26 results about "Visual navigation system" patented technology

The invention discloses a new energy automobile logistics transfer robot based on visual navigation and an implementation method, relates to the field of logistics automation and intelligent equipment, and solves the problems that traditional equipment is low in navigation precision, difficult in data fusion and weak in obstacle avoidance capability. The transferring robot body comprises Mecanum wheels, supporting legs, an intelligent temperature control battery bin, a visual navigation system, a core control center, an interactive touch screen and a mechanical arm. The core control center comprises an image acquisition module, a data processing module, a path planning module and a transfer control module; all the modules work cooperatively, the automation and intelligence level of logistics transfer is remarkably improved, and powerful support is provided for the new energy automobile logistics industry.

The invention discloses an AR digital reconstruction and visual navigation system and method for an agricultural cultural heritage scene. The system comprises a digital modeling module, a scene recognition module, an AR reconstruction module, a path navigation module and an interactive navigation module. According to the invention, by fusing laser point cloud, unmanned aerial vehicle images and historical images, agricultural cultural heritage scenes such as rice terraces, mulberry-based fish ponds, waterwheel irrigation systems and the like with extremely high local characteristics are reconstructed, historical scenes in which natural or human factors disappear are recovered, and AR live-action is superposed with virtual farming behaviors, traditional festival activities and clothing styles and features, so that the real-scene and real-scene virtual farming is realized. A user can experience thousand years of agricultural culture personally on the scene, the visiting experience that the user cannot understand and cannot see completely in the past is changed, an exclusive route is planned for the user, various interaction modes such as voice, images and gestures are supported, and the method is suitable for users of different age groups, language backgrounds and cultural cognition levels.

This invention provides a fruit stalk clamping and shearing agricultural robot and its harvesting control method. The robot includes a control cabinet, a robotic arm, and a visual navigation system mounted on a tracked chassis support platform. The control cabinet contains a host computer control system and a slave computer control system. A movable end effector with an identification and positioning system and a supplementary lighting device is installed at the end of the robotic arm. The movable end effector can flexibly adapt to the harvesting needs of different crops and complex working conditions. The host computer control system combines data collected by a depth camera and LiDAR, and uses the YOLOv8-MC model to identify target crops and their key points in the images, significantly improving the crop identification accuracy in complex environments, reducing the probability of missed or incorrect harvesting, and minimizing damage to the fruit. When constructing a global map, the host computer control system performs depth correction and map optimization for changes in illumination, further improving the robot's path planning and operational accuracy.

The invention relates to an anesthesia puncture visual navigation system combining augmented reality and three-dimensional reconstruction, and belongs to the technical field of anesthesia puncture visual navigation. The anesthesia puncture visual navigation system comprises a physiological movement monitoring unit used for simultaneously collecting respiratory movement cycle data and soft tissue elastic deformation information; a comprehensive motion state data packet is generated by calculating the correlation coefficient of the breathing amplitude and the tissue elasticity modulus change rate, the space deviation caused by breathing motion and soft tissue deformation of a patient to puncture navigation can be effectively compensated, the puncture precision is remarkably improved compared with a traditional static navigation system under the normal breathing state of the patient, and the puncture accuracy is improved. The puncture failure rate and the complication risk are effectively reduced, the problem that precision is further deteriorated due to the fact that correction parameters are still used blindly when registration quality is deteriorated in a traditional system is solved, dependence on personal experience of doctors is reduced, and the problem that the system is completely invalid possibly caused by a single correction mode is solved.

The invention discloses an all-weather unstructured orchard visual navigation system, which is characterized in that an improved CycleGAN image processing module is introduced to perform enhancement processing on an image acquired under a severe weather condition, interference factors such as rain, snow and fog in the image are effectively removed, the image quality is improved, and an improved YOLOv11-seg network is combined, so that the visual navigation precision of the orchard is improved. And high-precision and high-stability segmentation of the unstructured road region is realized. Meanwhile, a continuous, smooth and controllable navigation path is constructed based on a path line generation method of pixel mutation detection and cubic B-spline fitting, and path planning precision and operation stability in an orchard scene are guaranteed. The constructed all-weather unstructured orchard visual navigation system comprises three modules: an all-weather adaptation module based on the improved CycleGAN, a road segmentation module based on the improved YOLOv11-seg, and a navigation path line generation module.

