Agricultural machinery holographic sensing positioning method based on BDS / INS fusion
By integrating BDS/INS with an environmental perception system, and combining Kalman filtering and path planning, the problems of positioning errors and low operating efficiency of traditional agricultural machinery in complex farmland environments have been solved, achieving high-precision automatic navigation and automated operation.
Patent Information
- Application Number
- CN202511592004.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-03
- Publication Date
- 2026-02-27
AI Technical Summary
Traditional agricultural machinery has low positioning accuracy in complex farmland environments, making it difficult to adapt to changes in crop growth, terrain, and external environmental conditions in real time, resulting in large positioning errors and low operating efficiency.
By combining BDS/INS fusion technology with an environmental perception system, and utilizing Kalman filtering algorithm and real-time path planning, data fusion is achieved by acquiring satellite positioning information through BDS and motion state information through INS, and then combining ultrasonic and visual sensors for environmental perception, thus realizing holographic perception and positioning.
It improves the positioning accuracy and anti-interference ability of agricultural machinery in complex environments, realizes automatic navigation with decimeter-level accuracy, automatically avoids obstacles, optimizes the operation path, and improves operation efficiency and accuracy.
Smart Images
Figure CN121577009A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of agricultural machinery technology, specifically to a holographic sensing and positioning method for agricultural machinery based on BDS / INS fusion. Background Technology
[0002] With the rapid development of agricultural mechanization, the precision and efficiency of agricultural operations are receiving increasing attention. Traditional agricultural machinery largely relies on GPS systems for positioning. However, in practical applications, such as in complex farmland environments, GPS systems face numerous challenges. Factors such as buildings, vegetation, and weather changes often lead to signal loss or interference, affecting positioning accuracy. Furthermore, traditional agricultural machinery often struggles to provide stable positioning data when dealing with high-speed travel, sharp turns, or low-signal environments. In recent years, many studies both domestically and internationally have attempted to introduce environmental perception technologies into agricultural machinery navigation systems, utilizing ultrasonic sensors, visual sensors, and other means to monitor the surrounding environment, thereby providing real-time perception data for the machinery. These technologies can identify surrounding obstacles, terrain changes, and crop growth status, providing strong support for path planning and automated operations of agricultural machinery. However, these systems often suffer from the problem of inaccurate synchronization between environmental perception data and positioning information, preventing the navigation system from efficiently and accurately performing tasks in complex farmland environments.
[0003] BDS / INS fusion technology can improve the positioning accuracy of agricultural machinery in complex environments, but traditional methods often fail to fully consider the role of environmental perception information. In complex farmland environments, the positioning system still cannot adapt to changes in crop growth, terrain, and external environmental conditions in real time. This results in low positioning accuracy and poor operating efficiency for traditional agricultural machinery when performing tasks such as precision tillage and obstacle avoidance, and its performance is particularly inadequate in harsh environments. Summary of the Invention
[0004] To address the shortcomings of existing technologies, this invention provides a holographic perception and positioning method for agricultural machinery based on BDS / INS fusion. The technical problem this invention aims to solve is: by combining BDS / INS fusion technology with an environmental perception system, it addresses how to achieve high-precision data fusion of agricultural machinery in complex environments through the fusion of Kalman filtering algorithm and real-time path planning.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: a holographic perception and positioning method for agricultural machinery based on BDS / INS fusion, comprising: S1. real-time acquisition of satellite positioning information of agricultural machinery through BDS, wherein the satellite positioning information includes longitude, latitude, altitude and timestamp data, and the BDS adjusts the positioning accuracy in real time based on terrain changes and environmental changes to cope with the positioning error of traditional BDS in complex agricultural environments;
[0006] S2. The motion state information of agricultural machinery is obtained using the INS system. The motion state information includes acceleration, angular velocity and angle change. The motion state information is fused with BDS positioning information through an improved Kalman filter algorithm. The Kalman filter algorithm is used to process the errors generated during the dynamic driving of agricultural machinery, improve the anti-interference ability of the system and the positioning accuracy in high-speed and low-signal environments.
[0007] S3. Establish an environmental perception system, which includes an ultrasonic sensor and a visual sensor. The ultrasonic sensor monitors the terrain, obstacles, and crop status around the agricultural machinery. The visual sensor integrates distance, obstacle type, and crop growth status to form environmental perception data. The environmental perception data is updated synchronously with the positioning information to provide holographic perception information.
