm 3, a multi-sensor system 4, and an adjustable landing platform 2 is installed above the unmanned vehicle chassis 1, the adjustable landing platform 2 is inlaid and linked with the unmanned vehicle chassis 1 through a fixed bottom plate 2-1, three limit slide grooves 2-2 are arranged above the fixed bottom plate 2-1, three double-joint support arms 3 arranged in an equilateral triangle are respectively installed above the slide grooves 2-2, and the upper ends of the double-joint support arms 3 are fixed to the transparent platform 2-4 by strong suction cups 2-3. The unmanned vehicle chassis 1 is equipped with a lithium battery pack 1-1, a high-performance industrial computer 1-2, and a main controller 1-3; the adjustable landing platform 2 is equipped with a six-axis attitude sensor 4-1, a high-definition camera 4-2 and a laser rangefinder 4-3.

[0031] The lithium battery pack 1-1 and the high-performance industrial computer 1-2 are fixed on the side of the fixed base plate 2-1 and connected to the power supply through a power cord. The high-performance industrial computer 1-2 is connected to the main controller 1-3 at the edge of the large fixed base plate 2-1 through a high-speed USB cable for power supply and data transmission. The top of the unmanned vehicle chassis 1 is symmetrically connected and fixed horizontally and vertically by two side long bars 1-4 and four supporting long bars 1-17 on the lower side. The two front frame connecting arms 1-7 are respectively connected and fixed to the two side long bars 1-4. The front supporting arm 1-16 and the middle supporting arm 1-14 are both connected and fixed to the front-middle arm connecting bar 1-10. Two seat bearings 1-8 are connected and fixed above the front-middle arm connecting bar 1-10. The two seat bearings 1-8 and the steel sheet fasteners 1-11 are penetrated by a steel shaft 1-9. The four steel sheet fasteners 1-11 are respectively fixed to the two front frame connecting arms 1-7. Four vertical short bars 1-18, four side long bars 1-4 and four supporting long bars 1-17 are vertically staggered and fixed to form the overall frame of the back of the unmanned vehicle. The connection and fixation of the above structures are all fastened and locked by trapezoidal nuts and the side groove structure of the profile.

[0032] The rear support arm 1-5 of the unmanned vehicle is connected to the side long bar 1-4 at the top and fixedly connected at the bottom through four screw holes on the motor support 1-12. The motor support 1-12 and the M3508 motor 1-15 are fixed through four screw holes on the other side of the motor support 1-12 and connected to the obstacle-crossing tire 1-6 through the bearing sleeve 1-13.

[0033] The double-joint support arm 3 is composed of a high-precision servo motor 3-1, an active joint 3-2, a driven joint 3-3, a universal ball shaft 3-4, a force feedback sensor 3-5 and a strong suction cup 3-6, wherein the high-precision servo motor 3-1 is connected to the main controller 1-3 and the lithium battery pack 1-1 respectively through internal data lines to achieve power supply and control connection; the high-precision servo motor 3-1 controls the rotation angle of the active joint 3-2 and the driven joint 3-3, and the connection between the active joint 3-2 and the driven joint 3-3 is fixedly connected with a high-precision steering gear 3-6, and the force feedback sensor 3-5 monitors the support force in real time and transmits the feedback data through its internal Bluetooth module 3-5-1 The main controller 1-3, the high-precision servo motor 3-1 and the high-precision steering gear 3-6 all have a self-locking function. In the absence of signal transmission, the high-precision servo motor 3-1 and the high-precision steering gear 3-6 have a large torque and cannot rotate at will. The rotation can only be controlled by the pulse signal sent by the main controller 1-3. The universal ball shaft 3-4 and the strong suction cup 2-3 are fixed by the inlay of rubber balls and grooves. There is a certain pre-tightening force at the connection, which is enough to make the drone land smoothly without shaking. In the default state of the movement of the double-joint support arm 3, the universal ball shaft 3-4 remains in the vertical upward direction and follows the movement of the double-joint support arm 3. The rotation of the universal ball shaft 3-4 is passively caused by the pull-thrust force of the three double-joint support arms 3 on the transparent landing platform 2-4 when they move in coordination. The fixed base plate 2-1 of the adjustable landing platform 2 is a support plate modified from a PCB circuit board. The pins of the three high-precision servo motors 3-1, three high-definition cameras 4-2 and three force feedback sensors 3-5 electronic components are fixed on the fixed base plate 2-1 by welding. The main controller 1-3, which is also welded on the fixed base plate 2-1, realizes power supply and data transmission for the above-mentioned components and equipment.

