Intelligent logistics carrying method and intelligent logistics robot

Abstract

This invention provides an intelligent logistics handling method and an intelligent logistics robot, comprising: acquiring handling instructions sent by an operator through a communication unit; parsing the handling instructions to obtain handling task parameters; obtaining tracking control instructions based on the handling task parameters; controlling the chassis to track and move to the target material position according to the tracking control instructions; acquiring image data of the target material and performing recognition processing on the image data to obtain material type, spatial position, and grasping posture information; generating motion trajectory parameters of the robotic arm based on the spatial position and grasping posture information; acquiring the target material; if multiple materials need to be loaded, temporarily storing the grasped materials in a loading device and repeating material recognition and grasping until all materials are loaded; releasing the target material in a designated area; controlling the chassis to track and return to the starting point, and providing real-time feedback on the execution status information. This method achieves autonomous recognition, precise grasping, and efficient handling.

Description

Technical Field

[0001] This invention relates to the field of logistics handling technology, and in particular to an intelligent logistics handling method and an intelligent logistics robot. Background Technology

[0002] With the booming development of e-commerce and the rapid growth of the logistics industry, the demand for efficient and intelligent material handling equipment is becoming increasingly urgent. Traditional material handling mainly relies on manual labor, but rising labor costs and limited human resources make manual handling difficult to meet the needs of modern logistics. Some automated material handling equipment uses fixed tracks or simple robotic arms, which suffer from poor adaptability, low recognition accuracy, and low handling efficiency. Especially in complex environments such as vehicle manufacturing plants, where there are many types of materials and varied handling paths, traditional equipment struggles to achieve flexible and precise autonomous handling, resulting in slow material feeding speeds and high reliance on manual labor. Therefore, an intelligent and efficient logistics handling solution is urgently needed. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide an intelligent logistics handling method and an intelligent logistics robot, which improves the success rate of grasping, saves process time, and realizes autonomous identification, accurate grasping and efficient handling.

[0004] In a first aspect, embodiments of the present invention provide an intelligent logistics handling system applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit; the robotic arm includes a robotic gripper; the method includes: acquiring a handling instruction sent by an operator through the communication unit, the handling instruction including target material information, target material location, and placement position; parsing the handling instruction to obtain handling task parameters; collecting path signals through the path perception unit according to the handling task parameters, and processing the path signals to obtain a tracking control instruction; controlling the chassis to track and move to the target material location according to the tracking control instruction; and through... The visual recognition unit acquires image data of the target material and processes the image data to obtain information on the material type, spatial location, and grasping posture. Based on the spatial location and grasping posture information, the CID algorithm generates motion trajectory parameters for the robotic arm. The robotic arm is controlled to perform grasping actions according to the motion trajectory parameters to acquire the target material. It is determined whether multiple materials need to be loaded. If so, the grasped materials are temporarily stored in the loader, and the material recognition and grasping are repeated until all materials are loaded. The chassis is controlled to move along the track to the placement position, and the robotic arm is controlled to perform the placement action to release the target material in the designated area. The chassis is controlled to return to the starting point, and the execution status information obtained from the main control unit is fed back in real time through the display unit.

[0005] In a preferred embodiment of the present invention, the above-mentioned parsing of the handling instructions to obtain handling task parameters includes: parsing the handling instructions according to the protocol and extracting the instruction type field; determining whether the handling task is single material handling or multi-material handling based on the instruction type field; if it is multi-material handling, then parsing to obtain the quantity of materials, the grabbing order of each material and the corresponding target material location.

[0006] In a preferred embodiment of the present invention, the above-mentioned acquisition of path signals by the path sensing unit and processing of the path signals to obtain tracking control commands includes: acquiring grayscale signals of the ground path in real time by the path sensing unit; comparing the grayscale signals with a preset path threshold to obtain a path deviation value; calculating the steering correction amount of the chassis based on the path deviation value, and generating tracking control commands.

[0007] In a preferred embodiment of the present invention, the above-mentioned acquisition of image data of target material by visual recognition unit and recognition processing of image data to obtain material type, spatial location and grasping posture information includes: acquiring image data of target material by visual recognition unit; The image data is preprocessed to obtain an enhanced image; features are extracted from the enhanced image to obtain a material feature vector; the material feature vector is matched with a preset material feature library to identify the material type; depth information is extracted from the enhanced image to calculate the spatial position and grasping posture information of the material.

[0008] In a preferred embodiment of the present invention, the above-mentioned extraction of depth information from the enhanced image and calculation of the spatial position and gripping posture information of the material includes: performing parallax calculation on the multi-view image using a binocular vision algorithm to obtain a depth map; determining the center point coordinates and edge contour of the material based on the depth map; and calculating the gripping point coordinates and the closing angle of the mechanical claw based on the center point coordinates and edge contour.

[0009] In a preferred embodiment of the present invention, the above-mentioned generation of motion trajectory parameters of the robotic arm based on spatial position and grasping posture information and using the CID algorithm includes: obtaining the current position parameters and target position parameters of the robotic arm, and calculating the position deviation value; inputting the position deviation value into the CID controller; the CID controller calculating the control output value according to the combined operation rules of time control, integral control and derivative control; generating motion trajectory parameters of each joint of the robotic arm according to the control output value; the motion trajectory parameters include motion speed, acceleration and target angle.

[0010] In a preferred embodiment of the present invention, controlling the robotic arm to perform a grasping action to acquire the target material according to motion trajectory parameters includes: controlling the movement of the linkage structure of the robotic arm according to the motion trajectory parameters, so that the robotic claw moves to the grasping position of the target material; controlling the robotic claw to perform a closing action to acquire the target material; after the grasping is completed, detecting the grasping force by a force sensor set on the inner side of the robotic claw, and stopping the closing when the grasping force reaches a preset threshold.

[0011] In a preferred embodiment of the present invention, it is determined whether multiple materials need to be loaded. If so, the grabbed materials are temporarily stored in the loading device, and the material identification and grabbing steps are repeated until all materials are loaded. This includes: obtaining the material quantity information in the handling instruction and comparing it with the quantity of materials already grabbed; if the quantity of materials already grabbed is less than the material quantity information, it is determined that loading needs to continue; controlling the robotic arm to place the currently grabbed material into the receiving cavity of the loading device; detecting the loading status through the material detection sensor set in the loading device and updating the quantity of materials already grabbed; repeating the material identification and grabbing steps until the quantity of materials already grabbed is equal to the material quantity information.