[0008] S4. The dynamic path adjustment of agricultural machinery is carried out through a real-time path planning algorithm. The dynamic path adjustment of agricultural machinery is based on the positioning information and the environmental perception data. The path planning algorithm obtains surrounding obstacles, terrain information and farmland status information through real-time feedback of terrain and obstacle information. In complex farmland environments, it realizes automatic obstacle avoidance, precision farming and automated farmland operations. The path planning includes changes in environmental information, including external factors such as temperature and humidity changes and crop growth status.
[0009] S5. Automatic navigation of agricultural machinery under holographic perception and decimeter-level precision positioning: The automatic navigation system generates an adaptive path based on environmental perception and precise positioning results, which can adaptively adjust the speed, direction and route of agricultural machinery, and combine crop status and changes in the surrounding environment to avoid the high error and low efficiency problems of traditional agricultural machinery in harsh environments.
[0010] Preferably, the Kalman filter algorithm performs data fusion on BeiDou satellite positioning information and inertial navigation information, and the state equation of the Kalman filter algorithm is:
[0011] .
[0012] in, For the first The state vector at time t, the The dimensions are meters, meters per second, and meters per second², respectively. Here is the state transition matrix. For the control matrix, To control the input, the The units are meters per second². The process noise represents the impact of system model uncertainties. The dimensions are meters, meters per second, and meters per second², respectively.
[0013] Preferably, the observation equation of the Kalman filter algorithm is:
[0014] .
[0015] in, For the first The observation vector at time t represents the positioning information obtained from the BDS, in meters. The observation matrix connects the state vector and the observation data. The observation noise represents the error from the BDS system.
[0016] Preferably, the ultrasonic sensor measures the distance between the agricultural machinery and obstacles by emitting ultrasonic signals and receiving reflected signals, and the visual sensor acquires visual information about the surrounding environment of the agricultural machinery in real time through an image acquisition module.
[0017] Preferably, the path planning algorithm calculates the distance between the current position and the target position of the agricultural machinery, and performs optimal path planning based on the distance. The formula for calculating the distance is:
[0018] .
[0019] in, For the first The Euclidean distance between the agricultural machinery and the target location at any given time, ( , ) represents the current position coordinates of the agricultural machinery. , () represents the coordinates of the target location.
[0020] Preferably, the automatic navigation system further includes an obstacle detection and avoidance module.
[0021] Preferably, the obstacle detection and avoidance module detects potential obstacles in front of the agricultural machinery based on real-time perception data and high-precision positioning information, and corrects the generated path in real time according to the detection results to ensure the safe operation of the agricultural machinery.
[0022] Preferably, the automatic navigation system includes the precision of agricultural machinery operations and the efficiency of balanced operations.
[0023] This invention provides a holographic sensing and positioning method for agricultural machinery based on BDS / INS fusion. It offers the following advantages: by combining BDS and INS, it effectively improves the positioning accuracy and anti-interference capability of agricultural machinery in complex farmland environments. The BDS system provides high-precision positioning information, while the INS system compensates for the shortcomings of weak or unavailable GPS signals, ensuring the stability of the positioning system in high-speed or low-signal environments. The application of the Kalman filter algorithm makes the fusion of BDS and INS more accurate, thereby effectively improving the overall system performance.
[0024] This holographic perception and positioning method for agricultural machinery based on BDS / INS fusion, by incorporating an environmental perception system and combining ultrasonic and visual sensors, not only enhances the real-time perception capabilities of agricultural machinery but also enables it to detect changes in the surrounding environment in real time, automatically avoid obstacles, and adjust its path. The introduction of this technology allows agricultural machinery to adapt to environmental changes, optimize its operating path and efficiency, and ultimately achieve high-precision, automated farmland operations, significantly improving the efficiency and accuracy of agricultural production. Attached Figure Description
[0025] Figure 1 This is a schematic diagram of a structure for realizing an invention;
[0026] Figure 2 This is a schematic diagram of the dynamic path planning process for realizing an invention. Detailed Implementation
[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0028] Example 1
[0029] like Figure 1-2 As shown, this embodiment of the invention provides a holographic sensing and positioning method for agricultural machinery based on BDS / INS fusion, including: S1. Real-time acquisition of satellite positioning information of agricultural machinery through BDS, the satellite positioning information including longitude, latitude, altitude and timestamp data, BDS adjusting positioning accuracy in real time based on terrain and environmental changes to cope with the positioning error of traditional BDS in complex agricultural environments.
[0030] S2. The motion state information of agricultural machinery is acquired using the INS system. This motion state information includes acceleration, angular velocity, and angle changes. The motion state information is fused with BDS positioning information using an improved Kalman filter algorithm. The Kalman filter algorithm is used to handle errors generated during the dynamic movement of the agricultural machinery, improving the system's anti-interference capability and positioning accuracy in high-speed, low-signal environments. The Kalman filter algorithm fuses BeiDou satellite positioning information with inertial navigation information. The state equation of the Kalman filter algorithm is:
[0031] .