[0034] The six-axis attitude sensor 4-1 is installed at the center position below the adjustable landing platform 2 to monitor the spatial attitude of the platform in real time; the high-definition camera 4-2 is installed in the space gap between the three double-joint support arms 3 of the platform, fixed in an equilateral triangle position, and is used to capture visual information during the landing of the UAV; the laser rangefinder 4-3 is installed at the center position of the platform to accurately measure the distance between the UAV and the platform; the slide 2-2 provides a variety of preset installation positions for the double-joint support arm 3 to facilitate special application requirements. When the unmanned vehicle is moving, the relative position of the limit slide 2-2 and the double-joint support arm 3 will not change.

[0035] The high-performance industrial computer 1-2 has a built-in multi-source data fusion algorithm, which integrates deep learning and adaptive control algorithms, and processes data from the six-axis attitude sensor 4-1, the high-definition camera 4-2, the laser rangefinder 4-3 and the drone feedback in real time to calculate the optimal platform attitude adjustment strategy.

[0036] During the landing of the drone, the control system first compares the surrounding terrain information with the pre-loaded drone remote sensing data to determine the current terrain. The performance industrial computer 1-2 reads and identifies the vehicle posture data in combination with the six-axis attitude sensor 4-1, performs attitude solution through dynamic weighted fusion, and outputs command information to the main controller 1-3, which is converted into PWM pulse information and transmitted to the high-precision servo motor 3-1 and high-precision steering gear 3-6 for preliminary attitude adjustment. Subsequently, the high-definition camera 4-2 and the laser rangefinder 4-3 are used to track the landing trajectory of the drone in real time, and the platform attitude is fine-tuned. When the drone contacts the platform and begins to gradually reduce the rotor speed, the unmanned vehicle control system calculates the spatial motion trajectory of the double-joint support arm 3 based on the force feedback sensor 3-5 data and the horizontal offset azimuth information of the drone landing, and performs a smooth acceptance of the drone to minimize the landing impact of the drone.

[0037] The high-performance industrial computer 1-2 is equipped with a real-time fusion analysis algorithm for multi-source data, which integrates convolutional neural networks and recursive neural networks to form an end-to-end adaptive control model. It processes data streams from various sensors in real time, predicts the motion trajectory of the UAV, and optimizes the landing platform attitude adjustment strategy to ensure accurate and safe landing of the UAV under complex terrain conditions.

[0038] The end-to-end adaptive control model is implemented using the PyTorch deep learning framework. When extracting features, a multimodal fusion network is used to process different sensor data: the IMU data of the six-axis attitude sensor is processed through a 1D convolutional neural network; the high-definition camera image is extracted through the ResNet50 backbone network; the laser rangefinder data is extracted through PointNet++ for point cloud features; and the telemetry data fed back by the drone is processed through the LSTM network. All features are fused through the attention mechanism (Self-Attention) to form a unified feature representation.

