Posture positioning method and device, unmanned forklift, readable storage medium and program product

Abstract

The application relates to a pose positioning method and device, an unmanned forklift, a readable storage medium and a program product. A first pose of an unmanned forklift is acquired through a first sensing device, and a second pose of a target object to be operated on the unmanned forklift is acquired through a second sensing device; a pose change amount between the first pose and a preset pose reference anchor point is calculated; wherein the pose reference anchor point is used to represent a standard pose of the unmanned forklift; based on relative position information of the second sensing device on the unmanned forklift and the pose change amount, the second pose is compensated in pose to determine a third pose; and according to the third pose, an execution device of the unmanned forklift is controlled to operate on the target object, so that positioning deviation is effectively inhibited, operation stability and success rate are improved, collision risk is reduced, and system operation efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of logistics automation technology, and in particular to an attitude positioning method, device, unmanned forklift, readable storage medium, and program product. Background Technology

[0002] With the development of the logistics and warehousing industry, unmanned forklifts, with their advantages of high efficiency and precision, are widely used in automated cargo handling and warehousing scenarios. However, because the positioning sensors of unmanned forklifts are installed at a high position on the vehicle, uneven or undulating ground conditions during actual picking operations can cause errors in the sensors' perception of the forklift's own and the cargo's posture. This can lead to problems such as cargo collisions or failed picking during the forklift's entry process, affecting the forklift's operational efficiency and safety. Summary of the Invention

[0003] Therefore, it is necessary to provide an attitude positioning method, device, unmanned forklift, readable storage medium, and program product to address the above-mentioned technical problems. This method can suppress the picking and positioning deviation caused by the combined effect of sensor installation height and uneven ground, improve operational stability and success rate, and reduce collision risk.

[0004] In a first aspect, this application provides an attitude positioning method, which is applied to an unmanned forklift equipped with a first sensing device and a second sensing device. The method includes:

[0005] The first posture of the unmanned forklift is obtained through the first sensing device, and the second posture of the target object to be operated by the unmanned forklift is obtained through the second sensing device.

[0006] Calculate the attitude change between the first attitude and the preset attitude reference anchor point; whereby the attitude reference anchor point is used to characterize the standard attitude of the unmanned forklift.

[0007] Based on the relative position information and attitude change of the second sensing device on the unmanned forklift, attitude compensation is performed on the second attitude to determine the third attitude.

[0008] Based on the third posture, the actuators of the unmanned forklift are controlled to perform operations on the target object.

[0009] In one embodiment, prior to the step of acquiring the first attitude of the unmanned forklift via the first sensing device, the method further includes:

[0010] When the unmanned forklift travels to the target position, its linear velocity, angular velocity and acceleration information are collected.

[0011] Once the unmanned forklift meets the preset stability conditions, it is determined that the unmanned forklift has entered the target state.

[0012] The current attitude information of the unmanned forklift in the target state at the target position is used as the attitude reference anchor point; wherein, the preset stability conditions include at least one of the following: linear velocity information is lower than a first threshold, angular velocity information is lower than a second threshold, and acceleration information is within a preset range of gravitational acceleration.

[0013] In one embodiment, the step of acquiring the second posture of the target object to be operated by the unmanned forklift through the second sensing device includes:

[0014] The second sensing device acquires a captured image including the target object, and calculates the target coordinate information of the target object in the captured image;

[0015] Based on the device parameters of the second sensing device and the relative positional relationship between the second sensing device and the unmanned forklift, the target coordinate information is converted into corresponding two-dimensional pose information to obtain the second pose.

[0016] In one embodiment, the attitude change includes pitch angle change and roll angle change. After calculating the attitude change between the first attitude and a preset attitude reference anchor point, the method further includes:

[0017] When the pitch angle change is greater than the third threshold or the roll angle change is greater than the fourth threshold, the unmanned forklift is determined to be in an abnormal posture.

[0018] When the unmanned forklift is in an abnormal posture, output a prompt message to indicate how to handle the abnormal posture.

[0019] In one embodiment, the relative position information of the second sensing device on the unmanned forklift includes height information;

[0020] The steps for determining the third attitude based on the relative position information and attitude change of the second sensing device on the unmanned forklift include:

[0021] Based on the pitch angle change and altitude information, calculate the first compensation amount used to represent the direction of operation;

[0022] Based on the change in side tilt angle and height information, a second compensation amount is calculated to represent the direction perpendicular to the working direction.

[0023] Based on the first compensation amount and the second compensation amount, determine the horizontal projection deviation from the observation plane where the second sensing device is located to the control reference plane of the unmanned forklift.

[0024] Based on the horizontal projection deviation, the second attitude is corrected to determine the third attitude.

[0025] In one embodiment, the steps of controlling the actuator of the unmanned forklift to perform operations on the target object according to the third posture include:

[0026] Based on the third posture, a first control command is generated to control the unmanned forklift in the working direction, and a second control command is generated to control the unmanned forklift in a direction perpendicular to the working direction.

[0027] In response to the first control command, the position of the unmanned forklift is adjusted, and the operation is performed on the target object based on the adjusted position;

[0028] In response to the second control command, the lateral angle of the unmanned forklift is adjusted, and the operation is performed on the target object based on the adjusted lateral angle.

[0029] Secondly, this application also provides an attitude positioning device, which is applied to an unmanned forklift. The unmanned forklift is equipped with a first sensing device and a second sensing device. The device includes:

[0030] The acquisition module is used to acquire the first posture of the unmanned forklift through the first sensing device and to acquire the second posture of the target object to be operated by the unmanned forklift through the second sensing device.

[0031] The calculation module is used to calculate the change in attitude between the first attitude and the preset attitude reference anchor point; wherein, the attitude reference anchor point is used to represent the standard attitude of the unmanned forklift.

[0032] The compensation module is used to perform attitude compensation on the second attitude based on the relative position information and attitude change of the second sensing device on the unmanned forklift, so as to determine the third attitude.

[0033] The control module is used to control the actuators of the unmanned forklift to perform operations on the target object based on the third posture.

[0034] Thirdly, this application also provides an unmanned forklift, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the attitude positioning method provided in the first aspect above.