The invention discloses a robot visual navigation system and method based on Transform and dynamic feature optimization. The robot visual navigation system comprises an image acquisition module, an image feature matching module, a path point prediction module, a path point optimization module and a motion control calculation module. According to the invention, by introducing Transform and a dynamic feature optimization mechanism, high-quality processing and accurate modeling are carried out on image data; non-local mean denoising is adopted, ORB feature extraction and matching are improved, and mismatching points are filtered in combination with an RANSAC algorithm; a handshake synchronization mechanism between an image and path prediction is designed, and it is ensured that an image used for path point prediction is the latest collected image all the time by comparing timestamps; through outlier detection, clustering and geometric center calculation, the system can optimize path point selection in real time according to environmental changes, invalid paths are automatically avoided, and the continuity, rationality and safety of navigation paths are improved.

The present invention provides a space intelligent flying robot in a microgravity-normal air environment, belonging to the field of flying robots. To achieve the goal of enabling the space intelligent flying robot in a microgravity environment to have independent control over position, posture, output force, and torque. The robot comprises a carrier main frame, an outer shell, a computing system disposed within the carrier main frame, a visual navigation system disposed in front of and behind the carrier main frame, a laser ranging module embedded in the outer shell, a power supply system disposed on the left and right sides of the carrier main frame, a power system embedded in the outer shell and within the carrier main frame, a gripping system disposed below the carrier main frame, and an interactive system disposed in front of and above the main frame. While realizing basic functions, the present invention also makes innovative designs in the robot architecture, optimizing the robot's performance in manipulation, control, perception, and real-time performance, and has high engineering application value and good engineering application prospects.

The invention discloses an AI visual navigation and postoperative care auxiliary device for lumbar intervertebral disc resection, which relates to the technical field of medical equipment and comprises an AI visual navigation system and a postoperative care auxiliary device, the AI visual navigation system comprises an image data acquisition module, a deep learning processing module, a three-dimensional reconstruction module, a real-time positioning navigation module and a man-machine interaction module, the data transmission module is in communication connection with the AI visual navigation system, and dynamic recognition of an intraoperative anatomical structure is achieved through an AI deep learning technology. By combining high-precision registration of the real-time positioning and navigation module, the operation positioning precision is remarkably improved, the risk of key tissue damage is reduced, the sensing and monitoring module collects waist rehabilitation data in multiple dimensions, the data transmission real-time performance is high, medical staff can remotely master the rehabilitation state of a patient in real time, data support is provided for making a personalized nursing scheme, and the medical staff can conveniently and rapidly know the rehabilitation state of the patient. And subjectivity and blindness of traditional nursing are avoided.

The present application discloses a digital twin simulation test system for a space target visual navigation system, which relates to the field of ground simulation test technology. The system includes: a physical simulation test subsystem and a digital simulation test subsystem. The physical simulation test subsystem includes a space scene physical simulation module, a physical optical imaging module and a physical information processing module. The digital simulation test subsystem includes a space scene digital simulation module, a digital optical imaging module and a digital information processing module. The space scene physical simulation module and the space scene digital simulation module are used to simulate the on-orbit optical characteristics, on-orbit illumination state and relative motion state of a real space target. The physical optical imaging module and the digital optical imaging module are used to simulate the imaging process of a real optical imaging module. The physical information processing module and the digital information processing module are used to simulate the processing process of a real information processing module. The present application can better perform ground simulation testing on a space target visual navigation system.

The invention discloses a ratooning rice combine harvester visual navigation system based on binocular vision. The ratooning rice combine harvester visual navigation system comprises an equipment position adjusting unit, an image collecting unit, an image processing unit and a hydraulic control unit. The equipment position adjusting unit adjusts the orientation of the image acquisition unit in real time according to the posture of the harvester; the image acquisition unit is used for acquiring ratooning rice images and transmitting the images to the image processing unit; the image processing unit processes the ratooning rice image, identifies a crop boundary to obtain boundary line information, judges the steering and posture position of the harvester according to the boundary line information, and sends a generated speed execution signal and a steering execution signal to the hydraulic control unit; the hydraulic control unit controls the advancing speed of the harvester according to the speed execution signal and controls steering of the harvester according to the steering execution signal. According to the method for obtaining the boundary navigation line by utilizing the probability Hough transformation, the problem of low image imaging precision caused by overlarge vibration of a traditional intelligent harvester is solved.