[0012] In a preferred embodiment of the present invention, the execution status information obtained from the main control unit is fed back in real time through the display unit, including: obtaining the execution status information through the main control unit; the execution status information includes the content of the currently executed instruction, material grabbing information and chassis position information; converting the execution status information into display data and displaying it in real time through the display unit; and simultaneously transmitting the execution status information back to the operator terminal through the communication unit.

[0013] Secondly, embodiments of the present invention also provide an intelligent logistics robot, comprising: a chassis for supporting various functional units and enabling mobility; an execution unit disposed on the chassis for performing material grasping, loading, and placement operations; a sensing unit disposed on the chassis and the execution unit for collecting environmental and material information; a main control unit electrically connected to the chassis, the execution unit, and the sensing unit respectively, for receiving and processing various signals and generating control commands; a communication unit electrically connected to the main control unit for data interaction with external devices; and a display unit electrically connected to the main control unit for real-time feedback of the robot's operating status information.

[0014] The embodiments of the present invention bring the following beneficial effects: This invention provides an intelligent logistics handling method and an intelligent logistics robot, applicable to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit. The method acquires handling instructions sent by the operator through the communication unit. These instructions include target material information, target material location, and placement position. The handling instructions are parsed to obtain handling task parameters. Based on these parameters, path signals are collected by the path perception unit and processed to obtain tracking control instructions. The chassis is then controlled to follow the path and move to the target material location. Visual recognition is then used to further enhance the handling process. The unit acquires image data of the target material and processes it to obtain information on the material type, spatial location, and grasping posture. Based on this information, a CID algorithm is used to generate motion trajectory parameters for the robotic arm. The robotic arm is then controlled to perform a grasping action to acquire the target material. If multiple materials need to be loaded, the unit determines whether they are needed. If so, the grasped materials are temporarily stored in a loading device, and the process of material identification and grasping is repeated until all materials are loaded. The unit then controls the chassis to move to the placement position and controls the robotic arm to perform the placement action, releasing the target material into the designated area. The chassis then returns to the starting point, and the execution status information obtained from the main control unit is displayed in real time via a display unit. This method improves the grasping success rate, saves process time, and achieves autonomous identification, precise grasping, and efficient handling.

[0015] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0016] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 A flowchart of an intelligent logistics handling method provided in an embodiment of the present invention; Figure 2 A flowchart of another intelligent logistics handling method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an intelligent logistics handling device provided in an embodiment of the present invention; Figure 4 A structural diagram of an intelligent logistics robot provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] With the booming development of e-commerce and the rapid growth of the logistics industry, the demand for efficient and intelligent material handling equipment is becoming increasingly urgent. Traditional material handling mainly relies on manual labor, but rising labor costs and limited human resources make manual handling difficult to meet the needs of modern logistics. Some automated material handling equipment uses fixed tracks or simple robotic arms, which suffer from poor adaptability, low recognition accuracy, and low handling efficiency. Especially in complex environments such as vehicle manufacturing plants, where there are many types of materials and varied handling paths, traditional equipment struggles to achieve flexible and precise autonomous handling, resulting in slow material feeding speeds and high reliance on manual labor. Therefore, an intelligent and efficient logistics handling solution is urgently needed.

[0021] Based on this, the present invention provides an intelligent logistics handling method and an intelligent logistics robot, which are applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit. The method acquires handling instructions sent by the operator through the communication unit. These instructions include target material information, target material location, and placement location. The handling instructions are parsed to obtain handling task parameters. Based on these parameters, path signals are collected through the path perception unit and processed to obtain tracking control instructions. The chassis is then controlled to follow the path and move to the target material location. The method utilizes vision recognition to achieve the desired result. The identification unit collects image data of the target material and processes it to obtain information on the material type, spatial location, and grasping posture. Based on the spatial location and grasping posture information, a CID algorithm is used to generate motion trajectory parameters for the robotic arm. The robotic arm is then controlled to perform a grasping action to acquire the target material. It is determined whether multiple materials need to be loaded. If so, the grasped materials are temporarily stored in the loading container, and the process of material identification and grasping is repeated until all materials are loaded. The chassis then moves to the placement position, and the robotic arm performs the placement action, releasing the target material into the designated area. The chassis then returns to the starting point, and the execution status information obtained from the main control unit is displayed in real time via the display unit. This method improves the grasping success rate, saves process time, and achieves autonomous identification, accurate grasping, and efficient handling.

[0022] To facilitate understanding of this embodiment, a detailed description of an intelligent logistics handling method disclosed in this embodiment of the invention will be provided first.

[0023] Example 1 This invention provides an intelligent logistics handling method applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit; the robotic arm includes a robotic gripper.

[0024] Figure 1 A flowchart illustrating an intelligent logistics handling method provided in an embodiment of the present invention. Figure 1 As shown, the intelligent logistics handling method may include the following steps: Step S101: Obtain the handling instruction sent by the operator through the communication unit. The handling instruction includes target material information, target material location, and placement location.

[0025] The communication unit is a hardware module responsible for receiving wireless signals. It is used for wireless communication with external devices (such as operator terminals and servers). The communication unit can be a WiFi module, Bluetooth module, or 4G / 5G module, supporting remote command reception and status feedback.

[0026] Among them, the handling instruction is the control command sent by the operator through a mobile APP, tablet or remote console, which includes target material information (such as material name and model), target material location (such as shelf number and coordinates) and placement location (such as production line station or temporary storage area).

[0027] The operator can select the materials to be moved and the destination on the control terminal and click the send button. The control terminal encapsulates the instructions into data packets and transmits them wirelessly via WiFi or Bluetooth. The robot's communication unit listens for the wireless signal in real time, verifies the received data packets, and then transmits them to the main control unit after confirmation. This enables remote command of the robot's operations, allowing the operator to issue tasks without being physically present on-site, thus improving operational flexibility and response speed.

[0028] Step S102: Parse the transport instructions to obtain the transport task parameters.

[0029] In this process, by parsing the transport instructions, the raw instruction data can be converted into task parameters that the machine can understand.