[0035] Fourthly, this application also provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the attitude localization method provided in the first aspect above.

[0036] Fifthly, this application also provides a program product, including a computer program that, when executed by a processor, performs the steps of the attitude positioning method provided in the first aspect above.

[0037] The aforementioned attitude positioning method, device, unmanned forklift, readable storage medium, and program product are described. The attitude positioning method is applied to an unmanned forklift equipped with a first sensing device and a second sensing device. The first sensing device acquires the first attitude of the unmanned forklift, and the second sensing device acquires the second attitude of the target object to be operated on. The attitude change between the first attitude and a preset attitude reference anchor point is calculated; the attitude reference anchor point represents the standard attitude of the unmanned forklift. Based on the relative position information of the second sensing device on the unmanned forklift and the attitude change, attitude compensation is performed on the second attitude to determine a third attitude. Based on the third attitude, the actuator of the unmanned forklift is controlled to operate on the target object. Thus, by acquiring the attitude of the unmanned forklift and the attitude of the target object, calculating the attitude change, and compensating for it to determine the third attitude for operation control, the method effectively suppresses the picking and positioning deviation caused by the combined effect of sensor installation height and uneven ground, effectively suppressing positioning deviation, improving operational stability and success rate, reducing collision risk, and improving system operating efficiency. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is an application environment diagram of the attitude localization method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating an attitude localization method in one embodiment;

[0041] Figure 3 This is a schematic diagram of a module of an unmanned forklift in one embodiment;

[0042] Figure 4 This is a schematic diagram illustrating an extended process of the attitude localization method in one embodiment;

[0043] Figure 5 This is a flowchart illustrating the attitude localization method in another embodiment;

[0044] Figure 6 This is a schematic diagram of a scenario flow for an attitude localization method in one embodiment;

[0045] Figure 7 This is a structural block diagram of an attitude positioning device in one embodiment;

[0046] Figure 8This is an internal structural diagram of an unmanned forklift in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0049] The attitude positioning method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Terminal 102 can be equipped with a first sensing device and a second sensing device. The first sensing device acquires the first posture of the unmanned forklift, and the second sensing device acquires the second posture of the target object to be operated by the unmanned forklift. After acquiring the first posture of the unmanned forklift and the second posture of the target object, the posture change between the first posture and a preset posture reference anchor point can be calculated. Based on the relative position information of the second sensing device on the unmanned forklift and the posture change, posture compensation is performed on the second posture to determine a third posture. Finally, based on the third posture, the actuator of the unmanned forklift is controlled to perform operations on the target object.

[0050] Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones (e.g., unmanned forklifts), low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0051] With the accelerated automation of the logistics and warehousing industry, unmanned forklifts have become core equipment for scenarios such as cargo handling and warehouse management due to their high efficiency and precise operation. Currently, most unmanned forklift systems rely on two-dimensional navigation technology for positioning and path planning. This technology is based on the ideal assumption that the vehicle is always moving in a horizontal plane and does not fully consider the dynamic attitude changes of the vehicle body in three-dimensional space.

[0052] In real-world operating environments, warehouse floors are generally uneven, undulating, or subject to localized subsidence. This inevitably causes unmanned forklifts to experience pitch or tilt when traveling at low speeds or performing picking and loading tasks. Since positioning sensors (e.g., vision cameras or lidar) are typically mounted higher on the vehicle to obtain a wider field of view and avoid obstruction by goods, while the vehicle control reference point (e.g., chassis center or fork arm reference point) is located at a lower position, this height difference leads to significant spatial pose decoupling problems when the vehicle's attitude changes. Specifically, when an unmanned forklift experiences a slight pitch or tilt due to uneven ground, the projection deviation of the high-position sensor in the two-dimensional plane will far exceed the actual displacement of the low-position control reference point due to the geometric amplification effect of the installation height. This causes continuous fluctuations between the cargo pose information collected by the sensor and the actual control reference point position. These fluctuations are directly transmitted to the cargo recognition and control system, resulting in unstable positioning and frequent adjustments to control commands during forklift entry. This not only significantly increases the risk of collisions with cargo or shelves but also significantly reduces the success rate of operations and the efficiency of system operation.

[0053] To address these issues, existing technologies employ 3D navigation or 3D mapping schemes, using a 3D model of the environment to correct attitude errors. However, constructing a 3D model requires structural modifications to the existing 2D navigation framework, involving complex hardware upgrades and algorithm reconstruction. This significantly increases system costs and implementation difficulty, and the large volume of 3D data processing and lengthy modeling time make it difficult to meet the stringent real-time and cost-effective requirements of warehousing scenarios. Therefore, while maintaining the existing 2D navigation architecture, effectively suppressing the picking and positioning deviations caused by the combined effects of sensor installation height and uneven ground has become a key bottleneck restricting the development of unmanned forklift technology.

[0054] In one exemplary embodiment, such as Figure 2 As shown, an attitude localization method is provided, which is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 21 to 24, wherein:

[0055] As one implementation method, the terminal 102 can be an unmanned forklift, such as... Figure 3As shown, an unmanned forklift may include: an attitude acquisition module, a cargo recognition module, an attitude compensation module, a vehicle control module, a vehicle body, and a two-dimensional navigation module.

[0056] The system comprises several modules: an attitude acquisition module (which can be a first sensing device installed on the forklift to acquire attitude information of the unmanned forklift); a cargo recognition module (which can be a second sensing device installed on the forklift to identify the current pose of a target object); an attitude compensation module (which, after acquiring the first attitude of the forklift and the second attitude of the target object, corrects the identified second attitude based on the first attitude to determine the actual relative position between the target object and the forklift); a vehicle control module (which, after determining the third attitude obtained through compensation of the second attitude, controls the vehicle to perform operations on the target object); and a two-dimensional navigation module (which controls the vehicle to move within a preset area).

[0057] Step 21: Obtain the first posture of the unmanned forklift through the first sensing device, and obtain the second posture of the target object to be operated by the unmanned forklift through the second sensing device.

[0058] The first sensing device refers to the sensor installed on the unmanned forklift to obtain the attitude information of the unmanned forklift itself. The first sensing device can be an inertial measurement unit, tilt sensor or lidar, which can be used to monitor the attitude changes of the unmanned forklift in space in real time, such as tilt and pitch.