[0032] in, For the first The state vector at any given time contains the position, velocity, and acceleration of the agricultural machinery. The dimensions are meters, meters per second, and meters per second², respectively. This is the state transition matrix, reflecting the motion model of the agricultural machinery, showing the state transitions from the previous time step to the current time step. The control matrix represents the effect of the control input on the state. For control input, it represents motion state information from the INS. The units are meters per second². Process noise represents the impact of system model uncertainties. The dimensions are meters, meters per second, and meters per second², respectively.
[0033] The observation equation of the Kalman filter algorithm is:
[0034] .
[0035] in, For the first The observation vector at time t represents the positioning information obtained from the BDS, in meters. The observation matrix connects the state vector and the observation data. The observation noise represents the error from the BDS system.
[0036] S3. Establish an environmental perception system, which includes ultrasonic sensors and visual sensors. The ultrasonic sensors monitor the terrain, obstacles, and crop status around the agricultural machinery. The visual sensors integrate distance, obstacle type, and crop growth information to form environmental perception data. This data is updated synchronously with positioning information to provide holographic perception information. The ultrasonic sensors measure the distance between the agricultural machinery and obstacles by emitting ultrasonic signals and receiving reflected signals. The visual sensors acquire real-time visual information about the environment surrounding the agricultural machinery through an image acquisition module.
[0037] S4. Dynamic path adjustment of agricultural machinery is achieved through a real-time path planning algorithm. This dynamic path adjustment is based on positioning information and environmental perception data. The path planning algorithm obtains information about surrounding obstacles, terrain, and farmland status through real-time feedback of terrain and obstacle information. In complex farmland environments, it enables automatic obstacle avoidance, precision tillage, and automation of farmland operations. Path planning incorporates changes in environmental information, including temperature and humidity variations and external factors related to crop growth status. The path planning algorithm calculates the distance between the current position and the target position of the agricultural machinery and performs optimal path planning based on this distance. The formula for calculating the distance is:
[0038] .
[0039] in, For the first The Euclidean distance between the agricultural machinery and the target location at any given time, ( , ) represents the current position coordinates of the agricultural machinery. , () represents the coordinates of the target location.
[0040] S5. Automatic navigation of agricultural machinery under holographic perception and decimeter-level precision positioning: The automatic navigation system generates an adaptive path based on environmental perception and precise positioning results. It can adaptively adjust the speed, direction, and route of the agricultural machinery, taking into account changes in crop condition and the surrounding environment, thus avoiding the high error and low efficiency problems of traditional agricultural machinery in harsh environments. The automatic navigation system includes precision and balanced operation efficiency for agricultural machinery, and further includes an obstacle detection and avoidance module. The obstacle detection and avoidance module detects potential obstacles in front of the agricultural machinery based on real-time perception data and high-precision positioning information, and corrects the generated path in real time based on the detection results to ensure the safe operation of the agricultural machinery.
[0041] Example 2
[0042] Unlike Embodiment 1, this embodiment describes the acquisition of BDS satellite positioning information and the acquisition and fusion of motion state information from the INS system.
[0043] 1. Acquisition of BDS satellite positioning information
[0044] Real-time satellite positioning information of agricultural machinery is obtained through BDS. The location data provided by the BDS system includes the longitude, latitude, altitude, and timestamp of the agricultural machinery. The specific data format is as follows:
[0045] Longitude: in degrees, with an accuracy of 0.0001 degrees.
[0046] Latitude: in degrees, with an accuracy of 0.0001 degrees.
[0047] Height: in meters, with an accuracy of 0.1 meters.
[0048] Timestamp: Represents the UTC time of the location, with a precision of 1 second.
[0049] Positioning data is obtained by receiving BDS satellite signals and performing differential calculations. The BDS system adjusts its positioning accuracy in real time, taking into account terrain changes and environmental factors. For example, in farmland, the BDS system dynamically adjusts its accuracy based on the terrain's undulations and the crop's planting status to keep positioning errors within a minimum range.
[0050] In areas with tall buildings or dense trees, BDS signals can be blocked, leading to a decrease in positioning accuracy. The BDS system, by monitoring and analyzing changes in the surrounding environment in real time, automatically adjusts positioning parameters to optimize positioning accuracy, overcoming the positioning errors that occur in traditional BDS systems in complex farmland environments.