[0030] The task parameters may include structured information such as target material type, grab location coordinates, placement location coordinates, quantity to be handled, and grab sequence.

[0031] Specifically, parsing the handling instructions to obtain handling task parameters may include: parsing the handling instructions according to the protocol and extracting the instruction type field; determining whether the handling task is single-material handling or multi-material handling based on the instruction type field; if it is multi-material handling, parsing to obtain the quantity of materials, the grabbing order of each material, and the corresponding target material location.

[0032] Upon receiving the original instruction, the main control unit first performs protocol parsing to identify the instruction type. The instruction type field is typically located in the packet header; for example, 0x01 indicates single-material handling, and 0x02 indicates multi-material handling. If it's a single-material instruction, the material information and location are directly extracted; if it's a multi-material instruction, the material list, the handling order, and the corresponding locations are further parsed. This allows for accurate parsing of complex multi-material instructions, providing a basis for subsequent multiple handling operations and avoiding handling confusion or omissions.

[0033] Step S103: Based on the handling task parameters, the path sensing unit collects the path signal and processes the path signal to obtain the tracking control command.

[0034] The path sensing unit typically consists of multiple grayscale sensors, installed at the bottom of the chassis, to detect ground path markings (such as black lines and colored stripes).

[0035] Among them, the tracking control command is the drive command that controls the chassis to move along a preset path, including forward, backward, left turn, right turn and other actions.

[0036] The main control unit can plan a path from the starting point to the target point based on the target location in the task parameters. The path perception unit collects ground grayscale signals in real time, compares them with preset path thresholds, and determines whether the current path has been deviated from. Based on the deviation value, the steering correction amount is calculated, and control commands are generated and sent to the chassis drive motor.

[0037] Specifically, the path sensing unit collects path signals and processes them to obtain tracking control commands. This process may include: collecting grayscale signals of the ground path in real time through the path sensing unit; comparing the grayscale signals with a preset path threshold to obtain a path deviation value; calculating the chassis steering correction amount based on the path deviation value and generating tracking control commands.

[0038] The path perception unit consists of 3-5 grayscale sensors arranged in a straight line or V-shape. The sensors collect the intensity of reflected light from the ground in real time, converting it into grayscale values ​​from 0-255. The main control unit compares the grayscale value of each sensor with a preset threshold (e.g., a black line threshold of 50), calculating the deviation between the current sensor array and the path centerline. A larger deviation indicates a more severe deviation. Based on the deviation value, a PID control input is calculated to generate steering correction commands. This achieves precise path following, ensuring stable tracking even when turning or on unclear paths, guaranteeing the robot does not deviate from the route.

[0039] Step S104: Control the chassis to move to the target material position according to the tracking control command.

[0040] The chassis may include a drive motor, wheels, and a transmission mechanism, which are responsible for executing movement commands.

[0041] Among them, line-following movement is the process by which a robot autonomously navigates according to ground path markings.

[0042] The main control unit converts tracking control commands into PWM signals and sends them to the chassis drive motor. The drive motor adjusts its speed and direction according to the PWM duty cycle, driving the wheels to rotate and achieve forward, backward, or turning movements. Simultaneously, the path perception unit continuously feeds back position information, forming a closed-loop control system to ensure the robot stably follows the path. The robot can autonomously and smoothly move to the target material location without human intervention, improving the automation level of material handling.

[0043] Step S105: Collect image data of the target material through the visual recognition unit, and perform recognition processing on the image data to obtain information on material type, spatial location and grasping posture.

[0044] The visual recognition unit may include a camera and an image processing chip for acquiring and processing images.

[0045] Among them, image data are raw digital images captured by the camera, containing information such as the color, shape, and texture of the material.

[0046] Among them, the material type is the identified material name or number.

[0047] The spatial location refers to the coordinates (x, y, z) of the material in three-dimensional space.

[0048] Among them, the gripping posture refers to the direction and tilt angle of the material, which is used to determine the optimal gripping method of the mechanical gripper.

[0049] Once the robot reaches the target location, the vision recognition unit activates the camera to capture an image of the material. The image processing chip preprocesses the image (e.g., denoising and enhancement), extracts features, and matches them against a pre-set material feature library to identify the material type. Simultaneously, depth information is calculated using binocular vision or structured light technology to determine the material's spatial position and orientation. This achieves accurate material recognition and positioning, providing the necessary data support for the robotic arm's precise grasping and preventing incorrect or missed grasps.

[0050] Step S106: Based on the spatial position and grasping posture information, the motion trajectory parameters of the robotic arm are generated using the CID algorithm.

[0051] Among them, the CID algorithm is a motion control algorithm that combines time control (C), integral control (I) and derivative control (D) to optimize the motion trajectory of the robotic arm and achieve smooth and fast positioning.

[0052] The motion trajectory parameters can include the angles, angular velocities, and angular accelerations of each joint of the robotic arm, which are used to control the motion path of the robotic arm.

[0053] Specifically, based on spatial position and grasping posture information, the motion trajectory parameters of the robotic arm are generated through the CID algorithm. This may include: obtaining the current position parameters and target position parameters of the robotic arm, and calculating the position deviation value; inputting the position deviation value into the CID controller; the CID controller calculating the control output value according to the combined operation rules of time control, integral control and derivative control; and generating the motion trajectory parameters of each joint of the robotic arm based on the control output value. The motion trajectory parameters include motion speed, acceleration and target angle.

[0054] The CID controller combines time control (C), integral control (I), and derivative control (D). Time control adjusts the output based on the deviation between the actual running time and the set time to ensure the movement is completed within the specified time; integral control accumulates and compensates for persistent deviations, eliminating static errors; and derivative control adjusts in advance based on the rate of change of the deviation, suppressing oscillations. The weighted sum of the outputs of the three components yields the control quantity, which is then transformed kinematically to generate the motion parameters of each joint. The robotic arm moves smoothly without impact, has high positioning accuracy, fast dynamic response, and adapts to different load and speed requirements.

[0055] For example, the robotic arm moves from its current joint angle (30°, 45°, 60°) to a target (45°, 60°, 30°), with a deviation of (15°, 15°, -30°). The CID controller calculates: C control output = Kp × deviation = 0.5 × (15, 15, -30) = (7.5, 7.5, -15).

[0056] I control output = Ki × integral deviation = 0.1 × (10, 10, -20) = (1, 1, -2).