[0059] Here, the first attitude can refer to the real-time spatial attitude information of the unmanned forklift itself obtained by the first sensing device, which usually includes the pitch angle, roll angle and heading angle of the unmanned forklift.

[0060] The second sensing device refers to a sensor installed on the unmanned forklift to acquire the posture information of the target object to be operated. The second sensing device can be a vision camera, depth camera, lidar or ultrasonic sensor, which can be used to identify and locate the position and posture of the target object in the field of view of the unmanned forklift.

[0061] Here, the second attitude can refer to the attitude information of the target object to be operated relative to the second sensing device, which is obtained by the second sensing device. The second attitude can typically include the position and attitude of the target object in the sensor coordinate system.

[0062] The target object can refer to the entity that the unmanned forklift needs to operate on, such as pallets, boxes of goods, or items to be moved on shelves.

[0063] In practical applications, the first sensing device can be a simple tilt sensor mounted on the autonomous forklift chassis to directly measure the chassis's pitch and roll angles. For example, when the autonomous forklift is traveling on uneven ground, the tilt sensor outputs real-time pitch and roll angle data as the forklift's first attitude. The second sensing device can be a standard 2D camera mounted on the forklift's uprights, configured to periodically capture images of the area in front of the forklift. After acquiring the images, the operator can manually select target objects within the images and record their pixel coordinates as the target object's second attitude.

[0064] Step 22: Calculate the attitude change between the first attitude and the preset attitude reference anchor point.

[0065] Among them, the attitude reference anchor point is used to represent the standard attitude of the unmanned forklift.

[0066] It should be noted that the attitude reference anchor point can refer to a preset reference value used to characterize the standard attitude of the unmanned forklift. It can be used to represent the attitude of the unmanned forklift in an ideal horizontal and stable state, and serve as the benchmark for subsequent attitude change calculations.

[0067] Here, attitude change can refer to the difference between the real-time first attitude of the unmanned forklift and the attitude reference anchor point, which can be used to reflect the degree of tilt or deflection of the unmanned forklift relative to its standard attitude.

[0068] In one embodiment, the attitude reference anchor point can be a pre-set fixed value. For example, the attitude of the unmanned forklift on a perfectly level ground is defined as the standard attitude, with both pitch and roll angles at zero degrees. When the unmanned forklift starts operating, a first attitude including real-time pitch and roll angles is acquired and directly compared with the zero-degree standard attitude to obtain the pitch and roll angle changes. For example, if the first attitude of the unmanned forklift shows a pitch angle of 2 degrees and a roll angle of 1 degree, while the attitude reference anchor point shows a pitch angle of 0 degrees and a roll angle of 0 degrees, then the attitude changes are calculated as a pitch angle change of 2 degrees and a roll angle change of 1 degree.

[0069] Step 23: Based on the relative position information and attitude change of the second sensing device on the unmanned forklift, attitude compensation is performed on the second attitude to determine the third attitude.

[0070] The third attitude refers to the attitude information of the target object relative to the control reference point of the unmanned forklift, which is obtained after attitude compensation and is more accurate. The third attitude can be used to guide the precise operation of the unmanned forklift.

[0071] Relative position information can refer to the installation position parameters of the second sensing device on the unmanned forklift body. Relative position information can include the three-dimensional coordinates of the second sensing device relative to the control reference point of the unmanned forklift, such as height and lateral offset.

[0072] The relative position information of the second sensing device on the unmanned forklift can be a preset fixed height value, such as the vertical distance between the center of the camera lens and the control reference point of the unmanned forklift (such as the center of the drive wheel).

[0073] In one embodiment, when the unmanned forklift changes its attitude, the position of the second sensing device shifts accordingly. Attitude compensation can be performed using a simplified geometric model. For example, a linear compensation value for the target object in the vertical direction can be calculated based on the pitch angle change and the height information; simultaneously, another linear compensation value for the target object in the horizontal direction can be calculated based on the roll angle change and the height information. These compensation values ​​are then directly superimposed onto the original second attitude (e.g., the pixel coordinates of the target object) to obtain the corrected third attitude.

[0074] Step 24: Based on the third posture, control the actuator of the unmanned forklift to perform operations on the target object.

[0075] The actuator can refer to the mechanical components on an unmanned forklift used to complete specific tasks. For example, components such as forks, lifting mechanisms, or grippers are used to perform operations on target objects.

[0076] After obtaining the compensated third posture, this posture information is directly converted into movement commands for the forklift. For example, if the third posture indicates that the target object is offset 5 cm to the left relative to the control reference point of the unmanned forklift and needs to be lifted 10 cm, the control system will generate a command to move the forklift 5 cm to the left and lift it 10 cm to perform a precise forklifting operation on the target object.

[0077] The aforementioned attitude positioning method achieves precise attitude positioning of the target object through intelligent compensation of sensor data. This avoids increasing system complexity and hardware costs, while effectively solving problems such as time-consuming 3D modeling and large data processing volume. Through this attitude compensation, the final third attitude more accurately reflects the true position of the target object relative to the control reference plane of the unmanned forklift, enabling the actuator to operate according to precise instructions. This significantly improves the operating accuracy, stability, and safety of the unmanned forklift on uneven ground. Therefore, it provides an efficient and economical method to effectively suppress the unstable picking and positioning problem caused by the combined effect of high sensor installation height and uneven ground, demonstrating its technological advancement and practicality.

[0078] In one exemplary embodiment, such as Figure 4 As shown, the attitude localization method further includes steps 101 to 103. Wherein:

[0079] Step 101: When the unmanned forklift travels to the target position, collect the linear velocity, angular velocity and acceleration information of the unmanned forklift.

[0080] Among them, linear velocity information refers to the speed of the unmanned forklift along its direction of movement, which can be used to reflect the speed of the unmanned forklift's translational movement.

[0081] In practical applications, wheel speed can be measured by wheel encoders and calculated in combination with wheel radius, or integral calculation can be performed by inertial measurement unit, or the linear velocity information of unmanned forklifts can be obtained by external positioning systems such as GPS or LiDAR.