The application relates to a cross-medium vehicle, belonging to the technical field of vehicles. The vehicle comprises a power propulsion system, a hybrid control system for providing power to the vehicle body, a navigation system for providing navigation support to the vehicle body, a gradient skin composed of multiple gradient materials and covering the outer surface of the vehicle body, and a diving system for controlling the floating and diving of the vehicle body. The vehicle can obtain the best aerodynamic / hydrodynamic performance in the air and seawater medium navigation state. The power propulsion system meets the requirements of high speed, long distance and large thrust of the vehicle. The distributed network and visual navigation system meet the navigation requirements of the cross-medium vehicle in the air, on the water surface and underwater, and joint operations. The hybrid control system realizes the accurate control of the vehicle. The application of the vehicle material can complete the deformation suitable for the changed environment.

The invention discloses a variable-magnification optical simulator for testing a satellite-borne visual navigation system. The variable-magnification optical simulator mainly comprises an optical camera, a fixed lens, a movable lens, a display screen and the like which are fixedly connected to an optical platform together, wherein the distance between the optical camera and the fixed lens is kept constant, and under the same central optical axis height, the fixed lens and the movable lens are kept coaxial and the distance can be changed through a lead screw guide rail, and the movable lens and the display screen are also kept coaxial and the distance can be changed through the lead screw guide rail; finally, by changing the distance among the fixed lens, the movable lens and the display screen, the optical camera is simulated to acquire space target images with different magnification times; according to the invention, the simulation test of the performance of the satellite-borne visual navigation system in a high dynamic space environment can be simulated.

This invention discloses a visual navigation method and system for agricultural robots based on vehicle speed adaptive gimbal perspective, belonging to the field of agricultural robot autonomous driving technology. The method includes: real-time acquisition of driving speed and dynamic adjustment of camera pitch angle; simultaneous acquisition of color and depth images, obtaining a binary image of crop rows from the color image; generating skeleton lines in the binary image of crop rows using a regional centroid slicing connection method, fitting a global navigation line, fusing depth information, and using the Zhang Zhengyou calibration method to transform the endpoints of the global navigation line to the world coordinate system, calculating the heading angle and lateral deviation of the agricultural robot; then, performing a self-vehicle coordinate system transformation to obtain the actual control deviation; finally, sending the machine vision navigation results to the steering controller via protocol-based instructions. This invention achieves adaptive control of the inter-row observation perspective applicable to multiple operating scenarios, significantly enhancing the adaptability and reliability of the visual navigation system in complex field operating environments.

The anesthesia puncture visual navigation system combining augmented reality with three-dimensional reconstruction belongs to the technical field of anesthesia puncture visual navigation, and comprises a physiological motion monitoring unit, which is used for simultaneously collecting respiratory motion cycle data and soft tissue elastic deformation information, and generating a comprehensive motion state data packet by calculating the correlation coefficient of the respiratory amplitude and the tissue elastic modulus change rate, so that the spatial deviation caused by the respiratory motion and the soft tissue deformation of the patient to the puncture navigation can be effectively compensated, the puncture precision is significantly improved compared with the traditional static navigation system under the normal respiratory state of the patient, the puncture failure rate and the complication risk are effectively reduced, the problem of further precision deterioration caused by the blind application of correction parameters of the traditional system when the registration quality deteriorates is avoided, the dependence on the personal experience of the doctor is reduced, and the problem of complete system failure caused by a single correction mode is avoided.

Embodiments are described for detecting optical discrepancies associated with image capture analyzing pixels in multiple images corresponding to common points of reference in a physical environment. In an embodiment, photometric error values are averaged over time to compute the mean error at each pixel. Once the estimate of the mean error has a sufficient number of updates above a specified value, the estimate is thresholded to provide a mask of any optical discrepancies occurring in the stereo pair of images. Applications include detecting optical discrepancies in images captured for use by a visual navigation system in guiding an autonomous vehicle (e.g., an unmanned aerial vehicle).

A system, method, and non-transitory computer readable medium for autonomous vehicle navigation and visual inspection utilizing a deep Q-network and reinforcement learning includes at least one camera mounted to the vehicle for capturing continuous image frames of a scene, and processing circuitry configured with a reinforcement learning engine that generates a next control action for vehicle movement based on the captured image frames and a reward for a previous control action. A self-supervised learning engine fine-tunes the deep Q-network, and a vehicle actuator maneuvers the vehicle accordingly. The visual inspection system includes a remote display terminal, an unmanned aerial vehicle (UAV) with an embedded transceiver for communicating captured image frames of a scene to the remote display terminal, and processing circuitry configured to control movement of the UAV to avoid moving objects based on the deep Q-network and reinforcement learning engine, displaying the captured image frames on the remote display terminal.

