Crop phenotype data acquisition unmanned vehicle system and crop phenotype data acquisition method

Abstract

The invention discloses a crop phenotype data acquisition unmanned vehicle system and a crop phenotype data acquisition method, and relates to the technical field of agricultural intelligent equipment and plant phenotype information acquisition. The system comprises an unmanned vehicle main body, a U-shaped sensor frame, three groups of acquisition sensors, three battery boxes and a controller, the unmanned vehicle main body comprises four wheels with independent driving and steering designs; the upper end of the unmanned vehicle main body is connected with the U-shaped sensor frame; the three groups of acquisition sensors are respectively arranged on a left side frame, a top end frame and a right side frame of the U-shaped sensor frame in a surrounding manner; and the controller is connected with each wheel, each wheel chassis, the U-shaped sensor frame, the acquisition sensor and the battery box, and is used for controlling the crop phenotype data acquisition unmanned vehicle system. According to the technical scheme of the embodiment of the invention, the trafficability and stability of the unmanned vehicle system are improved, the acquisition of crop phenotype data in a field environment is realized, and the method has relatively strong popularization and application capabilities.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural intelligent equipment and plant phenotype information collection, and particularly relates to a crop phenotype data collection unmanned vehicle system and a crop phenotype data collection method. BACKGROUND

[0002] With the continuous development of smart agriculture and precision breeding, rapid, accurate and high-throughput acquisition of crop phenotype data has become a core link of breeding selection, crop monitoring and yield evaluation. Especially in the field environment, three-dimensional perception and dynamic monitoring of crop structural characteristics are of great significance for crop variety improvement and agronomic measure optimization. Traditional crop phenotype data acquisition mainly relies on manual measurement, which is not only low in efficiency and poor in repeatability, but also difficult to meet the needs of large-scale, time-series and structured information collection.

[0003] In recent years, with the rapid development of unmanned vehicle technology, unmanned vehicle systems have become an important means to replace manual investigation and unmanned vehicle shooting. Some existing unmanned vehicle systems use laser radar, cameras and multispectral sensors to acquire crop phenotype data, which have good image resolution advantages.

[0004] However, the existing unmanned vehicle system has large rigidity and compact structure, which is suitable for greenhouse environment and not suitable for field environment. SUMMARY

[0005] The present application provides a crop phenotype data collection unmanned vehicle system and a crop phenotype data collection method, which improves the passability and stability of the unmanned vehicle system, realizes the collection of crop phenotype data in different field environments, and has strong popularization and application ability.

[0006] According to an aspect of the present application, a crop phenotype data collection unmanned vehicle system is provided, which comprises: an unmanned vehicle body, a U-shaped sensor frame, three groups of collection sensors, three battery boxes and a controller.

[0007] The unmanned vehicle body comprises four wheels with independent driving and steering design;

[0008] The upper end of the unmanned vehicle body is connected with the U-shaped sensor frame;

[0009] The three groups of collection sensors comprise left collection sensors, top collection sensors and right collection sensors; the three groups of collection sensors are respectively installed in a ring shape on the left frame, the top frame and the right frame of the U-shaped sensor frame;

[0010] The three groups of battery boxes include a left battery box, a right battery box and a top battery box; the left battery box is connected with the left wheel and the left collection sensor, and is used for supplying power for the left wheel and the left collection sensor; the right battery box is connected with the right wheel and the right collection sensor, and is used for supplying power for the right wheel and the right collection sensor; the top battery box is connected with the top collection sensor, and is used for supplying power for the top collection sensor.

[0011] The controller is connected with each wheel, each wheel chassis, the U-shaped sensor frame, the collection sensor and the battery box, and is used for controlling the crop phenotype data collection unmanned vehicle system.

[0012] According to an aspect of the present application, a crop phenotype data collection method is provided, and the method comprises:

[0013] In the operation preparation stage, according to the spatial resolution of the field crops detected by each group of collection sensors, the target collection height and the target collection angle of each group of collection sensors are determined;

[0014] For a single group of collection sensors, the U-shaped sensor frame is adjusted in height according to the target collection height of the collection sensor;

[0015] For a single group of collection sensors, the collection sensor is adjusted in angle according to the target collection angle of the collection sensor;

[0016] In the operation execution stage, the crop row spacing and the collection data type of the collection task are obtained;

[0017] According to the crop row spacing of the collection task, the U-shaped sensor frame is adjusted in width;

[0018] According to the collection data type, the target collection sensor corresponding to the collection data type is screened from each collection sensor, and the target collection sensor is used to execute the collection task.