[0082] Furthermore, angular velocity information refers to the speed at which the unmanned forklift rotates around its own axis, which can be used to reflect how fast the unmanned forklift rotates.

[0083] In one specific implementation, angular velocity information can be collected by a gyroscope sensor in the inertial measurement unit. The inertial measurement unit can directly measure the angular velocity components of the unmanned forklift in three-dimensional space to obtain the angular velocity information.

[0084] Furthermore, acceleration information can be used to represent the rate of change of the unmanned forklift's speed. Acceleration information can include linear acceleration and angular acceleration. Linear acceleration, as the vertical component of the unmanned forklift, can be used to determine whether the forklift is stationary or in uniform linear motion. Here, acceleration information can be obtained through the accelerometer sensor in the inertial measurement unit.

[0085] Step 102: If the unmanned forklift meets the preset stability conditions, determine that the unmanned forklift has entered the target state.

[0086] The preset stability conditions include at least one of the following: linear velocity information is lower than a first threshold, angular velocity information is lower than a second threshold, and acceleration information is within a preset range of gravitational acceleration.

[0087] Specifically, if the linear velocity information is below a first threshold, it indicates that the translational speed of the unmanned forklift is very small, close to being stationary. The first threshold can be a positive value close to zero, for example, 0.1 m / s, indicating that the unmanned forklift is in a state of slight movement or complete stop.

[0088] If the angular velocity information is below the second threshold, it indicates that the rotational speed of the unmanned forklift is very small, close to no rotation. The second threshold can also be a positive value close to zero, such as 0.5 degrees / second, indicating that the unmanned forklift does not have obvious steering or swaying.

[0089] Acceleration information within the preset range of gravitational acceleration means that the vertical acceleration component of the unmanned forklift is close to the Earth's gravitational acceleration (approximately 9.8 m / s²), while the horizontal acceleration component is close to zero. This indicates that the unmanned forklift is at rest or in uniform linear motion and is not affected by other non-gravitational accelerations.

[0090] Step 103: Use the current attitude information of the unmanned forklift in the target state at the target position as the attitude reference anchor point.

[0091] Among them, the attitude reference anchor point is the reference attitude used for subsequent attitude change calculation. It sets the current attitude information in the target state as the current attitude information of the unmanned forklift in the target state, which can ensure that the anchor point is established based on the actual and stable physical state of the unmanned forklift.

[0092] In the above scheme, after the unmanned forklift reaches the target position, its linear velocity, angular velocity, and acceleration information are collected. Based on preset stability conditions, these collected motion information are evaluated. Only when the unmanned forklift meets these stability conditions—that is, its linear velocity, angular velocity, and acceleration are all within a very small range, indicating that the unmanned forklift has reached a relatively static or stable target state—is its current attitude information stored as an attitude reference anchor point. This avoids using preset fixed anchor points that may not conform to the actual situation, thus providing a more accurate benchmark for calculating the attitude change between the initial attitude and the attitude reference anchor point. Therefore, the attitude reference anchor point can more accurately represent the standard attitude of the unmanned forklift, thereby improving the accuracy and reliability of the entire attitude positioning method.

[0093] In one exemplary embodiment, such as Figure 5 As shown, the attitude localization method includes steps 201 to 211. Wherein:

[0094] Step 201: Obtain the first posture of the unmanned forklift through the first sensing device, and obtain the captured image including the target object through the second sensing device, and calculate the target coordinate information of the target object in the captured image.

[0095] The acquired image refers to the visual data containing the target object to be processed captured by the second sensing device, which can be used to identify and locate the target object in the scene. The acquired image can be a still image frame or a frame from a video stream.

[0096] It should be noted that the second sensing device can be an optical camera, such as a monocular camera or a binocular camera, or a vision sensor integrated into an unmanned forklift.

[0097] After acquiring images including the target object through a second sensing device, the acquired images can be processed to identify the target object and determine its position in the image plane. Specifically, deep learning models can be used for target detection to obtain the bounding box or key point coordinates of the target object; or feature extraction algorithms and template matching, image segmentation, and other methods can be used to locate the target object and calculate its coordinate information such as center point, corner point, or contour point in the image.

[0098] Step 202: Based on the device parameters of the second sensing device and the relative positional relationship between the second sensing device and the unmanned forklift, the target coordinate information is converted into corresponding two-dimensional pose information to obtain the second pose.

[0099] The second pose can be achieved by using known sensor internal parameters and their installation position on the unmanned forklift to convert the two-dimensional coordinate information in the image into two-dimensional pose information in the local coordinate system of the unmanned forklift.

[0100] It should be noted that converting target coordinate information into corresponding two-dimensional pose information can transform sensor-specific image data into a pose representation that can be understood and utilized by the unmanned forklift, thereby bridging the gap between the original image data and the requirements of the control system.

[0101] Here, device parameters may include internal parameters such as camera focal length, principal point coordinates, and lens distortion coefficients. Relative positional relationship refers to the fixed installation position and attitude of the second sensing device relative to the unmanned forklift body, typically described by a transformation matrix that includes rotation and translation information.

[0102] In one embodiment, target information can be converted into two-dimensional pose information using camera calibration techniques and perspective projection principles. For example, when the target object is located on a specific plane (such as the ground), image coordinates can be converted into two-dimensional coordinates on that plane using homography transformation. Alternatively, when the second sensing device can provide depth information, the 3D coordinates of the target object can be directly calculated, and then projected or simplified into two-dimensional position (x, y) and orientation (yaw angle) information in the local coordinate system of the unmanned forklift, i.e., two-dimensional pose information.

[0103] Step 203: Calculate the attitude change between the first attitude and the preset attitude reference anchor point.

[0104] The content of step 203 can be referred to the above embodiments, and will not be repeated here.

[0105] In one embodiment, the attitude change includes pitch angle change and roll angle change. After step 107, which calculates the attitude change between the first attitude and a preset attitude reference anchor point, the method further includes:

[0106] (1) When the pitch angle change is greater than the third threshold or the roll angle change is greater than the fourth threshold, the unmanned forklift is determined to be in an abnormal posture.

[0107] (2) When the unmanned forklift is in an abnormal posture, output a prompt message to prompt the handling of the abnormal posture.