[0039] A method for using a multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle comprises the following steps: S1, use the OpenCV library to pre-process the images taken by the three high-definition cameras 4-2, including denoising, histogram equalization and normalization; use the PCL library to filter and downsample the laser rangefinder point cloud data; use the Pandas library to perform time synchronization and interpolation processing on the IMU and telemetry data; S2, target detection and tracking: The YOLOv5 algorithm is used to detect drone landing in real time using 4-2 video streams from three high-definition cameras, and the DeepSORT algorithm is used for multi-target tracking. The model is optimized through TensorRT, achieving a real-time processing speed of 30FPS on NVIDIA Jetson AGX Xavier; S3, trajectory prediction: The image parsing data of YOLOv5 and the depth distance data of the laser rangefinder 4-3 are integrated and input into the sequence-to-sequence model (Seq2Seq with Attention) of the Transformer architecture to predict the trajectory of the drone in the next 5 seconds. The model input is the position and posture data of the past 30 frames, and the output is the predicted 3D coordinate sequence; S4, platform attitude optimization: build a PyTorch-based reinforcement learning environment and use the PPO (Proximal Policy Optimization) algorithm to train the attitude adjustment strategy. The reward function takes into account the energy consumption and adjustment speed of the transparent landing platform 2-4 degrees, the high-precision servo motor 3-1 and the high-precision steering gear 3-6 as factors of the reward function; S5, Adaptive Fusion Strategy: Design a dynamic weight allocation mechanism based on Softmax to adaptively adjust the weights of target detection, trajectory prediction, and reinforcement learning strategies according to detection confidence, trajectory prediction error, and current system status; S6, safety constraints: using the model predictive control method in control theory, using the MATLAB SimscapeMultibody tool to establish a high-precision dynamic model of the platform, using the extended Kalman filter (EKF) to fuse multi-source sensor data, real-time estimation of the complete state of the transparent landing platform 2-4, including position, attitude, velocity and acceleration, and using ACADOToolkit to achieve real-time NMPC solution, including the weighted sum of the horizontal error, energy consumption and motion smoothness indicators of the transparent landing platform 2-4, setting the motion constraints of the high-precision servo motor 3-1 and the high-precision steering gear 3-6, ensuring that the generated control instructions are within the capabilities of the high-precision servo motor 3-1 and the high-precision steering gear 3-6, so that the transparent landing platform 2-4 can move safely and reliably; S7, real-time optimization: convert the PyTorch model into TensorRT format and deploy it on the Jetson AGX Xavier main control platform; use half-precision (FP16) quantization technology to improve the inference speed while ensuring accuracy, use CUDA programming to achieve GPU acceleration of key point cloud processing and matrix operations, adopt multi-threaded parallel processing strategy to parallelize data preprocessing, target detection, trajectory prediction and control instruction generation tasks, and use ROS2 (Robot Operating System 2) as the software framework to achieve efficient communication and data distribution synchronization between the unmanned vehicle's high-performance industrial computer 1-2 and the drone's main control module.

[0040] When the drone enters the final landing stage, the control system switches to fine control mode. The high-definition camera and laser rangefinder continue to provide high-frequency position feedback, based on which the platform posture is continuously fine-tuned. The force feedback sensor monitors the contact force in real time, and the control system accurately adjusts the damping coefficient of the double-joint support arm to achieve smooth acceptance.

Claims

1. A multi-joint self-balancing adjustment platform based on an inspection unmanned vehicle, characterized in that: include: An unmanned vehicle chassis (1), an adjustable landing platform (2), a double-joint support arm (3), and a multi-sensor system (4); the unmanned vehicle chassis (1) is equipped with an adjustable landing platform (2); the adjustable landing platform (2) is connected to the unmanned vehicle chassis (1) by being inlaid with a fixed bottom plate (2-1); three limit slide grooves (2-2) are arranged above the fixed bottom plate (2-1); three double-joint support arms (3) arranged in an equilateral triangle are respectively installed above the slide grooves (2-2); the upper ends of the double-joint support arms (3) are fixed to the transparent platform (2-4) by adsorption via strong suction cups (2-3); the unmanned vehicle chassis (1) is equipped with a lithium battery pack (1-1), an industrial computer (1-2), and a main controller (1-3); and the adjustable landing platform (2) is equipped with a six-axis attitude sensor (4-1), a high-definition camera (4-2), and a laser rangefinder (4-3).

2. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 1 is characterized in that: The top of the unmanned vehicle chassis (1) is symmetrically connected and fixed by two side long bars (1-4) and four supporting long bars (1-17) at the lower side in a horizontal and vertical manner. Two front frame connecting arms (1-7) are respectively connected and fixed to the two side long bars (1-4). The front supporting arm (1-16) and the middle supporting arm (1-14) are both connected and fixed to the front-middle arm connecting bar (1-10). Two seat bearings (1-8) are connected and fixed above the front-middle arm connecting bar (1-10). A steel shaft (1-9) penetrates the two seat bearings (1-8) and a steel sheet fastener (1-11). The four steel sheet fasteners (1-11) are respectively fixed to the two front frame connecting arms (1-7). Four vertical short bars (1-18), four side long bars (1-4) and four supporting long bars (1-17) are vertically staggered and connected and fixed to form an overall frame of the back of the unmanned vehicle.

3. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 2 is characterized in that: The rear support arm (1-5) is connected to the side long bar (1-4) at the top and fixedly connected at the bottom through four screw holes on the motor support (1-12). The motor support (1-12) and the M3508 motor (1-15) are fixed through four screw holes on the other side of the motor support (1-12) and connected to the obstacle-crossing tire (1-6) through the bearing sleeve (1-13).

4. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 3 is characterized in that: The double-joint support arm (3) is composed of a high-precision servo motor (3-1), an active joint (3-2), a driven joint (3-3), a universal ball shaft (3-4), a force feedback sensor (3-5) and a strong suction cup (2-3), wherein the high-precision servo motor (3-1) is respectively connected to a main controller (1-3) and a lithium battery pack (1-1) through an internal data line to achieve power supply and control connection; the high-precision servo motor (3-1) controls the rotation angle of the active joint (3-2) and the driven joint (3-3), the connection between the active joint (3-2) and the driven joint (3-3) is connected and fixed by a high-precision steering gear (3-6), and the force feedback sensor (3-5) monitors the support force in real time and sends feedback data to the main controller through its internal Bluetooth module (3-5-1). The controller (1-3), the high-precision servo motor (3-1) and the high-precision steering gear (3-6) all have a self-locking function. In the absence of signal transmission, there is a large torque at the high-precision servo motor (3-1) and the high-precision steering gear (3-6). The universal ball shaft (3-4) and the strong suction cup (2-3) are fixed by rubber balls and grooves. There is a certain pre-tightening force at the connection, which is sufficient to make the drone land smoothly without shaking. In the default state of the movement of the double-joint support arm (3), the universal ball shaft (3-4) maintains a vertical upward direction and follows the movement of the double-joint support arm (3); the rotation of the universal ball shaft (3-4) is passively triggered by the pull-thrust force of the three double-joint support arms (3) acting on the transparent landing platform (2-4) when they move in coordination.

5. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 4 is characterized in that: The fixed base plate (2-1) of the adjustable landing platform (2) is a support plate modified from a PCB circuit board. The pins of the electronic components of three high-precision servo motors (3-1), three high-definition cameras (4-2) and three force feedback sensors (3-5) are fixed to the fixed base plate (2-1) by welding. The main controller (1-3) which is also welded to the fixed base plate (2-1) realizes power supply and data transmission for the components.

6. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 5 is characterized in that: The six-axis attitude sensor (4-1) is installed at the center position below the adjustable landing platform (2) to monitor the spatial attitude of the platform in real time; A high-definition camera (4-2) is installed in the space gaps between the three double-joint support arms (3) of the platform, and is fixed in an equilateral triangle position, and is used to capture visual information during the landing of the UAV; a laser rangefinder (4-3) is installed at the exact center of the platform, and is used to accurately measure the distance between the UAV and the platform; the slide groove (2-2) provides a plurality of preset installation positions for the double-joint support arm (3), so as to facilitate the response to special application requirements; when the unmanned vehicle is moving, the relative position of the limit slide groove (2-2) and the double-joint support arm (3) will not change.

7. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 6 is characterized in that: The industrial computer (1-2) has a built-in multi-source data fusion algorithm, which integrates deep learning and adaptive control algorithms, processes data from a six-axis attitude sensor (4-1), a high-definition camera (4-2), a laser rangefinder (4-3) and feedback from a drone in real time, and calculates an optimal platform attitude adjustment strategy.

8. The multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 7 is characterized in that: During the landing process of the UAV, the control system first compares the surrounding terrain information with the pre-loaded UAV remote sensing data to determine the terrain at the current location. The industrial control computer (1-2) reads and recognizes the vehicle body posture data in combination with the six-axis attitude sensor (4-1), performs attitude calculation through dynamic weighted fusion, outputs command information to the main controller (1-3), and the main controller (1-3) converts it into PWM pulse information and transmits it to the high-precision servo motor (3-1) and the high-precision steering gear (3-6) for preliminary attitude adjustment. Subsequently, the high-definition camera (4-2) and the laser rangefinder (4-3) are used to track the landing trajectory of the UAV in real time and fine-tune the platform attitude. When the UAV contacts the platform and begins to gradually reduce the rotor speed, the unmanned vehicle control system calculates the spatial motion trajectory of the double-joint support arm (3) based on the force feedback sensor (3-5) data and the horizontal offset azimuth information of the landing of the UAV, and performs a smooth acceptance of the UAV to minimize the landing impact of the UAV.