[0019] The unmanned vehicle body with four wheels with independent driving and steering design can realize differential steering and right-angle turning, can adapt to different terrain conditions, and effectively improves the flexibility of the unmanned vehicle system in the field; the collection sensors are respectively installed in a ring shape on the U-shaped sensor frame, so that different angle collection of crops can be realized; through the partition management and partition control of the collection sensors, the flexibility and adaptability of the crop phenotype data collection are further improved; through the partition power supply of each group of battery boxes, the limitation of the position and volume of the battery box on the collectable crop height when the unmanned vehicle system is uniformly powered is avoided, and the flexibility of the unmanned vehicle system is further improved; therefore, the passability and stability of the unmanned vehicle system are improved, the collection of crop phenotype data in different field environments is realized, the unmanned vehicle system can adapt to various farmland terrains and planting modes, and has strong popularization and application potential.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a front view of a crop phenotype data collection unmanned vehicle system provided according to the first embodiment of the present application;

[0023] Figure 2 is a rear view of a crop phenotype data collection unmanned vehicle system provided according to the first embodiment of the present application;

[0024] Figure 3 is a side view of a crop phenotype data collection unmanned vehicle system provided according to the first embodiment of the present application;

[0025] Figure 4 is a bottom view of a crop phenotype data collection unmanned vehicle system provided according to the first embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of a controller provided according to the first embodiment of the present application;

[0027] Figure 6 is a schematic diagram of crop phenotype data provided according to the first embodiment of the present application;

[0028] Figure 7 This is a flowchart of a crop phenotypic data acquisition method according to Embodiment 2 of the present invention;

[0029] Figure 8 This is a schematic diagram of the controller that implements the crop phenotypic data acquisition method of this invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a front view of an unmanned vehicle system for collecting crop phenotypic data according to Embodiment 1 of the present invention. This embodiment of the invention is applicable to situations where crop phenotypic data is collected in a field environment. The system can execute crop phenotypic data collection methods and can be implemented in hardware.

[0034] See Figure 1The crop phenotypic data acquisition unmanned vehicle system shown includes: an unmanned vehicle body 110, a U-shaped sensor frame 120, three sets of acquisition sensors 130, three battery boxes 140, and a controller 150. The unmanned vehicle body 110 includes four wheels with independent drive and steering design. The upper part of the unmanned vehicle body 110 is connected to the U-shaped sensor frame 120. The three sets of acquisition sensors 130 include a left acquisition sensor 131, a top acquisition sensor 133, and a right acquisition sensor 132. The three sets of acquisition sensors 130 are respectively mounted in a ring around the left, top, and right frames of the U-shaped sensor frame 120. The three battery boxes 140 include a left battery box 141. The system includes a right-side battery box 142 and a top-side battery box 143; a left-side battery box 141 connected to the left-side wheel 111 and the left-side data acquisition sensor 131, used to power the left-side wheel 111 and the left-side data acquisition sensor 131; a right-side battery box 142 connected to the right-side wheel 112 and the right-side data acquisition sensor 132, used to power the right-side wheel 112 and the right-side data acquisition sensor 132; a top-side battery box 143 connected to the top-side data acquisition sensor 133, used to power the top-side data acquisition sensor 133; and a controller 150 connected to each wheel, each wheel chassis, the U-shaped sensor frame 120, the data acquisition sensor 130, and the battery box 140, used to control the crop phenotypic data acquisition unmanned vehicle system.

[0035] The unmanned vehicle body 110 navigates between crops in a field environment. The unmanned vehicle body 110, equipped with four independently driven and steering wheels (meaning four wheels driven by wheel-side motors and featuring independent suspension and shock absorption systems at the bottom), enables differential steering and right-angle turns, adapting to various terrain conditions and supporting stable passage between narrow-row crops, effectively enhancing the flexibility of the unmanned vehicle system in the field. Optionally, the wheels can be high-grip rubber tires. Optionally, the independent suspension and shock absorption system can be a multi-degree-of-freedom damping system. A U-shaped sensor frame 120 can be vertically mounted along the unmanned vehicle frame on the upper part of the unmanned vehicle body 110. Through the four-wheel independent drive system combined with an adaptive terrain adjustment structure, the unmanned vehicle system can traverse undulating terrain with a small turning radius and strong passability, making it suitable for different planting patterns and significantly enhancing the stability of the unmanned vehicle system's operation.