[0108] The pitch angle change refers to the difference between the tilt angle of the unmanned forklift in the forward and backward direction and the pitch angle in the standard posture, which can be used to reflect the degree of forward or backward tilt of the vehicle.

[0109] In a specific implementation, the pitch angle change can be obtained by acquiring the real-time pitch angle of the unmanned forklift through an inertial measurement unit and comparing it with a preset standard pitch angle, or by calculating the height difference between the front and rear ends of the vehicle body using a laser rangefinder or vision sensor combined with vehicle body structural parameters.

[0110] The change in tilt angle can refer to the difference between the tilt angle of the unmanned forklift in the left and right directions and the tilt angle in the standard posture, which can be used to reflect the degree to which the vehicle body tilts to the left or right.

[0111] In a specific implementation, the change in roll angle can also be obtained by acquiring the real-time roll angle through an inertial measurement unit and comparing it with a preset standard roll angle, or by measuring the height difference between the two sides of the vehicle body using tilt sensors or ultrasonic sensors installed on both sides of the vehicle body.

[0112] It should be noted that the third and fourth thresholds are preset standard parameters used to determine whether the attitude of the unmanned forklift is abnormal. The third threshold defines the maximum acceptable attitude deviation range of the unmanned forklift in the pitch direction, and the fourth threshold defines the maximum acceptable attitude deviation range of the unmanned forklift in the tilt direction.

[0113] When the pitch angle change exceeds the third threshold or the roll angle change exceeds the fourth threshold, a comparator circuit or software logic can be used to determine if the unmanned forklift is in an abnormal posture. Furthermore, fuzzy logic or machine learning models can be introduced to intelligently determine abnormal postures by comprehensively considering multiple parameters.

[0114] When the unmanned forklift is in an abnormal posture, it can output prompts to handle the abnormal posture. This can be issued through the audible and visual alarm device on the unmanned forklift, or displayed as text or graphic warnings on the vehicle display screen or remote monitoring interface. It can also be an instruction sent to the upper control system or remote operator, such as pausing the current operation, entering a safe mode, or requesting manual intervention.

[0115] In this embodiment, the attitude change is refined into pitch angle change and roll angle change, and corresponding thresholds are set for real-time monitoring. When the attitude change in any direction exceeds the preset threshold, the unmanned forklift can be determined to be in an abnormal attitude. This ensures that the attitude of the unmanned forklift is within a controllable and safe range before subsequent operations. Once an abnormal attitude is determined, the system immediately outputs a prompt message, promptly informing the operator or the upper control system that the unmanned forklift has an abnormal attitude and requires intervention or adjustment. Thus, by adding an attitude anomaly detection and early warning mechanism, the unmanned forklift can self-assess the stability of its attitude before performing operations and issue timely alarms when potential risks are detected. This improves the reliability of attitude positioning and provides a higher level of safety assurance for the intelligent operation of the unmanned forklift.

[0116] Step 204: Based on the pitch angle change and altitude information, calculate the first compensation amount used to represent the direction of operation.

[0117] It should be noted that the relative position information of the second sensing device on the unmanned forklift includes height information.

[0118] The first compensation amount can be used to quantify the observation deviation in the working direction caused by the change in the pitch angle of the unmanned forklift and the height of the second sensing device.

[0119] In one implementation, the first compensation amount in the working direction can be calculated using trigonometric functions based on the pitch angle change and altitude information. For example, if the pitch angle change is θ_pitch and the altitude information is H, the first compensation amount can be approximated as H * tan(θ_pitch) or H * sin(θ_pitch). Alternatively, the first compensation amount can be output by inputting the pitch angle change and altitude information through a pre-established lookup table or a machine learning-based model.

[0120] Step 205: Based on the change in side tilt angle and height information, calculate a second compensation amount to represent the direction perpendicular to the working direction.

[0121] The second compensation amount can be used to quantify the observation deviation in the direction perpendicular to the direction of operation caused by the change in the tilt angle of the unmanned forklift and the height of the second sensing device.

[0122] In one specific implementation, a second compensation amount in the direction perpendicular to the working direction can be calculated using trigonometric functions based on the roll angle change and altitude information. For example, if the roll angle change is θ_roll and the altitude information is H, the second compensation amount can be approximated as H * tan(θ_roll) or H * sin(θ_roll). Alternatively, a pre-established lookup table or a machine learning-based model can be used to input the roll angle change and altitude information and output the corresponding second compensation amount.

[0123] Step 206: Determine the horizontal projection deviation from the observation plane where the second sensing device is located to the control reference plane of the unmanned forklift based on the first compensation amount and the second compensation amount.

[0124] The horizontal projection deviation can be calculated by comprehensively calculating the compensation amounts caused in the pitch and roll directions to obtain the overall horizontal offset of the observation point of the second sensing device relative to the actual control reference point of the unmanned forklift.

[0125] In one specific implementation, the horizontal projection deviation can be directly constructed by treating the first compensation amount and the second compensation amount as components of a two-dimensional vector to form the horizontal projection deviation vector. Alternatively, the horizontal projection deviation can be calculated by using a coordinate transformation matrix to project points on the observation plane of the second sensing device onto the control reference plane of the unmanned forklift after pitch and roll transformations.

[0126] Step 207: Based on the horizontal projection deviation, correct the second attitude to determine the third attitude.

[0127] The third attitude can be used to reflect the true attitude of the target object relative to the control reference of the unmanned forklift.

[0128] As one implementation method, the horizontal projection deviation can be directly superimposed on the horizontal coordinate components of the second attitude to obtain the corrected third attitude.

[0129] As another implementation method, the second attitude can be transformed from the observation coordinate system of the second sensing device to the control reference coordinate system of the unmanned forklift through inverse coordinate transformation, and the influence of horizontal projection deviation can be considered during the transformation process.