9. A method for using the multi-joint self-balancing adjustment platform based on the inspection unmanned vehicle according to claim 7, characterized in that: The industrial control computer (1-2) is configured with a multi-source data real-time fusion analysis algorithm, which integrates a convolutional neural network and a recursive neural network to form an end-to-end adaptive control model, processes data streams from various sensors in real time, predicts the motion trajectory of the drone, optimizes the landing platform attitude adjustment strategy, and ensures accurate and safe landing of the drone under complex terrain conditions; The end-to-end adaptive control model is implemented using the PyTorch deep learning framework. During feature extraction, a multimodal fusion network is used to process data from different sensors: the IMU data of the six-axis attitude sensor is processed using an ID convolutional neural network; the high-definition camera image is subjected to feature extraction using the ResNet50 backbone network; the laser rangefinder data is subjected to point cloud feature extraction using PointNet++; the telemetry data fed back by the drone is processed using an LSTM network, and all features are fused through an attention mechanism to form a unified feature representation.

10. The method according to claim 9, characterized in that The steps include: S1, data preprocessing: use the OpenCV library to preprocess the image, including denoising, histogram equalization and normalization; use the PCL library to filter and downsample the laser rangefinder point cloud data; use the Pandas library to perform time synchronization and interpolation processing on IMU and telemetry data; S2, target detection and tracking: the YOLOv5 algorithm is used to detect the drone landing in real time using three high-definition cameras (4-2), and the DeepSORT algorithm is used for multi-target tracking; Model optimization through TensorRT achieves real-time processing speed of 30FPS on NVIDIA Jetson AGX Xavier; S3, trajectory prediction: Fuse the image parsing data of YOLOv5 and the depth distance data of the laser rangefinder (4-3), and input them into the sequence-to-sequence model of the Transformer architecture to predict the trajectory of the drone in the next 5 seconds. The model input is the position and posture data of the past 30 frames, and the output is the predicted 3D coordinate sequence; S4, platform attitude optimization: build a PyTorch-based reinforcement learning environment and use the PPO algorithm to train the attitude adjustment strategy; the reward function takes into account the transparent landing platform (2-4), the energy consumption and adjustment speed of the high-precision servo motor (3-1) and the high-precision steering gear (3-6); S5, Adaptive Fusion Strategy: Design a dynamic weight allocation mechanism based on Softmax to adaptively adjust the weights of target detection, trajectory prediction, and reinforcement learning strategies according to detection confidence, trajectory prediction error, and current system status; S6, safety constraints: using the model predictive control method in control theory, using the MATLAB Simscape Multibody tool to establish a high-precision dynamic model of the platform, using the extended Kalman filter to fuse multi-source sensor data, and real-time estimation of the complete state of the transparent landing platform (2-4), including position, attitude, velocity and acceleration, and using ACADO Toolkit to achieve real-time NMPC solution, including the weighted sum of the horizontal error, energy consumption and motion smoothness indicators of the transparent landing platform (2-4), setting the motion constraints of the high-precision servo motor (3-1) and the high-precision steering gear (3-6), ensuring that the generated control instructions are within the capabilities of the high-precision servo motor (3-1) and the high-precision steering gear (3-6), so that the transparent landing platform (2-4) can move safely and reliably; S7, real-time optimization: convert the PyTorch model into TensorRT format and deploy it on the Jetson AGX Xavier main control platform; use half-precision quantization technology to improve inference speed while ensuring accuracy, use CUDA programming to achieve GPU acceleration of key point cloud processing and matrix operations, use multi-threaded parallel processing strategy to parallelize data preprocessing, target detection, trajectory prediction and control instruction generation tasks, and use ROS2 as the software framework to achieve efficient communication and data distribution synchronization between the unmanned vehicle industrial computer (1-2) and the drone main control module.

Images