[0036] The data acquisition sensors 130 are mounted in a ring around the U-shaped sensor frame 120. This means that for sensors at the same acquisition height, the sensors 130 can be installed in a ring around a certain height of the U-shaped sensor frame 120, thus enabling data acquisition from different angles of the crop. The data acquisition sensors 130 can be divided into three groups. These three groups can include a left-side sensor 131, a top-side sensor 133, and a right-side sensor 132. The left-side sensor 131 is mounted around the left-side sensor 131. The top-side sensor 133 is mounted around the top frame of the U-shaped sensor frame 120. The right-side sensor 132 is mounted around the right-side frame of the U-shaped sensor frame 120. This achieves zoned management and control of the data acquisition sensors 130, improving the flexibility and adaptability of crop phenotypic data acquisition. For example, the data acquisition sensors can include RGB (three primary colors) cameras, depth cameras, LiDAR, multispectral cameras, and thermal infrared imagers. Among these, RGB cameras can be used to acquire crop color and morphological characteristics. For example, RGB cameras acquire crop morphological images at a fixed frequency to calculate indicators such as leaf area and plant shape. Depth cameras can be used to acquire point cloud data for reconstructing the three-dimensional structure of crops. LiDAR can be used for precise distance measurement and spatial structure mapping. Multispectral cameras can be used to acquire information such as vegetation indices and nitrogen distribution. For example, a multispectral camera periodically triggers the acquisition of reflectance images to calculate vegetation indices such as NDVI (Normalized Difference Vegetation Index) and RECI (Remote Sensing Enhanced Vegetation Index). Thermal infrared imagers can be used to acquire temperature distribution data to infer water stress status and monitor pests and diseases.

[0037] The three battery boxes 140 include a left battery box 141, a right battery box 142, and a top battery box 143. The left battery box 141 is connected to the left wheel 111 and the left-side data acquisition sensor 131, providing power to these components. The right battery box 142 is connected to the right wheel 112 and the right-side data acquisition sensor 132, providing power to these components. The top battery box 143 is connected to the top-side data acquisition sensor 133, providing power to it. By providing power to each battery box separately, the limitations imposed by the battery box's position and volume on the height of the crops that can be harvested are avoided when the entire autonomous vehicle system is powered uniformly, further improving the flexibility of the autonomous vehicle system.

[0038] The controller 150 is connected to each wheel, each wheel chassis, the U-shaped sensor frame 120, the data acquisition sensor 130, and the battery box 140, and is used to control the unmanned vehicle system for collecting crop phenotypic data. For example, Figure 5 As shown, the controller 150 can integrate a mobile platform module, a multi-source sensing module, a data acquisition and fusion module, a control decision module, and a communication and remote control module. The mobile platform module enables the unmanned vehicle system to maneuver and navigate in the field. The multi-source sensing module is used to construct crop structure representation capabilities from different perspectives and scales. The data acquisition and fusion module ensures the spatiotemporal consistency and fusion accuracy of the data. The control decision module supports path planning, obstacle avoidance control, and task scheduling. The communication and remote control module ensures remote user management, data uploading, and status monitoring.

[0039] Optionally, the chassis height of each wheel is adjustable. Compared to a greenhouse environment, the terrain in a field environment is more varied. To ensure the safety and stability of the unmanned vehicle system, the chassis height of each wheel can be adjusted, thereby improving the safety and stability of the unmanned vehicle system in field environments. Furthermore, the ground clearance of each wheel chassis is 300mm, with an adjustable height of ±100mm. This, in turn, improves the adjustment efficiency of the wheel chassis while ensuring the safety and stability of the unmanned vehicle system in field environments.

[0040] Optionally, the autonomous vehicle body and U-shaped sensor frame can be made of aluminum alloy. Compared to other materials, aluminum alloy is lightweight and has high strength. Using aluminum alloy for the autonomous vehicle body and U-shaped sensor frame can reduce the weight of the autonomous vehicle system while ensuring its structural stability, thereby improving the adaptability of the autonomous vehicle system in field operations.