[0051] 2. Motion state information acquisition and fusion of INS system
[0052] After acquiring BDS satellite positioning data, the motion status information of the agricultural machinery is obtained using INS. The INS system includes multiple inertial sensors, such as accelerometers and gyroscopes, to measure the acceleration, angular velocity, and angular changes of the agricultural machinery in real time. The specific data acquired is as follows:
[0053] Acceleration: in meters per second squared, with an accuracy of 0.01 m / s².
[0054] Angular velocity: in degrees per second, with an accuracy of 0.01° / s.
[0055] Angle variation: in degrees, with an accuracy of 0.01°.
[0056] It can reflect the movement status of agricultural machinery, such as travel direction, speed changes, and turning angle. During the movement, the information provided by the INS system is collected and transmitted in real time to the data fusion algorithm.
[0057] 3. Data Fusion
[0058] The Kalman filter algorithm dynamically adjusts the weights to weight and fuse the data from both sources, thereby suppressing their respective errors.
[0059] In practical implementation, the state equation of the Kalman filter is:
[0060] .
[0061] Where x(k) represents the system's state vector, A is the state transition matrix, B is the control input matrix, u(k) is the motion state data from the INS, and w(k) is the process noise.
[0062] The observation equation is then:
[0063] .
[0064] Where z(k) is the positioning data obtained from BDS, H is the observation matrix, and v(k) is the observation noise.
[0065] Through this data fusion method, the Kalman filter algorithm effectively handles errors generated during the dynamic operation of agricultural machinery, providing more accurate positioning information in high-speed, low-signal environments. For example, when the BDS signal is interfered with or unavailable, the data provided by the INS can effectively fill the gaps, ensuring that the agricultural machinery can continue to operate efficiently.
[0066] 4. Improved accuracy
[0067] By implementing the above steps, the integration of BDS and INS can significantly improve the positioning accuracy of agricultural machinery in complex farmland environments. In practical applications, the positioning accuracy of agricultural machinery can reach the decimeter level, with an error range controlled within ±0.1 meters, enabling it to cope with the challenges posed by high-speed travel, sharp turns, and complex terrain during operation.
[0068] Example 3
[0069] This embodiment illustrates automatic navigation based on environmental perception information, precise positioning data, and real-time path planning algorithms, using holographic perception and decimeter-level precision positioning.
[0070] 1. Environmental perception and acquisition of precise positioning information
[0071] Agricultural machinery obtains high-precision positioning information through the aforementioned BDS and INS systems. The positioning data provided by BDS has an accuracy of decimeter level, and the positioning error is usually kept within ±0.1 meters. INS provides dynamic status data of agricultural machinery, including acceleration, angular velocity, and angle change, with accuracies of 0.01 m / s², 0.01° / s, and 0.01°, respectively.
[0072] Agricultural machinery is equipped with an environmental perception system, including ultrasonic sensors and visual sensors. Ultrasonic sensors measure the distance between the machinery and surrounding obstacles with an accuracy of 1 centimeter. Visual sensors acquire real-time environmental data of the surrounding farmland via cameras, including obstacles, crop growth status, and terrain changes, updating synchronously with positioning information to provide comprehensive environmental perception information for path planning and navigation.
[0073] 2. Automatic navigation path generation and adjustment
[0074] Based on location information and environmental perception data, the automatic navigation system calculates the travel route of agricultural machinery using a real-time path planning algorithm. During path planning, the system considers the following data:
[0075] Current location and target location: For example, suppose the current location of the agricultural machinery is longitude: 120.3456°, latitude: 30.1234°, and the target location is longitude: 120.3470°, latitude: 30.1248°. The system first calculates the Euclidean distance between the current location of the agricultural machinery and the target location, which is approximately 30 meters.
[0076] Obstacle detection and avoidance: Using ultrasonic and visual sensors, the system can detect obstacles ahead in real time. For example, when an obstacle appears 5 meters in front of the agricultural machinery, the system will adjust the path according to the type and location of the obstacle to ensure that the agricultural machinery can safely avoid it.
[0077] Crop growth status: Visual sensors can acquire real-time data on crop growth in farmland. For example, if the sensor detects dense crop growth in a certain area, the system adjusts its working depth and speed to ensure a balance between operational efficiency and crop protection.
[0078] Based on the above information, the path planning algorithm calculates the optimal path, taking into account environmental factors such as temperature, humidity, and crop growth status, and dynamically adjusts the path planning. The core of path planning is to calculate the shortest path between the current position of the agricultural machinery and the target position, and to adjust the path in conjunction with real-time feedback information to avoid obstacles and optimize operational efficiency.