[0130] In this embodiment, accurately determining the installation height (i.e., height information) of the second sensing device on the unmanned forklift is crucial for the accuracy of attitude compensation. When the unmanned forklift pitches or tilts, the observation plane of the second sensing device will shift horizontally relative to the control reference plane of the unmanned forklift due to its installation height. To accurately quantify this shift, a first compensation amount in the working direction can be calculated based on the pitch angle change of the unmanned forklift and the height information of the second sensing device. A second compensation amount in the direction perpendicular to the working direction can be calculated based on the roll angle change of the unmanned forklift and the same height information. By combining the compensation amounts in these two directions, the overall horizontal projection deviation from the observation plane of the second sensing device to the control reference plane of the unmanned forklift can be accurately determined. This accurately calculated horizontal projection deviation is then used to correct the second attitude of the target object originally acquired by the second sensing device, thereby obtaining a more accurate third attitude.

[0131] Therefore, the mechanism of fine-grained compensation based on height information and attitude change allows the unmanned forklift to accurately perceive and locate the target object even when its own attitude is not standard.

[0132] Step 208: Based on the third posture, generate a first control command for controlling the unmanned forklift in the working forward direction and a second control command for controlling the unmanned forklift perpendicular to the working forward direction.

[0133] The first control command can be a specific command that converts the compensated target object posture information into the unmanned forklift's movement along its main working path. It can be used to enable the unmanned forklift to accurately approach or move away from the target object in order to achieve the expected working distance.

[0134] As one implementation method, the distance and direction that the unmanned forklift needs to move can be calculated by a motion planning algorithm based on the relative position of the target object in the coordinate system of the unmanned forklift in the third posture along the working direction, combined with the preset working distance or alignment point, and the distance and direction that the unmanned forklift needs to move can be encapsulated as the first control command.

[0135] As another implementation, speed or displacement commands for driving the unmanned forklift to move along the working direction can be generated in real time by comparing the deviation between the position of the target object in the third posture in the working direction and the current position of the unmanned forklift.

[0136] Furthermore, the second control command can be used to control the unmanned forklift in a direction perpendicular to the working direction, and can be used to indicate the lateral alignment or angular deviation between the unmanned forklift and the target object.

[0137] As one implementation method, the offset or angular deviation of the target object relative to the unmanned forklift in the third posture, perpendicular to the working direction, can be analyzed. Combined with the operational requirements, the required lateral translation or rotation angle of the unmanned forklift can be calculated, thereby generating a second control command. Alternatively, the lateral position and attitude information of the target object provided by the third posture can be used to generate a second control command for adjusting the lateral position or yaw angle of the unmanned forklift through visual servo control or path tracking algorithms.

[0138] Step 209: In response to the first control command, adjust the position of the unmanned forklift and perform operations on the target object based on the adjusted position.

[0139] After receiving the first control command, the drive system of the unmanned forklift can drive the forklift to move along the working direction. For example, the wheel drive mechanism of the unmanned forklift drives the wheels through a motor, causing the forklift to move forward or backward until it reaches the position specified in the command or meets the working conditions. After the unmanned forklift reaches the designated position, the actuator (e.g., the fork arm) can perform preliminary work operations on the target object based on this position, such as extending the fork arm to carry the target object.

[0140] Step 210: In response to the second control command, adjust the lateral angle of the unmanned forklift and perform operations on the target object based on the adjusted lateral angle.

[0141] Upon receiving a second control command, the steering system or lateral movement mechanism of the automated forklift adjusts its lateral position or yaw angle. For example, the forklift's steering motor or independent drive motor can enable lateral translation or rotation in place to achieve precise lateral and angular alignment with the target object. After the forklift completes the lateral angle adjustment, its actuators can perform the final operation on the target object based on this precisely aligned lateral angle, such as fully inserting the forks into the pallet or precisely grasping the target.

[0142] In this embodiment, the control of the unmanned forklift is decomposed into two independent control commands: position adjustment in the working direction and lateral angle adjustment perpendicular to the working direction. These commands are executed separately, enabling the unmanned forklift to perform operations on the target object more precisely and accurately. This allows the unmanned forklift to address positional and angular deviations specifically after receiving a third posture with attitude compensation, thereby improving the success rate and efficiency of operations.

[0143] As a specific exemplary embodiment, please refer to Figure 6 An unmanned forklift equipped with two-dimensional laser navigation receives an instruction to remove a pallet of goods from a shelf, and the warehouse floor is slightly uneven in this scenario.

[0144] The unmanned forklift's two-dimensional navigation module plans the optimal path based on the task order, guiding the vehicle to travel at a normal speed to the preset area corresponding to the entry point in front of the target shelf (a circular area with a radius of 0.5m centered on the entry center point). When approaching this area, the unmanned forklift is controlled to decelerate smoothly and come to a complete stop.

[0145] When the unmanned forklift comes to a complete stop, a parking stability assessment can be initiated simultaneously. By determining whether the vehicle speed has dropped below 0.05 m / s, the inertial measurement unit (IMU) (the second sensing device) determines whether the vehicle body is no longer rotating (angular velocity < 0.5° / s) or whether the current acceleration of the unmanned forklift is basically consistent with the gravitational acceleration.

[0146] Once the unmanned forklift meets the parking stability conditions and maintains this condition for a short period, it can be confirmed that the vehicle is in a stable, stationary reference state. At this point, the initial pitch angle θ0 and initial roll angle φ0 of the unmanned forklift are recorded, and this attitude information is set as the attitude reference anchor point and stored in a temporary buffer.

[0147] Once anchoring is complete, a ready signal can be sent to the unmanned forklift, unlocking the fork mechanism and officially initiating the forklift loading process. Simultaneously, the vehicle attitude dynamic compensation function is activated, allowing real-time monitoring of the unmanned forklift via the attitude acquisition module. The IMU begins high-frequency output of the unmanned forklift's current vehicle attitude (current pitch angle θ1, current roll angle φ1), and the attitude compensation module continuously calculates the change in current attitude relative to the attitude reference anchor point. Specifically, the pitch angle change Δθ = θ1 - θ0, and the roll angle change Δφ = φ1 - φ0.

[0148] In one embodiment, a safety boundary can be preset. When the change in pitch angle or roll angle exceeds 5°, the current state of the unmanned forklift is considered abnormal. Once the current state of the unmanned forklift is determined to be abnormal, for example, if the body of the unmanned forklift undergoes a drastic change, the operation can be stopped immediately to prevent accidents caused by collisions or malfunctions.