[0041] Optionally, the height of the U-shaped sensor frame is adjustable. Existing unmanned vehicle systems for crop phenotypic data acquisition have a relatively fixed acquisition height, making it difficult to adapt to the different growth stages of crops. By making the height of the U-shaped sensor frame adjustable, the unmanned vehicle system can adapt to the height of crops during their growth stages, improving the versatility and adaptability of the unmanned vehicle system for crop phenotypic data acquisition. Furthermore, the height of the U-shaped sensor frame can reach 270cm. Existing unmanned vehicle systems for crop phenotypic data acquisition can typically only collect phenotypic data for short-stalked crops, lacking a system suitable for collecting phenotypic data from tall crops. By making the height of the U-shaped sensor frame up to 270cm, the unmanned vehicle system can collect phenotypic data from tall crops, and the efficiency of adjusting the height of the U-shaped sensor frame in the unmanned vehicle system can be improved, thereby enhancing the passability and stability of the unmanned vehicle system in field environments with densely planted tall crops.

[0042] Optionally, the width of the U-shaped sensor frame can be adjusted. Existing unmanned vehicle systems for crop phenotypic data acquisition have a relatively fixed acquisition width. This limits their application to greenhouse environments where crop spacing is relatively constant, and they struggle to adapt to variations in crop spacing and field environmental fluctuations, potentially causing damage to crops during data acquisition. By making the width of the U-shaped sensor frame adjustable, the unmanned vehicle system can better adapt to changes in field environments and crop spacing. For example, the adjustable width of the U-shaped sensor frame could include 140cm, 160cm, and 180cm, thereby further improving the efficiency of the frame width adjustment.

[0043] Optionally, the left and right acquisition sensors each have a basal observation layer, a middle observation layer, and a top observation layer. The basal observation layer can be used to collect phenotypic data from the base of the crop. The middle observation layer can be used to collect phenotypic data from the middle of the crop. The top observation layer can be used to collect phenotypic data from the upper layers of the crop. Optionally, multiple sensor mounting points can be set on the U-shaped sensor frame using an adjustable snap-fit ​​mechanism. Optionally, multiple acquisition sensors with different viewing directions can be arranged in each layer. For example,... Figure 6 As shown, the upper view image represents crop phenotypic data collected from the top observation layer. The middle view image represents crop phenotypic data collected from the middle observation layer. The lower view image represents crop phenotypic data collected from the basal observation layer. By further refining the left and right acquisition sensors into basal, middle, and top observation layers, multi-angle and multi-scale phenotypic data acquisition at different vertical heights (basal, middle, and top) of the crop can be achieved. Through a multi-level deployment structure, complete crop structure information coverage from the ground surface to the ear is achieved, providing basic data for the quantification of key traits such as ear height, leaf posture, and stem diameter, significantly increasing the dimensionality of crop phenotypic data acquisition and improving the comprehensiveness and richness of the collected crop phenotypic data. Furthermore, the installation height of the basal observation layer is 30cm-50cm; the installation height of the middle observation layer is 90cm-120cm; and the installation height of the top observation layer is 160cm-200cm. By specifying the installation height of the basal observation layer to 30cm-50cm, the middle observation layer to 90cm-120cm, and the top observation layer to 160cm-200cm, the installation efficiency of the basal, middle, and top observation layers was improved, thereby increasing the efficiency of crop phenotypic data collection.

[0044] The technical solution of this invention, through a four-wheeled unmanned vehicle body with independent drive and steering design, can achieve differential steering and right-angle turns, adapting to different terrain conditions and effectively improving the flexibility of the unmanned vehicle system in field travel. By mounting the acquisition sensors separately around a U-shaped sensor frame, it is possible to collect data on crops from different angles. Through zoned management and control of the acquisition sensors, the flexibility and adaptability of crop phenotypic data acquisition are further improved. By using zoned power supply for each group of battery boxes, the limitation of the position and volume of the battery boxes on the height of crops that can be collected is avoided when the unmanned vehicle system is powered uniformly, further improving the flexibility of the unmanned vehicle system. Thus, the passability and stability of the unmanned vehicle system are improved, enabling the acquisition of crop phenotypic data in different field environments, adapting to various farmland terrains and planting patterns, and possessing strong potential for widespread application.