[0057] D control output = Kd × deviation change rate = 0.2 × (5, 5, -10) = (1, 1, -2).

[0058] Total output = (9.5, 9.5, -19), which is converted into the velocity and acceleration of each joint.

[0059] Step S107: Control the robotic arm to perform a grasping action according to the motion trajectory parameters to obtain the target material.

[0060] Among them, the robotic arm is a multi-joint actuator, which is usually driven by a servo motor.

[0061] Among them, the robotic gripper is the grasping tool at the end of the robotic arm, used to directly contact and grasp materials.

[0062] The gripping action is the process by which the robotic arm moves from its current position to the gripping point and closes its gripper to hold the material.

[0063] The main control unit sends motion trajectory parameters to the servo drives of each joint of the robotic arm, driving the motors to move along the planned trajectory, enabling the robotic gripper to precisely move to the gripping point. Upon arrival, the gripper closes to hold the material. A rubber anti-slip layer is provided on the inner side of the gripper to increase friction and prevent material slippage. Simultaneously, a force sensor monitors the gripping force in real time, stopping the closure when a preset threshold is reached to avoid damaging the material.

[0064] For example, the robotic arm moves along a planned trajectory. The robotic gripper reaches above part A, moves downwards to the gripping position, and then closes. A force sensor detects a gripping force of 5N, determines that the grip is secure, and stops closing. The robotic arm then lifts upwards, completing the gripping process.

[0065] Specifically, controlling the robotic arm to perform a grasping action to acquire the target material based on motion trajectory parameters may include: controlling the movement of the robotic arm's linkage structure based on motion trajectory parameters to move the robotic claw to the grasping position of the target material; controlling the robotic claw to perform a closing action to acquire the target material; and after grasping, detecting the grasping force through a force sensor located on the inside of the robotic claw, and stopping the closing when the grasping force reaches a preset threshold.

[0066] The robotic arm's joint servo drives receive trajectory parameters and execute closed-loop position control. The closing of the robotic gripper is driven by a solenoid valve or a micro motor, and the force sensor uses a strain gauge to detect the pressure between the gripper and the material. When the pressure reaches a preset threshold, the controller immediately cuts off the drive signal and stops the closing. After gripping, a pressure holding function can maintain the gripping force to prevent slippage during handling.

[0067] For example, when the robotic arm moves to the gripping point, the gripper closes, and a force sensor monitors the pressure value in real time. When the pressure reaches 5N, it is determined that a firm grip has been achieved, and the closing process immediately stops. If a drop in pressure is detected (such as due to vibration causing loosening), the controller automatically increases the closing force to maintain a constant pressure. Precise control of the gripping force ensures a firm grip while preventing damage to the material, adapting to materials of different materials and hardness.

[0068] Step S108: Determine whether multiple materials need to be loaded. If so, temporarily store the grabbed materials in the filler and repeat the material identification and grabbing process until all materials are loaded.

[0069] The filling device is a material storage device that can hold multiple materials.

[0070] Specifically, the process involves determining whether multiple materials need to be loaded. If so, the grabbed materials are temporarily stored in the loading unit, and the material identification and grabbing steps are repeated until all materials are loaded. This may include: obtaining the material quantity information from the handling instruction and comparing it with the quantity of materials already grabbed; if the quantity of materials already grabbed is less than the material quantity information, it is determined that loading needs to continue; controlling the robotic arm to place the currently grabbed material into the receiving cavity of the loading unit; detecting the loading status through the material detection sensor set in the loading unit and updating the quantity of materials already grabbed; and repeating the material identification and grabbing process until the quantity of materials already grabbed equals the material quantity information.

[0071] The filling device is equipped with a photoelectric switch or ultrasonic sensor to detect whether material is being added. Each time material is added, the sensor triggers a signal, and the main control unit updates the count of material already grasped. The bottom of the filling device can be designed as a liftable platform that automatically lowers as material is added, maintaining a consistent filling height each time.

[0072] For example, a task might require moving five parts. After the first part is placed in the loading device, a photoelectric switch is triggered, and the counter updates to 1. The robotic arm returns to grab the second part, and after it's placed in, the counter updates to 2, and so on, until it reaches 5. The lifting platform inside the loading device gradually lowers as more material is added, ensuring each part can be smoothly placed. This achieves orderly temporary storage of multiple materials, accurate counting, and supports subsequent batch placement, improving handling efficiency.

[0073] Step S109: Control the chassis to move along the track to the placement position, and control the robotic arm to perform the placement action to release the target material into the designated area.

[0074] The placement action is the process by which the robotic arm moves the material from the gripping position to the placement point and then releases it.

[0075] The main control unit controls the chassis to move along a tracking path to the placement position. Upon arrival, the vision recognition unit assists in locating the placement point. The robotic arm moves along the planned trajectory above the placement point, descends to a suitable height, and the robotic gripper opens to release the material. If there are multiple materials in the filling container, they are either removed sequentially and placed in designated locations, or all of them are emptied at once.

[0076] Step S110: Control the chassis to return to the starting point by tracking, and provide real-time feedback of the execution status information obtained from the main control unit through the display unit.

[0077] The execution status information may include the content of the currently executed instruction, the quantity of materials grabbed, the completed tasks, the current position of the chassis, and the remaining battery power.

[0078] The display unit is an HMI serial port screen, used to intuitively display status information.

[0079] Specifically, the real-time feedback of execution status information obtained from the main control unit through the display unit may include: obtaining execution status information through the main control unit; the execution status information includes the content of the currently executed instruction, material grabbing information, and chassis position information; converting the execution status information into display data and displaying it in real time through the display unit; and simultaneously transmitting the execution status information back to the operator terminal through the communication unit.

[0080] The main control unit updates status information at each key node of task execution, including instruction content (the task being executed), material grabbing information (quantity grabbed, current material type), chassis location information (current coordinates, target coordinates), and equipment status (battery level, temperature, fault codes). The display unit presents this information in real time using a graphical interface (such as progress bars, icons, and text). Simultaneously, the communication unit pushes status information to the operator terminal via MQTT or HTTP protocols.

[0081] For example, during task execution, the HMI serial port screen displays: "Moving part A, 3rd of 5, current location: shelf 2, remaining battery 72%." The operator's mobile app simultaneously displays the same information and marks the robot's location on the map in real time. This enables remote monitoring and real-time status awareness, allowing operators to understand task progress and robot status at any time, facilitating scheduling and maintenance.