[0149] Furthermore, after determining the pitch and roll angle changes, if the current vehicle body offset of the unmanned forklift is within the normal range, pose compensation calculation can be performed. Specifically, a physical model can be used for real-time calculation. By using the installation height h of the cargo recognition sensor (first sensing device), projection deviation compensation is performed on the plane where the second pose is located, thereby realizing pose compensation calculation for the second pose. The calculation formula is as follows: Projection deviation = Installation height × Trigonometric function of pose change angle.

[0150] Specifically, the pitch (Δθ) of the vehicle body causes a deviation in the front and rear position of the cargo as seen by the sensor. Therefore, the displacement deviation generated in the forklift direction can be calculated: Δx ≈ h×sin(Δθ);

[0151] The left and right tilt of the vehicle body (Δφ) causes a deviation in the left and right position of the cargo as seen by the sensor. Therefore, the displacement deviation in the direction perpendicular to the fork entry direction can be calculated: Δy≈h×sin(Δφ).

[0152] After determining the displacement deviations in the x and y directions, further projection deviation compensation can be performed. Specifically, the camera / LiDAR (second sensing device) installed on the unmanned forklift identifies the original position (x_s, y_s, α_s) of the pallet in the sensor coordinate system. Here, x_s is the coordinate along the fork entry direction in the sensor coordinate system, y_s is the coordinate perpendicular to the fork entry direction, and α_s is the deflection angle of the goods relative to the sensor coordinate system. Furthermore, the target pose (x_c, y_c, α_c) (third pose) can be calculated by combining preset horizontal offsets Δx0 and Δy0, and the calculated dynamic deviations (Δx, Δy). The specific calculation formula is as follows: (x_c, y_c, α_c) = (x_s - Δx - Δx0, y_s - Δy - Δy0, α_s). Here, this target pose can be used to reflect the true positional relationship of the goods relative to the forklift actuator.

[0153] After determining the third posture (x_c, y_c, α_c) of the target object, the unmanned forklift can be driven to perform a fork-entry operation to work on the target object. In the x-direction, with x_c=0 as the target, the speed of the fork-entry motor is precisely adjusted through PID control to align the center of the forks with the center of the pallet where the target object is located. In the y-direction, the vehicle body is controlled to correct the lateral deviation y_c to within ±2 cm. If the angular deviation α_c is greater than 1°, the vehicle body direction is finely adjusted to ensure that the forks are parallel to the pallet insertion holes. After the forks are smoothly inserted into the pallet to a preset depth (e.g., 20 cm), the goods are lifted to a safe height to complete the retrieval. Subsequently, the unmanned forklift leaves the storage point at a low speed (0.3 m / s).

[0154] In one implementation, once the unmanned forklift has been detected to have steadily moved away, the attitude compensation function can be immediately disabled, and the attitude reference anchor points in the temporary memory can be cleared. The unmanned forklift then seamlessly switches back to the standard two-dimensional navigation mode, relying on LiDAR and odometers for subsequent transportation and positioning, until the next pickup task begins, at which point the entire process restarts.

[0155] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0156] Based on the same inventive concept, this application also provides an attitude positioning device for implementing the attitude positioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more attitude positioning device embodiments provided below can be found in the limitations of the attitude positioning method described above, and will not be repeated here.

[0157] In one exemplary embodiment, such as Figure 7 As shown, an attitude positioning device is provided, including: an acquisition module, a calculation module, a compensation module, and a control module, wherein:

[0158] The acquisition module is used to acquire the first posture of the unmanned forklift through the first sensing device and to acquire the second posture of the target object to be operated by the unmanned forklift through the second sensing device.

[0159] The calculation module is used to calculate the change in attitude between the first attitude and the preset attitude reference anchor point; wherein, the attitude reference anchor point is used to represent the standard attitude of the unmanned forklift.

[0160] The compensation module is used to perform attitude compensation on the second attitude based on the relative position information and attitude change of the second sensing device on the unmanned forklift, so as to determine the third attitude.

[0161] The control module is used to control the actuators of the unmanned forklift to perform operations on the target object based on the third posture.

[0162] In an exemplary embodiment, the attitude positioning device further includes a reference anchor point setting module, which comprises: an information acquisition module, a state determination module, and an anchor point determination module, wherein:

[0163] The information acquisition module is used to collect the linear velocity, angular velocity and acceleration information of the unmanned forklift when it travels to the target position.

[0164] The state determination module is used to determine whether the unmanned forklift has entered the target state when the preset stability conditions are met.

[0165] Anchor point determination module is used to use the current attitude information of the unmanned forklift in the target state at the target position as the attitude reference anchor point; wherein, the preset stability conditions include at least one of the following: linear velocity information is lower than a first threshold, angular velocity information is lower than a second threshold, and acceleration information is within a preset range of gravitational acceleration.

[0166] In an exemplary embodiment, the acquisition module includes: a coordinate calculation unit and a pose transformation unit, wherein:

[0167] The coordinate calculation unit is used to acquire a captured image including the target object through the second sensing device, and to calculate the target coordinate information of the target object in the captured image;

[0168] The pose conversion unit is used to convert the target coordinate information into corresponding two-dimensional pose information based on the device parameters of the second sensing device and the relative positional relationship between the second sensing device and the unmanned forklift, so as to obtain the second pose.

[0169] In one exemplary embodiment, the attitude positioning device further includes an anomaly warning module, which includes an abnormal attitude determination unit and a prompt information output unit, wherein:

[0170] The abnormal attitude determination unit is used to determine that the unmanned forklift is in an abnormal attitude when the pitch angle change is greater than the third threshold or the roll angle change is greater than the fourth threshold.

[0171] The prompt information output unit is used to output prompt information to prompt the handling of abnormal posture when the unmanned forklift is in an abnormal posture.

[0172] In an exemplary embodiment, the compensation module includes: a first compensation amount calculation unit, a second compensation amount calculation unit, a deviation amount calculation unit, and a correction unit, wherein:

[0173] The first compensation calculation unit is used to calculate the first compensation amount to represent the direction of operation based on the pitch angle change and altitude information.