[0045] Example 2

[0046] Figure 7 This is a flowchart illustrating a crop phenotypic data acquisition method according to Embodiment 2 of the present invention. This embodiment of the invention is applicable to situations where crop phenotypic data is collected in a field environment. The method can be executed by a crop phenotypic data acquisition device, which can be implemented in hardware and / or software. This device can be configured within an electronic device that performs crop phenotypic data acquisition, such as a controller.

[0047] See Figure 7 The crop phenotypic data collection methods shown include:

[0048] S701. During the operation preparation stage, the target acquisition height and target acquisition angle of each group of acquisition sensors are determined based on the spatial resolution of the crops detected by each group of acquisition sensors.

[0049] The preparation phase refers to the stage before the data collection task is executed. The field crop refers to the crop phenotypic data being collected in the field environment. Spatial resolution characterizes the completeness and clarity of the phenotypic data of the field crop collected by the acquisition sensor. The target acquisition height is the acquisition height that the acquisition sensor needs to reach. The target acquisition angle is the acquisition angle that the acquisition sensor needs to reach. There can be a corresponding relationship between spatial resolution, acquisition height, and acquisition angle.

[0050] Specifically, during the preparation phase, the spatial resolution of crops detected by each set of acquisition sensors can be obtained. Based on the correspondence between spatial resolution and acquisition height and angle, the target acquisition height and angle for each set of acquisition sensors are determined.

[0051] Optionally, during the preparation phase, different types of data acquisition sensors can be selected and installed on the U-shaped sensor frame according to the growth height and planting density of the crops in the plot, and the height and angle of the data acquisition sensors can be adjusted and calibrated.

[0052] S702. For a single set of acquisition sensors, the height of the U-shaped sensor frame is adjusted according to the target acquisition height of the acquisition sensor.

[0053] Specifically, for a single set of acquisition sensors, the height of the U-shaped sensor frame can be adjusted so that the actual acquisition height of the acquisition sensor mounted on the U-shaped sensor frame reaches the target acquisition height.

[0054] S703. For a single set of acquisition sensors, adjust the angle of the acquisition sensor according to the target acquisition angle of the acquisition sensor.

[0055] Specifically, for a single set of acquisition sensors, the angle of the acquisition sensor can be adjusted so that the actual acquisition angle of the acquisition sensor reaches the target acquisition angle.

[0056] S704. During the job execution phase, obtain the crop row spacing and data type of the data collection task.

[0057] The task execution phase can be the execution phase of the data collection task. The data collection task can be the collection of crop phenotypic data in a field environment. Crop row spacing can be the distance between crops in a field environment. The data type of the data collected can be the data type of the phenotypic data to be collected.

[0058] Specifically, during the operation execution phase, the crop row spacing and data type of the data collection task can be obtained through the vehicle-mounted touch screen or remote control terminal.

[0059] S705. Adjust the width of the U-shaped sensor frame according to the crop row spacing of the data acquisition task.

[0060] Specifically, the width of the U-shaped sensor frame can be adjusted so that the unmanned vehicle system can collect data on the crop row spacing for the task.

[0061] S706. Based on the type of data to be acquired, select the target acquisition sensor corresponding to the type of data from among the acquisition sensors, and use the target acquisition sensor to perform the acquisition task.

[0062] The target acquisition sensor can be the acquisition sensor corresponding to the type of acquisition data.

[0063] Specifically, based on the type of data being acquired, a target acquisition sensor corresponding to the data type can be selected from among the various acquisition sensors, and the target acquisition sensor can be used to perform the acquisition task.