The invention relates to the field of anti-unmanned aerial vehicles, in particular to an unmanned aerial vehicle navigation decoy system. The real-time state of the target unmanned aerial vehicle is obtained through the sensing and tracking module, the confidence coefficient of a satellite navigation signal obtained by the target unmanned aerial vehicle is reduced through the satellite signal interference module, the expected decoy trajectory is generated through the trajectory generation module, and the geometric parameters and the refreshing sequence of the visual landmark interference pattern are updated in real time based on the expected decoy trajectory. And the laser projection interference array responds to the decoy control module and dynamically projects a visual landmark interference pattern with a specific code in the downward-looking imaging view field of the target unmanned aerial vehicle when the satellite signal interference does not take effect. Interference on the visual navigation system of the unmanned aerial vehicle is achieved through the visual landmark interference pattern, the problem that a traditional satellite navigation signal deception means is invalid when the unmanned aerial vehicle has the flying capacity under the condition of no satellite signal is solved, and the deception success rate is increased.

The invention discloses a visual cooperative control method for a prostate urethral dilation catheter, relates to the technical field of medical instruments, and solves the problem that a prostate dilation system combining real-time visual guidance, multi-modal feedback monitoring and intelligent cooperative control does not exist at present. According to the technical scheme, the method is characterized by comprising the following steps that 1, a prostate three-dimensional anatomical model of a patient is constructed, operation planning is conducted, and key operation parameters are calculated; 2, accurately positioning and expanding the catheter through a real-time visual navigation system; step 3, carrying out collaborative expansion by adopting a progressive pressure control model; the implementation mode of prostate dilatation is fundamentally changed, 'manual art 'depending on personal skill is converted into'precise engineering' based on models and data, finally leap-type comprehensive improvement is achieved in multiple aspects such as curative effect, safety, efficiency and generalization performance, and the prostate dilatation system has great clinical value and social benefits.

The invention relates to an agricultural machine tool, in particular to an in-line swing type intelligent weed extractor based on a visual navigation system, which is characterized in that an intelligent control system receives images shot by a visual guide device and data acquired by a speed measuring device, and controls a weed extraction part to complete weed extraction action, and each line of crops is provided with a set of electric control executing mechanism; the inter-plant hoeing cutter is installed below the electric control executing mechanism, and the servo motor drives the inter-plant hoeing cutter to operate between crop plants along a cycloid track, so that weeds between the plants are removed. The hoeing device has the advantages that the hoeing component is directly driven by a power machine, transmission is simple, action is sensitive, the hoeing component can rotate around crop plants, weeds among the plants can be removed by avoiding the plants, and the defects that the hoeing component of an existing machine is rigidly connected with a plough body, only can linearly run, and is low in sensitivity, high in damage rate and not suitable for hoeing operation of fragile plants are overcome; therefore, applicable intelligent hoeing equipment is provided for various crops, especially fragile plants such as vegetables and the like.

The invention discloses an agv vehicle control and navigation system based on a visual large model, and relates to the technical field of agv vehicle control. The agv vehicle control and navigation system based on the visual large model comprises an initialization and data acquisition unit, a path planning and guiding module, an image data processing module, a path deviation analysis and selection module, a path adjustment module, an agv speed regulation and control module and a position positioning and exception handling module. Electromagnetic and visual navigation systems are fused, and an LSTM algorithm and a multi-visual sensor fusion technology are utilized, so that the path planning accuracy is improved; extracting fixed object features to update a database, and enhancing system adaptability; the path is preferentially selected, and the navigation reliability is improved; a navigation system can be automatically switched to cope with an interference area; dynamic speed regulation can be achieved, and the driving requirement is met; the method can position and predict a path in real time, detect abnormity, adjust direction and speed in time, give an alarm when processing cannot be carried out, and guarantee safe and stable operation of agv.