[0082] The intelligent logistics handling method provided in this invention is applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit. The method acquires handling instructions sent by the operator through the communication unit. These instructions include target material information, the target material's location, and its placement position. The handling instructions are parsed to obtain handling task parameters. Based on these parameters, path signals are collected by the path perception unit and processed to obtain tracking control instructions. The chassis is then controlled to follow the path to the target material's location. The vision recognition unit collects the target material's location information. The system collects image data of the target material, processes it for identification, and obtains information on the material type, spatial location, and grasping posture. Based on this information, a CID algorithm is used to generate motion trajectory parameters for the robotic arm. The robotic arm is then controlled to perform a grasping action to acquire the target material. If multiple materials need to be loaded, the system determines whether they are needed. If so, the grasped materials are temporarily stored in a loading device, and the process of material identification and grasping is repeated until all materials are loaded. The chassis then moves to the placement position, and the robotic arm performs the placement action, releasing the target material into the designated area. The chassis then returns to the starting point, and the execution status information obtained from the main control unit is displayed in real time. This method improves the grasping success rate, saves process time, and achieves autonomous identification, accurate grasping, and efficient handling.

[0083] Example 2 This invention also provides another intelligent logistics handling method; this method is implemented based on the method in the above embodiments; this method focuses on describing the specific implementation of collecting image data of target materials through a visual recognition unit, and performing recognition processing on the image data to obtain material type, spatial location and grasping posture information.

[0084] Figure 2 A flowchart of another intelligent logistics handling method provided in an embodiment of the present invention is shown below. Figure 2 As shown, the method of acquiring image data of the target material through a visual recognition unit and performing recognition processing on the image data to obtain information on the material type, spatial location, and grasping posture may include the following steps: Step S201: Image data of the target material is acquired through the visual recognition unit.

[0085] The visual recognition unit first acquires high-resolution images.

[0086] Step S202: Preprocess the image data to obtain an enhanced image.

[0087] Preprocessing may include grayscale conversion, Gaussian filtering for noise reduction, and histogram equalization to enhance contrast.

[0088] Step S203: Extract features from the enhanced image to obtain the material feature vector.

[0089] Feature extraction can employ SIFT, SURF, or deep learning algorithms to extract feature vectors such as the shape, texture, and color of the material.

[0090] Step S204: Match the material feature vector with the preset material feature library to identify the material type.

[0091] In this process, the feature vector can be compared with a preset material feature library, and the matching degree can be calculated using Euclidean distance or cosine similarity. The one with the highest matching degree is selected as the recognition result.

[0092] Step S205: Extract depth information from the enhanced image and calculate the spatial position and grasping posture information of the material.

[0093] Depth information extraction can be achieved by calculating the parallax between the left and right images using the principle of binocular vision, obtaining a depth map, and then calculating the 3D coordinates and attitude angle of the material.

[0094] Specifically, extracting depth information from the enhanced image and calculating the spatial position and gripping posture information of the material can include: calculating the disparity of the multi-view image using a binocular vision algorithm to obtain a depth map; determining the center point coordinates and edge contour of the material based on the depth map; and calculating the gripping point coordinates and the closing angle of the mechanical gripper based on the center point coordinates and edge contour.

[0095] This process employs binocular stereo vision technology, where two cameras simultaneously capture images of the target material, obtaining two images, one on the left and one on the right. A disparity map is calculated using block matching or semi-global matching algorithms, where the value of each pixel represents its horizontal offset within the left and right images. Based on the inverse relationship between disparity and distance, the depth value of each pixel is calculated, generating a depth map. The depth map is then segmented to extract the point cloud data of the material. The coordinates of its center point, minimum bounding rectangle, and principal direction angle are calculated to obtain the coordinates of the gripping point and the closing angle of the robotic gripper.

[0096] For example, the parallax calculation of the left and right images yields the depth map of part A, with center point coordinates of (x=125cm, y=88cm, z=51cm). The edge contour is elliptical, and the major axis angle is 30°. Therefore, the gripping point is the center point, and the closing angle of the robotic gripper should be perpendicular to the major axis direction, i.e., -60°. This achieves precise three-dimensional positioning, and even if the material is tilted or stacked, the optimal gripping posture can be calculated, improving gripping adaptability.

[0097] Example 3 Corresponding to the above method embodiments, this invention provides an intelligent logistics handling device applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit. The robotic arm includes a robotic gripper. Figure 3 This is a schematic diagram of the structure of an intelligent logistics handling device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the intelligent logistics handling device may include: The handling instruction acquisition module 301 is used to acquire handling instructions sent by the operator through the communication unit. The handling instructions include target material information, target material location, and placement location.

[0098] The transport instruction parsing module 302 is used to parse the transport instructions to obtain transport task parameters.

[0099] The path signal processing module 303 is used to collect path signals through the path sensing unit according to the transport task parameters, and process the path signals to obtain tracking control commands.

[0100] The chassis tracking movement module 304 is used to control the chassis to track and move to the target material position according to the tracking control command.

[0101] The recognition and processing module 305 is used to collect image data of the target material through the vision recognition unit, and to perform recognition processing on the image data to obtain information on the material type, spatial location and grasping posture.

[0102] The motion trajectory parameter generation module 306 is used to generate motion trajectory parameters of the robotic arm based on spatial position and grasping posture information using the CID algorithm.

[0103] The target material acquisition module 307 is used to control the robotic arm to perform grasping actions and acquire the target material based on the motion trajectory parameters.

[0104] The loading judgment module 308 is used to determine whether multiple materials need to be loaded. If so, the grabbed materials are temporarily stored in the filler, and the material recognition and grabbing are repeated until all materials are loaded.

[0105] The placement action control module 309 is used to control the chassis to follow the track and move to the placement position, and to control the robotic arm to perform the placement action to release the target material into the designated area.

[0106] The execution status information acquisition module 310 is used to control the chassis to return to the starting point by tracking, and to provide real-time feedback of the execution status information obtained from the main control unit through the display unit.