[0064] The technical solution of this invention, in the operation preparation stage, determines the target acquisition height and target acquisition angle of each group of acquisition sensors based on the spatial resolution of the crops detected by each group of acquisition sensors. For a single group of acquisition sensors, the height of the U-shaped sensor frame is adjusted according to the target acquisition height, and the angle of the acquisition sensor is adjusted according to the target acquisition angle. This achieves height adjustment of the U-shaped sensor frame and angle adjustment of the acquisition sensors in the operation preparation stage, improving the adaptability of acquisition height and angle. In the operation execution stage, the crop row spacing and acquisition data of the acquisition task are obtained. The width of the U-shaped sensor frame is adjusted according to the crop row spacing of the acquisition task. According to the acquisition data type, the target acquisition sensor corresponding to the acquisition data type is selected from each acquisition sensor, and the acquisition task is executed using the target acquisition sensor. This achieves width adjustment of the U-shaped sensor frame and selection of acquisition sensors, improving the flexibility and adaptability of crop phenotypic data acquisition. Therefore, it can support flexible adjustments for different crop heights, different growth stages, and different acquisition task scenarios, has strong scalability, a wide range of applicable crops, and good versatility and application promotion value.

[0065] Based on the above embodiments, the crop phenotypic data acquisition device of the present invention further includes: an autonomous navigation and obstacle avoidance module (i.e., a control decision module), a multi-sensor synchronous acquisition and fusion module (i.e., a data acquisition and fusion module), a data management and remote control platform (i.e., a communication and remote control module), and a post-processing and phenotypic analysis support module.

[0066] The autonomous navigation and obstacle avoidance module is equipped with a high-precision positioning system, an inertial navigation system (IMU), and an environmental perception module (i.e., equipped with LiDAR and cameras). It supports autonomous path planning, local dynamic obstacle avoidance, and trajectory tracking in the field, improving the stability and safety of field operations. The high-precision positioning system achieves a positioning accuracy of ±2cm; the inertial navigation system is used for attitude estimation and short-term navigation compensation; and the environmental perception module supports environmental mapping and positioning in the absence of GPS (Global Positioning System). The autonomous navigation and obstacle avoidance process includes: after the unmanned vehicle system starts, it first performs initial positioning using the high-precision positioning system and constructs a local environmental map using point cloud data collected by the LiDAR. During field movement, the unmanned vehicle system continuously receives attitude data from the inertial navigation system and obstacle information from the environmental perception module. Combined with real-time path planning algorithms, it dynamically adjusts its direction of travel to achieve precise movement and real-time obstacle avoidance, preventing collisions with crop plants.

[0067] The multi-sensor synchronous acquisition and fusion module establishes a unified embedded data acquisition and control system. Based on a distributed robot operating system architecture and timestamp management mechanism, it realizes the acquisition, preprocessing, and synchronous storage of data from multiple sensors, and supports subsequent point cloud modeling, image recognition, and trait analysis. During field navigation, the acquisition sensors at each height level begin synchronously collecting crop phenotypic data according to the task instructions. All phenotypic data are timestamped and cached on the industrial control computer, while preliminary data preprocessing (such as image distortion correction, noise filtering, and data format standardization) is performed. If abnormalities are detected during the crop phenotypic data acquisition process (such as obstacles or tire slippage), the system can automatically feed back to the autonomous navigation and obstacle avoidance module to interrupt the task or replan the path. The unified acquisition time and time synchronization mechanism can significantly reduce data deviation between acquisition sensors, improve the spatial consistency and semantic modeling capabilities of fused images and point clouds, and significantly enhance the multi-source data fusion and processing capabilities.

[0068] The data management and remote control platform communicates with a remote server via a 4G / 5G module, supporting real-time data transmission, task scheduling, and remote control. A visual data management platform and a work record system are also developed to facilitate data querying and task scheduling. During operation, collected data can be stored locally in real-time via a high-capacity SSD; if the network signal is stable, it can be uploaded to a remote server via the 4G / 5G module. Users can view the operating status of the unmanned vehicle system, the working status of the data acquisition sensors, and the quality of crop phenotypic data collection on the data management and remote control platform, and remotely modify work tasks.

[0069] The post-processing and phenotypic analysis support module allows all crop phenotypic data to be exported to the plant phenotypic analysis platform after the operation is completed. Combined with point cloud registration, image recognition and statistical modeling algorithms, indicators such as plant height, leaf tilt angle, ear height, NDVI distribution map and temperature heat map are calculated to provide decision-making basis for agronomic management and breeding evaluation.