The invention belongs to the field of visual navigation, and discloses a refueling taper sleeve positioning method based on visible light and infrared fusion. The refueling taper sleeve positioning method comprises the following steps: establishing an air refueling visual navigation system; aiming at the visible light imaging image, resolving the appearance characteristics of the refueling taper sleeve by using a convolutional neural network to obtain a two-dimensional coordinate of the refueling taper sleeve under a pixel coordinate system; aiming at the infrared imaging image, resolving the characteristics of the LED infrared lamp beads of the refueling taper sleeve by using a visual algorithm to obtain the two-dimensional coordinates of the refueling taper sleeve under a pixel coordinate system; performing pose estimation, coordinate conversion and fusion on the two-dimensional coordinates of the refueling taper sleeve under the pixel coordinate system to obtain a three-dimensional coordinate estimation value of the refueling taper sleeve; the three-dimensional coordinate estimated value of the refueling taper sleeve is predicted and updated step by step through Kalman filtering, the prediction precision is continuously improved, and finally the three-dimensional coordinate predicted value, meeting the precision requirement, of the refueling taper sleeve is output. The refueling taper sleeve positioning method has accuracy and robustness and has engineering practical value.

This application describes a visual navigation system for a legged robot in unstructured scenes. This system addresses the problem of insufficient utilization of ground feature information in existing technologies, which leads to inaccurate navigation. This application establishes a multi-layer local perception map that can describe ground features, adding a description of ground features to the traditional local map. Furthermore, based on the local perception map, the system incorporates ground feature parameters into the trajectory optimization process, thereby addressing the issue of insufficient utilization of ground feature information by legged robots. This improves the accuracy of the robot's visual navigation.

The invention relates to the technical field of medical equipment, in particular to a cerebral hematoma visual puncture navigation system and method.The navigation system comprises a skull guide plate, a guide limiting assembly, a mobile phone locator, a puncture catheter, a neuroendoscope and a navigation workstation; the guiding and limiting assembly is connected to the skull guide plate through the fixing piece and used for limiting the insertion direction of the puncture catheter, and the deviation controller is arranged, so that a limiting sliding way of the puncture catheter is jointly constructed through the second centering bearing and the first centering bearing; according to the visual puncture navigation system for the encephaloma, the directional deviation of the second centering bearing relative to the first centering bearing is adjusted in time through the first driver and the second driver, so that the axial direction of the limiting slide way is adjusted, the puncture direction is limited, and the puncture direction can be adjusted in time. The operation risk and the operation requirements on doctors are reduced, and the operation efficiency is improved.

A visual navigation safety measurement method based on visual integrity monitoring combines scene priori knowledge with visual measurement characteristics, establishes a real-time safety boundary quantification model of a visual navigation system, and combines priori feature constraints of a structured scene to obtain a real-time safety boundary quantification model of the visual navigation system. A complete technical chain from feature extraction to safety evaluation to decision control is constructed, accurate navigation safety evaluation and dynamic control are provided for carrier navigation in structured scenes such as runway landing and automobile road driving, and real-time monitoring, quantitative evaluation and safety guarantee of the reliability of the visual navigation system are realized.

The invention discloses a visual navigation system for air refueling, and relates to the field of machine vision, and the system comprises an acquisition module which is used for acquiring a real-time scene image containing a taper sleeve target in an air refueling process; the preprocessing module is used for receiving the scene image, performing noise reduction and enhancement processing on the scene image, and forwarding the processed scene image to the identification module; according to the method, a clear taper sleeve scene image is obtained through high-resolution and high-frame-rate collection and anti-glare design, the image quality is optimized through noise reduction and enhancement processing, the taper sleeve is accurately recognized by combining texture feature extraction and dynamic background elimination, and coordinate and contour information of the taper sleeve is output. The fusion model is adopted to continuously track the taper sleeve, and parameters can be dynamically adjusted to improve tracking stability.

The invention relates to the technical field of robot navigation and three-dimensional vision, in particular to a three-dimensional vision navigation system for an intelligent composite robot with a body, which comprises a preprocessing module, an initial positioning module, a pose optimization module, a path planning module and a path decision module. The system collects point clouds through a stereoscopic vision array, and performs initial positioning through multi-scale feature matching after correction filtering. During pose optimization, a dynamic weight factor is introduced into point cloud registration to suppress interference of a dynamic object and improve positioning precision. According to the path planning, after candidate paths are generated based on environmental semantic information, a decision-making module adopts a simulator based on a physical engine to carry out high-fidelity collision detection and motion smoothness quantitative evaluation on the paths, so that the optimal navigation path in the physical level is selected. The invention aims to improve the positioning robustness of the robot in a dynamic scene and the actual performability of the navigation path.