[0174] The second compensation calculation unit is used to calculate a second compensation amount that is perpendicular to the direction of operation, based on the change in side tilt angle and height information.

[0175] The deviation calculation unit is used to determine the horizontal projection deviation from the observation plane where the second sensing device is located to the control reference plane of the unmanned forklift based on the first compensation amount and the second compensation amount.

[0176] The correction unit is used to correct the second attitude based on the horizontal projection deviation in order to determine the third attitude.

[0177] In an exemplary embodiment, the control module includes: a control command generation unit, a first response unit, and a second response unit, wherein:

[0178] The control command generation unit is used to generate, based on the third posture, a first control command for controlling the unmanned forklift in the working forward direction, and a second control command for controlling the unmanned forklift perpendicular to the working forward direction.

[0179] The first response unit is used to respond to the first control command, adjust the position of the unmanned forklift, and perform operations on the target object based on the adjusted position;

[0180] The second response unit is used to respond to the second control command, adjust the lateral angle of the unmanned forklift, and perform operations on the target object based on the adjusted lateral angle.

[0181] Each module in the aforementioned attitude positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the unmanned forklift in hardware form or independent of it, or stored in the memory of the unmanned forklift in software form, so that the processor can call and execute the corresponding operations of each module.

[0182] In one exemplary embodiment, an unmanned forklift is provided. The unmanned forklift can be a terminal, and its internal structure diagram can be as follows: Figure 8As shown, the unmanned forklift includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a posture positioning method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the unmanned forklift can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the shell of the unmanned forklift, or external keyboards, touchpads, or mice, etc.

[0183] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the unmanned forklift to which the present application is applied. A specific unmanned forklift may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0184] In one exemplary embodiment, an unmanned forklift is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described attitude positioning method.

[0185] In one embodiment, a readable storage medium is provided on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described attitude localization method.

[0186] In one embodiment, a program product is provided, including a computer program that, when executed by a processor, implements the steps of the above-described attitude localization method.

[0187] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0188] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0189] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0190] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An attitude positioning method, characterized in that, The method is applied to an unmanned forklift, the unmanned forklift being equipped with a first sensing device and a second sensing device, the method comprising: The first posture of the unmanned forklift is obtained through the first sensing device, and the second posture of the target object to be operated by the unmanned forklift is obtained through the second sensing device. Calculate the attitude change between the first attitude and a preset attitude reference anchor point; wherein the attitude reference anchor point is used to characterize the standard attitude of the unmanned forklift. Based on the relative position information of the second sensing device on the unmanned forklift and the amount of attitude change, attitude compensation is performed on the second attitude to determine the third attitude; Based on the third posture, the actuator of the unmanned forklift is controlled to perform operations on the target object.

2. The method according to claim 1, characterized in that, Before the step of acquiring the first attitude of the unmanned forklift through the first sensing device, the method further includes: When the unmanned forklift reaches the target position, its linear velocity, angular velocity, and acceleration information are collected. When the unmanned forklift meets the preset stability conditions, it is determined that the unmanned forklift has entered the target state; The current attitude information of the unmanned forklift in the target state at the target location is used as the attitude reference anchor point; wherein, the preset stability conditions include at least one of the following: the linear velocity information is lower than a first threshold, the angular velocity information is lower than a second threshold, and the acceleration information is within a preset range of gravitational acceleration.

3. The method according to claim 1, characterized in that, The step of obtaining the second posture of the target object to be operated by the unmanned forklift through the second sensing device includes: The second sensing device acquires a captured image including the target object, and calculates the target coordinate information of the target object in the captured image; Based on the device parameters of the second sensing device and the relative positional relationship between the second sensing device and the unmanned forklift, the target coordinate information is converted into corresponding two-dimensional pose information to obtain the second pose.

4. The method according to claim 1, characterized in that, The attitude change includes pitch angle change and roll angle change. After the step of calculating the attitude change between the first attitude and a preset attitude reference anchor point, the method further includes: When the pitch angle change is greater than the third threshold or the roll angle change is greater than the fourth threshold, the unmanned forklift is determined to be in an abnormal posture. When the unmanned forklift is in the abnormal posture, a prompt message is output to indicate that the abnormal posture should be handled.

5. The method according to claim 1, characterized in that, The relative position information of the second sensing device on the unmanned forklift includes height information; The step of performing attitude compensation on the second attitude based on the relative position information of the second sensing device on the unmanned forklift and the attitude change amount to determine the third attitude includes: Based on the pitch angle change and the altitude information, a first compensation amount is calculated to represent the direction of operation. Based on the change in side tilt angle and the height information, a second compensation amount is calculated to represent the direction perpendicular to the working direction. Based on the first compensation amount and the second compensation amount, determine the horizontal projection deviation from the observation plane where the second sensing device is located to the control reference plane of the unmanned forklift; Based on the horizontal projection deviation, the second attitude is corrected to determine the third attitude.

6. The method according to any one of claims 1 to 5, characterized in that, The step of controlling the actuator of the unmanned forklift to perform operations on the target object according to the third posture includes: Based on the third posture, a first control command is generated to control the unmanned forklift in the working direction, and a second control command is generated to control the unmanned forklift in a direction perpendicular to the working direction. In response to the first control command, the position of the unmanned forklift is adjusted, and the operation is performed on the target object based on the adjusted position; In response to the second control command, the lateral angle of the unmanned forklift is adjusted, and the operation is performed on the target object based on the adjusted lateral angle.

7. An attitude positioning device, characterized in that, The device is applied to an unmanned forklift, the unmanned forklift being equipped with a first sensing device and a second sensing device, and the device includes: The acquisition module is used to acquire the first posture of the unmanned forklift through the first sensing device, and to acquire the second posture of the target object to be operated by the unmanned forklift through the second sensing device; The calculation module is used to calculate the attitude change between the first attitude and a preset attitude reference anchor point; wherein the attitude reference anchor point is used to characterize the standard attitude of the unmanned forklift. The compensation module is used to perform attitude compensation on the second attitude based on the relative position information of the second sensing device on the unmanned forklift and the attitude change amount, so as to determine the third attitude; The control module is used to control the actuator of the unmanned forklift to perform operations on the target object according to the third posture.

8. An unmanned forklift, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images