[0070] Through the innovative modular design, multi-level sensor deployment, and adaptive control strategy of the multi-height, multi-source sensing unmanned vehicle system with a surrounding frame of this invention, complete, accurate, and high-frequency phenotypic data acquisition of tall crop populations is achieved. This solves the problems of existing technologies where most platforms are designed for short-stalk crops or greenhouse operations, have compact structures and low deployment heights, and cannot meet the observation needs of multi-level structures of tall crops in field environments. Furthermore, the high rigidity of the vehicle body and poor passability make it susceptible to obstacles in densely planted or complex terrain fields. Additionally, the multi-sensor information fusion and spatiotemporal synchronization mechanisms are not yet perfect, resulting in fragmented and insufficiently covered sensing information, making it difficult to support high-precision modeling and intelligent analysis. This invention improves the passability and stability of the unmanned vehicle system in densely planted environments of tall crops, realizes multi-angle and multi-scale phenotypic information acquisition from different vertical heights (base, middle, and top) of crops, supports data fusion and time synchronization of multi-source sensors, improves the accuracy of crop trait modeling, can adapt to various farmland terrains and planting patterns, and has strong potential for widespread application.

[0071] Example 3

[0072] This invention provides a crop phenotypic data acquisition device according to Embodiment 3. This embodiment is applicable to situations where crop phenotypic data is collected in a field environment. The device can execute a crop phenotypic data acquisition method and can be implemented in hardware and / or software. The device can be configured in an electronic device that carries the crop phenotypic data acquisition function, such as a controller.

[0073] The crop phenotypic data acquisition device includes: a target acquisition height determination module, used to determine the target acquisition height and target acquisition angle of each group of acquisition sensors based on the spatial resolution of the crops detected by each group of acquisition sensors during the operation preparation stage; an acquisition sensor height adjustment module, used to adjust the height of the U-shaped sensor frame for a single group of acquisition sensors according to the target acquisition height of the acquisition sensor; an acquisition sensor angle adjustment module, used to adjust the angle of the acquisition sensor for a single group of acquisition sensors according to the target acquisition angle of the acquisition sensor; an acquisition task parameter acquisition module, used to acquire the crop row spacing and acquisition data type of the acquisition task during the operation execution stage; a U-shaped sensor frame width adjustment module, used to adjust the width of the U-shaped sensor frame according to the crop row spacing of the acquisition task; and an acquisition sensor filtering module, used to filter the target acquisition sensor corresponding to the acquisition data type among the acquisition sensors, and use the target acquisition sensor to perform the acquisition task.

[0074] The technical solution of this invention, in the operation preparation stage, determines the target acquisition height and target acquisition angle of each group of acquisition sensors based on the spatial resolution of the crops detected by each group of acquisition sensors. For a single group of acquisition sensors, the height of the U-shaped sensor frame is adjusted according to the target acquisition height, and the angle of the acquisition sensor is adjusted according to the target acquisition angle. This achieves height adjustment of the U-shaped sensor frame and angle adjustment of the acquisition sensors in the operation preparation stage, improving the adaptability of acquisition height and angle. In the operation execution stage, the crop row spacing and acquisition data of the acquisition task are obtained. The width of the U-shaped sensor frame is adjusted according to the crop row spacing of the acquisition task. According to the acquisition data type, the target acquisition sensor corresponding to the acquisition data type is selected from each acquisition sensor, and the acquisition task is executed using the target acquisition sensor. This achieves width adjustment of the U-shaped sensor frame and selection of acquisition sensors, improving the flexibility and adaptability of crop phenotypic data acquisition. Therefore, it can support flexible adjustments for different crop heights, different growth stages, and different acquisition task scenarios, has strong scalability, a wide range of applicable crops, and good versatility and application promotion value.

[0075] The crop phenotypic data acquisition device provided in the embodiments of the present invention can execute the crop phenotypic data acquisition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0076] Example 4

[0077] Figure 8 A schematic diagram of a controller 150 that can be used to implement embodiments of the present invention is shown. The controller is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The controller can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0078] like Figure 8As shown, the controller 150 includes at least one processor 151 and a memory, such as a read-only memory (ROM) 152 and a random access memory (RAM) 153, communicatively connected to the at least one processor 151. The memory stores computer programs executable by the at least one processor. The processor 151 can perform various appropriate actions and processes based on the computer program stored in the ROM 152 or loaded into the RAM 153 from storage unit 158. The RAM 153 may also store various programs and data required for the operation of the controller 150. The processor 151, ROM 152, and RAM 153 are interconnected via a bus 154. An input / output (I / O) interface 155 is also connected to the bus 154.