[0107] The intelligent logistics handling device provided in this embodiment of the invention is applied to an intelligent logistics robot. The intelligent logistics robot includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit. The device acquires handling instructions sent by the operator through the communication unit. These instructions include target material information, the target material's location, and its placement position. The handling instructions are parsed to obtain handling task parameters. Based on these parameters, the path perception unit collects path signals and processes them to obtain tracking control instructions. The chassis is then controlled to move along a path to the target material's location according to these instructions. The vision recognition unit collects the target material's location information. The system collects image data of the target material, processes it for identification, and obtains information on the material type, spatial location, and grasping posture. Based on this information, a CID algorithm is used to generate motion trajectory parameters for the robotic arm. The robotic arm is then controlled to perform a grasping action to acquire the target material. If multiple materials need to be loaded, the system determines whether they are needed. If so, the grasped materials are temporarily stored in a loading device, and the process of material identification and grasping is repeated until all materials are loaded. The chassis then moves to the placement position, and the robotic arm performs the placement action, releasing the target material into the designated area. The chassis then returns to the starting point, and the execution status information obtained from the main control unit is displayed in real time. This method improves the grasping success rate, saves process time, and achieves autonomous identification, accurate grasping, and efficient handling.

[0108] In some embodiments, the handling instruction parsing module is further configured to perform protocol parsing on the handling instructions and extract the instruction type field; determine whether the handling task is single-material handling or multi-material handling based on the instruction type field; if it is multi-material handling, then parse out the quantity of materials, the grabbing order of each material, and the corresponding target material location.

[0109] In some embodiments, the path signal processing module is further configured to acquire grayscale signals of the ground path in real time through the path sensing unit; compare the grayscale signals with a preset path threshold to obtain a path deviation value; calculate the steering correction amount of the chassis based on the path deviation value, and generate a tracking control command.

[0110] In some embodiments, the recognition processing module is further configured to acquire image data of the target material through the visual recognition unit; preprocess the image data to obtain an enhanced image; extract features from the enhanced image to obtain a material feature vector; match the material feature vector with a preset material feature library to identify the material type; and extract depth information from the enhanced image to calculate the spatial position and grasping posture information of the material.

[0111] In some embodiments, the recognition processing module is further configured to perform parallax calculation on multi-view images using a binocular vision algorithm to obtain a depth map; determine the center point coordinates and edge contours of the material based on the depth map; and calculate the gripping point coordinates and the closing angle of the mechanical claw based on the center point coordinates and edge contours.

[0112] In some embodiments, the motion trajectory parameter generation module is further configured to acquire the current position parameters and target position parameters of the robotic arm, calculate the position deviation value, input the position deviation value into the CID controller, calculate the control output value according to the combined operation rules of time control, integral control and derivative control, and generate motion trajectory parameters of each joint of the robotic arm based on the control output value; the motion trajectory parameters include motion speed, acceleration and target angle.

[0113] In some embodiments, the target material acquisition module is further configured to control the movement of the linkage structure of the robotic arm according to the motion trajectory parameters, so that the robotic claw moves to the grasping position of the target material; control the robotic claw to perform a closing action to acquire the target material; after the grasping is completed, the grasping force is detected by a force sensor set on the inner side of the robotic claw, and the closing stops when the grasping force reaches a preset threshold.

[0114] In some embodiments, the loading judgment module is further configured to obtain material quantity information in the handling instruction and compare it with the quantity of material already grasped; if the quantity of material already grasped is less than the material quantity information, it is determined that loading needs to continue; control the robotic arm to place the currently grasped material into the receiving cavity of the filler; detect the loading status through the material detection sensor set in the filler and update the quantity of material already grasped; repeat the material identification and grasping process until the quantity of material already grasped is equal to the material quantity information.

[0115] In some embodiments, the execution status information acquisition module is further configured to acquire execution status information through the main control unit; the execution status information includes the content of the currently executed instruction, material grabbing information, and chassis position information; convert the execution status information into display data and display it in real time through the display unit; and simultaneously transmit the execution status information back to the operator terminal through the communication unit.

[0116] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0117] Example 4 This invention also provides an intelligent logistics robot; this intelligent logistics robot is used to implement the intelligent logistics handling method described in the above embodiments.

[0118] Figure 4A structural diagram of the intelligent logistics robot provided in the embodiments of the present invention is shown below. Figure 4 As shown, the intelligent logistics robot includes the following structure: The chassis is used to support the various functional units and enable their movement.

[0119] The chassis is the robot's basic load-bearing structure, located at the bottom of the robot. It is responsible for supporting all other functional units and providing mobility.

[0120] The chassis may include: Frame: Made of high-strength aluminum alloy or carbon fiber, it is lightweight and high-strength, used to support and secure all functional units. The frame is equipped with mounting holes and cable channels for easy mounting and wiring of each module.

[0121] Mecanum wheels: Located at the four corners of the bottom of the frame, each wheel consists of multiple peripheral axles arranged at an angle. The peripheral axles are set at a 45° angle to the center line of the wheel hub. When the wheel rotates, the peripheral axles contact the ground to generate friction, converting part of the steering force into normal force, thus enabling omnidirectional movement.

[0122] The Mecanum wheel design enables the robot to move flexibly in confined spaces without a turning radius, allowing it to move arbitrarily laterally or diagonally.

[0123] Drive motors: Connected to each Mecanum wheel drive, these are typically brushless DC motors or stepper motors, characterized by fast response and high control precision. Each motor independently drives one wheel, achieving movement in different directions through differential speed control.

[0124] Motor driver: Electrically connected to the main control unit, it receives PWM control signals, converts them into motor drive current, and controls the motor speed and direction.

[0125] The execution unit, mounted on the chassis, is used to perform the grabbing, loading, and placement of materials.

[0126] The execution unit is the robot's motion execution mechanism, responsible for directly contacting the material and completing operations such as grasping, loading, and placing.

[0127] The execution unit may include a robotic arm and a loader.

[0128] robotic arm: Linkage structure: Composed of multiple rigid links connected by joints, typically a 4-axis or 6-axis articulated robotic arm. Each joint is driven by a servo motor or servo motor, enabling multi-degree-of-freedom motion.

[0129] Mechanical gripper: Located at the end of the robotic arm, it is used to directly contact and grasp materials. The mechanical gripper features a replaceable design and is equipped with various gripper shapes (such as parallel grippers, three-finger grippers, suction cups, etc.) to adapt to materials of different shapes.