[0079] 3. Dynamic path output and automatic navigation adjustment
[0080] After the real-time path planning algorithm calculates the optimal path, the system generates an adaptive path and outputs it to the automatic navigation module. The agricultural machinery's route, speed, and direction will be dynamically adjusted based on the following data:
[0081] Driving route: Agricultural machinery travels along the calculated path. For example, if the current path is from 120.3456°, 30.1234° to 120.3470°, 30.1248°, the system will adjust the driving angle in real time to ensure that the machinery can travel along the path.
[0082] Speed and Direction: The system adaptively adjusts the speed of agricultural machinery based on crop growth and obstacle locations. For example, in densely cropped areas, the speed is limited to 2 km / h to ensure accurate tillage depth, while in unobstructed open areas, the speed can be increased to 8 km / h.
[0083] Real-time feedback of environmental data, obstacle information, and crop growth status is continuously monitored, and path planning and the movement of agricultural machinery are dynamically adjusted to ensure the efficiency and safety of the operation process.
[0084] 4. High-efficiency operation and precision control
[0085] After completing automatic navigation, agricultural machinery can avoid obstacles and optimize its operating strategies based on the crop's growth status. When the system detects that crops are growing healthily in a specific area and that the area has good operating conditions, it will increase the operating speed while maintaining the operating depth and precision in accordance with agricultural standards. For example, if the crops are growing well, the machinery's operating speed may be increased to 10 kilometers per hour, ensuring that the tillage depth does not exceed 20 centimeters to meet agricultural operating standards.
[0086] Through this series of data collection, path planning, and dynamic adjustments, the automatic navigation system of this invention can achieve precise farmland operations in complex farmland environments, improving operational efficiency and reducing errors.
[0087] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A holographic sensing and positioning method for agricultural machinery based on BDS / INS fusion, characterized in that, include: S1. The satellite positioning information of agricultural machinery is acquired in real time through BDS, the satellite positioning information including longitude, latitude, altitude and timestamp data, and the BDS adjusts the positioning accuracy in real time based on terrain and environmental changes; S2. Obtain motion state information of agricultural machinery using the INS system. The motion state information includes acceleration, angular velocity, and angle change. The motion state information is fused with BDS positioning information using an improved Kalman filter algorithm. The Kalman filter algorithm is used to process errors generated during the dynamic driving of agricultural machinery. S3. Establish an environmental perception system, which includes an ultrasonic sensor and a visual sensor. The ultrasonic sensor monitors the terrain, obstacles, and crop status around the agricultural machinery. The visual sensor integrates distance, obstacle type, and crop growth status to form environmental perception data. The environmental perception data is updated synchronously with the positioning information. S4. The dynamic path of agricultural machinery is adjusted by a real-time path planning algorithm. The dynamic path adjustment of agricultural machinery is based on the positioning information and the environmental perception data. The path planning algorithm obtains surrounding obstacles, terrain information and farmland status information by real-time feedback of terrain and obstacle information. The path planning includes changes in environmental information, including external factors such as temperature and humidity changes and crop growth status. S5. Automatic navigation of agricultural machinery under holographic perception and decimeter-level precision positioning, wherein the automatic navigation system generates an adaptive path based on environmental perception and precise positioning results.
2. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The Kalman filter algorithm fuses BeiDou satellite positioning information and inertial navigation information. The state equation of the Kalman filter algorithm is as follows: in, For the first The state vector at time t, the The dimensions are meters, meters per second, and meters per second², respectively. Here is the state transition matrix. For the control matrix, To control the input, the The units are meters per second². For process noise, the The dimensions are meters, meters per second, and meters per second², respectively.
3. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The observation equation of the Kalman filter algorithm is: in, For the first The observation vector at time t represents the positioning information obtained from the BDS, in meters. The observation matrix connects the state vector and the observation data. The observation noise represents the error from the BDS system.
4. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The ultrasonic sensor measures the distance between agricultural machinery and obstacles by emitting ultrasonic signals and receiving reflected signals, while the visual sensor acquires real-time visual information about the environment surrounding the agricultural machinery through an image acquisition module.
5. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The path planning algorithm calculates the distance between the current position and the target position of the agricultural machinery, and performs optimal path planning based on the distance. The formula for calculating the distance is: in, For the first The Euclidean distance between the agricultural machinery and the target location at any given time, ( , ) represents the current position coordinates of the agricultural machinery. , () represents the coordinates of the target location.
6. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The automatic navigation system further includes an obstacle detection and avoidance module.
7. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 6, characterized in that: The obstacle detection and avoidance module detects potential obstacles in front of agricultural machinery based on real-time perception data and high-precision positioning information.
8. The agricultural machinery holographic sensing and positioning method based on BDS / INS fusion according to claim 1, characterized in that: The automatic navigation system includes the precision and balancing efficiency of agricultural machinery operations.