[0079] Multiple components in controller 150 are connected to I / O interface 155, including: input unit 156, such as keyboard, mouse, etc.; output unit 157, such as various types of displays, speakers, etc.; storage unit 158, such as disk, optical disk, etc.; and communication unit 159, such as network card, modem, wireless transceiver, etc. Communication unit 159 allows controller 150 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0080] Processor 151 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 151 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 151 performs the various methods and processes described above, such as crop phenotypic data acquisition methods.

[0081] In some embodiments, the crop phenotypic data acquisition method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 158. In some embodiments, part or all of the computer program may be loaded and / or mounted on controller 150 via ROM 152 and / or communication unit 159. When the computer program is loaded into RAM 153 and executed by processor 151, one or more steps of the crop phenotypic data acquisition method described above may be performed. Alternatively, in other embodiments, processor 151 may be configured to perform the crop phenotypic data acquisition method by any other suitable means (e.g., by means of firmware).

[0082] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0084] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0085] To provide interaction with the user, the systems and techniques described herein can be implemented on a controller having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the controller. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0086] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0087] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0088] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0089] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An unmanned vehicle system for collecting crop phenotypic data, characterized in that, The system includes: an unmanned vehicle body, a U-shaped sensor frame, three sets of data acquisition sensors, three battery boxes, and a controller; The unmanned vehicle body includes four wheels with independent drive and steering design; The upper part of the unmanned vehicle body is connected to the U-shaped sensor frame; The three sets of acquisition sensors include a left acquisition sensor, a top acquisition sensor, and a right acquisition sensor; the three sets of acquisition sensors are respectively mounted in a surrounding manner on the left frame, top frame, and right frame of the U-shaped sensor frame; The three battery boxes include a left battery box, a right battery box, and a top battery box; the left battery box is connected to the left wheel and the left acquisition sensor, and is used to power the left wheel and the left acquisition sensor; the right battery box is connected to the right wheel and the right acquisition sensor, and is used to power the right wheel and the right acquisition sensor; the top battery box is connected to the top acquisition sensor, and is used to power the top acquisition sensor. The controller is connected to each of the wheels, the chassis of each wheel, the U-shaped sensor frame, the acquisition sensor, and the battery box, and is used to control the unmanned vehicle system for acquiring crop phenotypic data.

2. The system according to claim 1, characterized in that, The wheel chassis height of each wheel is adjustable.

3. The system according to claim 2, characterized in that, The ground clearance of the wheel chassis of each wheel is 300mm; the adjustable height is ±100mm.

4. The system according to claim 1, characterized in that, The main body of the unmanned vehicle and the U-shaped sensor frame are made of aluminum alloy.

5. The system according to claim 1, characterized in that, The height of the U-shaped sensor frame is adjustable.

6. The system according to claim 5, characterized in that, The height of the U-shaped sensor frame can reach 270cm.

7. The system according to any one of claims 1, 5, and 6, characterized in that, The width of the U-shaped sensor frame is adjustable.

8. The system according to claim 1, characterized in that, The left-side acquisition sensor and the right-side acquisition sensor each have a base observation layer, a middle observation layer, and a top observation layer, respectively.

9. The system according to claim 8, characterized in that, The installation height of the base observation layer is 30cm-50cm; the installation height of the middle observation layer is 90cm-120cm; and the installation height of the top observation layer is 160cm-200cm.

10. A method for collecting crop phenotypic data, characterized in that, The method includes: During the preparation phase, the target acquisition height and target acquisition angle of each group of acquisition sensors are determined based on the spatial resolution of the crops detected by each group of acquisition sensors. For a single set of acquisition sensors, the height of the U-shaped sensor frame is adjusted according to the target acquisition height of the acquisition sensor; For a single set of acquisition sensors, the angle of the acquisition sensor is adjusted according to the target acquisition angle of the acquisition sensor; During the task execution phase, the crop row spacing and data type of the data collection task are obtained; The width of the U-shaped sensor frame is adjusted according to the crop row spacing of the data acquisition task. Based on the type of data to be acquired, a target acquisition sensor corresponding to the type of data is selected from among the acquisition sensors, and the acquisition task is performed using the target acquisition sensor.

Images