[0130] Rubber anti-slip layer: Located on the inner surface of the mechanical claw, it is made of rubber material with a high coefficient of friction to increase the friction between the material and the gripper and prevent the material from slipping during the gripping process.

[0131] Force sensor: Located inside the mechanical gripper, it is a strain gauge pressure sensor that detects the gripping force in real time. When the preset threshold is reached, a feedback signal is sent to prevent overpressure from damaging the material.

[0132] Filler: Storage cavity: Located on the chassis within the working range of the robotic arm, it is used to temporarily store multiple materials. The cavity size is designed according to the size of the target material and can hold 3-10 materials.

[0133] Material detection sensor: Located inside the receiving cavity, it uses a photoelectric switch or ultrasonic sensor to detect whether material has been placed in and the quantity of material. Each time material is placed in, the sensor triggers a signal to update the grasped count.

[0134] Lifting platform (optional): Located at the bottom of the receiving cavity, driven by a micro motor, it automatically descends as the amount of material increases, maintaining a consistent height for each insertion and preventing materials from piling up too high, which would make insertion difficult.

[0135] For example, when grasping a cylindrical part, the main control unit selects a three-finger gripper based on visual recognition results and calculates the angles of each joint of the robotic arm. The servo motor drives the robotic arm to move, and the three-finger gripper reaches directly above the part, descends to the grasping height, and closes. When the force sensor detects that the grasping force reaches 3N, it stops closing and maintains the gripping position. The robotic arm lifts the part, moves it above the loading device, the three-finger gripper opens, the part falls into the receiving cavity, a photoelectric switch detects the placement, and a counter increments by 1.

[0136] The sensing unit, located on the chassis and execution unit, is used to collect environmental and material information.

[0137] Among them, the sensing unit is responsible for collecting environmental and material information, providing a data foundation for autonomous decision-making.

[0138] The perception unit may include a visual recognition module and a path perception module.

[0139] Visual recognition module: OPENMV camera: Employs a high-resolution CMOS image sensor, supporting real-time image acquisition and on-chip processing, with a frame rate exceeding 30fps. The camera is mounted on the end effector of a robotic arm or a standalone pan-tilt unit, allowing it to move with the robotic arm or rotate independently.

[0140] Gimbal: Located below the camera, it drives the camera to shoot from multiple angles. The gimbal includes: Gimbal bracket: A supporting structure for fixing the camera.

[0141] Drive servo motor: Connected to the gimbal bracket, it can drive the gimbal to rotate in two degrees of freedom: pitch and yaw.

[0142] Image stabilization device: Located inside the gimbal bracket, it uses a gyroscope and accelerometer to detect vibrations in real time and compensate in reverse to eliminate image shake during movement.

[0143] Image processing chip: Integrated into the camera module or main control unit, responsible for image preprocessing, feature extraction, matching and recognition, and depth calculation.

[0144] Path awareness module: Grayscale sensors: Located at the bottom of the chassis, arranged in an array along the direction of travel, typically 3-5 sensors. Each sensor includes: Infrared emitter: emits infrared light towards the ground.

[0145] Photosensitive receiver tube: Receives light reflected from the ground and converts it into an electrical signal.

[0146] Signal conditioning circuit: amplifies, filters, and performs analog-to-digital conversion on electrical signals, outputting grayscale values ​​from 0 to 255.

[0147] Path markings: Black tape or colored strips placed on the ground to serve as guide lines for the robot to follow.

[0148] The main control unit is electrically connected to the chassis, execution unit and sensing unit respectively, and is used to receive and process various signals and generate control commands.

[0149] The main control unit is responsible for receiving various signals, processing data, running control algorithms, generating control commands, and coordinating the collaborative work of various units.

[0150] The main control unit includes: STM32 microcontroller: Uses STM32F103 or higher performance series as the core processor. It integrates an ARM Cortex-M core with a main frequency of up to 72MHz and has rich peripheral interfaces (UART, I2C, SPI, CAN, PWM, ADC, etc.).

[0151] Memory: Includes Flash memory for storing program code and preset parameters (such as material feature library, path threshold), and RAM memory for running programs and processing temporary data.

[0152] The CID control algorithm module is integrated into the microcontroller in software form, performing calculations for time control, integral control, and derivative control. The algorithm module includes: Time control submodule: Adjusts the output based on the deviation between the actual running time and the set time.

[0153] Integral control submodule: Accumulates compensation for persistent deviations and eliminates static errors.

[0154] Differential control submodule: Adjusts in advance based on the rate of change of deviation to suppress oscillation.

[0155] Motor drive circuit: electrically connected to the PWM output terminal of the microcontroller, amplifying the PWM signal into the current signal required to drive the motor.

[0156] The communication unit is electrically connected to the main control unit and is used for data interaction with external devices.

[0157] The communication unit is responsible for receiving operator instructions and transmitting status information.

[0158] The communication unit includes: Wireless communication module: Employs a WiFi module (such as ESP8266) or a Bluetooth module (such as HC-05), supporting 2.4GHz band wireless communication. It can also be expanded to a 4G / 5G module for long-distance communication.

[0159] Antenna: Electrically connected to the wireless communication module to enhance signal transmission and reception capabilities.

[0160] The communication protocol stack is integrated into the main control unit in software form, supporting protocols such as TCP / IP, MQTT, and HTTP, and realizing data encapsulation, transmission, and unpacking.

[0161] The display unit, electrically connected to the main control unit, is used to provide real-time feedback on the robot's operating status.

[0162] The display unit is the human-machine interface between the robot and the operator, used to intuitively display the robot's operating status information.

[0163] The display unit includes: HMI serial port display: Uses a color TFT LCD screen that supports touch control. The screen size is typically 3.5 inches to 7 inches, with a resolution of at least 480×320.

[0164] Display driver circuit: Electrically connected to the main control unit, it receives display data and drives the screen display.

[0165] Graphical interface software: Integrated into the main control unit or screen in the form of software, responsible for converting status information into a graphical display interface, including elements such as text, icons, progress bars, and maps.

[0166] Example 5 This invention also provides an electronic device for running the above-described intelligent logistics handling method; see [link to related documentation]. Figure 5 The diagram shows the structure of an electronic device, which includes a memory 500 and a processor 501. The memory 500 is used to store one or more computer instructions, which are executed by the processor 501 to realize the above-mentioned intelligent logistics handling method.

[0167] Furthermore, Figure 5 The electronic device shown also includes a bus 502 and a communication interface 503. The processor 501, the communication interface 503 and the memory 500 are connected via the bus 502.

[0168] The memory 500 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0169] Processor 501 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 501 or by instructions in software form. Processor 501 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 500, and processor 501 reads information from memory 500 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0170] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the aforementioned intelligent logistics handling method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0171] The computer program product for intelligent logistics handling provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0172] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0173] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0174] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0176] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0177] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent logistics handling method, characterized in that, This invention relates to an intelligent logistics robot, which includes: a chassis, a robotic arm mounted on the chassis, a filler mounted on the chassis, a main control unit, a vision recognition unit, a path perception unit, a communication unit, and a display unit; the robotic arm includes a robotic gripper. The method includes: The system acquires handling instructions sent by the operator through the communication unit, the handling instructions including target material information, target material location, and placement location; The transport instructions are parsed to obtain the transport task parameters; Based on the transport task parameters, the path sensing unit collects path signals and processes the path signals to obtain tracking control commands. The chassis is controlled to move to the target material location according to the tracking control command; The visual recognition unit acquires image data of the target material and performs recognition processing on the image data to obtain information on the material type, spatial location, and grasping posture. Based on the spatial location and grasping posture information, motion trajectory parameters of the robotic arm are generated using the CID algorithm; The robotic arm is controlled to perform a grasping action based on the motion trajectory parameters to acquire the target material; Determine whether multiple materials need to be loaded. If so, temporarily store the grabbed materials in the filler and repeat the material identification and grabbing process until all materials are loaded. The chassis is controlled to move along a tracking path to the placement position, and the robotic arm is controlled to perform a placement action to release the target material into the designated area; The chassis is controlled to return to the starting point by tracking, and the execution status information obtained from the main control unit is fed back in real time through the display unit.

2. The method according to claim 1, characterized in that, The parsing of the transport instruction to obtain transport task parameters includes: The transport instructions are parsed according to the protocol to extract the instruction type field; The instruction type field is used to determine whether the handling task is for single-material handling or multi-material handling. If it involves the handling of multiple materials, the parsing process will yield the quantity of materials, the grabbing order of each material, and the location of the corresponding target material.

3. The method according to claim 1, characterized in that, The step of acquiring path signals through the path sensing unit and processing the path signals to obtain tracking control commands includes: The path sensing unit collects grayscale signals of the ground path in real time. The grayscale signal is compared with a preset path threshold to obtain the path deviation value; The steering correction amount of the chassis is calculated based on the path deviation value, and a tracking control command is generated.

4. The method according to claim 1, characterized in that, The process of acquiring image data of the target material through the visual recognition unit and performing recognition processing on the image data to obtain material type, spatial location, and grasping posture information includes: Image data of the target material is acquired through the visual recognition unit; The image data is preprocessed to obtain an enhanced image; Feature extraction is performed on the enhanced image to obtain the material feature vector; The material feature vector is matched with a preset material feature library to identify the material type; Depth information is extracted from the enhanced image to calculate the spatial location and grasping posture information of the material.

5. The method according to claim 4, characterized in that, The step of extracting depth information from the enhanced image and calculating the spatial location and grasping posture information of the material includes: Depth maps are obtained by calculating disparity in multi-view images using a binocular vision algorithm. Determine the center point coordinates and edge contour of the material based on the depth map; Based on the center point coordinates and edge contours, calculate the gripping point coordinates of the material and the closing angle of the mechanical claw.

6. The method according to claim 1, characterized in that, The step of generating motion trajectory parameters for the robotic arm using the CID algorithm based on the spatial position and grasping posture information includes: Obtain the current position parameters and target position parameters of the robotic arm, and calculate the position deviation value; The position deviation value is input into the CID controller; the CID controller calculates the control output value according to the combined operation rules of time control, integral control and derivative control; The motion trajectory parameters of each joint of the robotic arm are generated based on the control output value; the motion trajectory parameters include motion speed, acceleration and target angle.

7. The method according to claim 1, characterized in that, The step of controlling the robotic arm to perform a grasping action and acquire the target material according to the motion trajectory parameters includes: The movement of the linkage structure of the robotic arm is controlled according to the motion trajectory parameters, so that the robotic claw moves to the grasping position of the target material; Control the robotic gripper to perform a closing action to acquire the target material; After the gripping is completed, the gripping force is detected by a force sensor located on the inside of the mechanical claw, and the closing stops when the gripping force reaches a preset threshold.

8. The method according to claim 1, characterized in that, The determination of whether multiple materials need to be loaded, and if so, the grabbed materials are temporarily stored in the filler, and the material identification and grabbing steps are repeated until all materials are loaded, including: Obtain the material quantity information in the handling instruction and compare it with the quantity of material already grabbed; If the quantity of materials already captured is less than the quantity of materials, it is determined that loading needs to continue; Control the robotic arm to place the currently grasped material into the receiving cavity of the filler; The loading status is detected by a material detection sensor installed in the filler, and the quantity of material already grabbed is updated. Repeat the material identification and grabbing process until the number of grabbed materials equals the material quantity information.

9. The method according to claim 1, characterized in that, The real-time feedback of execution status information obtained from the main control unit through the display unit includes: The execution status information is obtained through the main control unit; the execution status information includes the currently executed instruction content, material grabbing information, and chassis position information; The execution status information is converted into display data and displayed in real time through the display unit; Simultaneously, the execution status information is transmitted back to the operator terminal via the communication unit.

10. An intelligent logistics robot for implementing the intelligent logistics handling method according to any one of claims 1 to 9, characterized in that, The intelligent logistics robot includes: The chassis is used to support the various functional units and enable their movement. An execution unit, mounted on the chassis, is used to perform material grabbing, loading, and placement operations; A sensing unit, mounted on the chassis and execution unit, is used to collect environmental and material information; The main control unit is electrically connected to the chassis, the execution unit and the sensing unit respectively, and is used to receive and process various signals and generate control commands. A communication unit, electrically connected to the main control unit, is used for data interaction with external devices; The display unit, electrically connected to the main control unit, is used to provide real-time feedback on the robot's operating status information.

Images