An autonomous unloading method, device and medium for a loader

Abstract

This invention discloses an autonomous unloading method, device, and medium for a loader, belonging to the field of loader unloading technology. The method includes: determining a feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device; constructing a stage cost function and a terminal cost function for the unloading process based on a dynamic programming algorithm and the feasible solution space, and determining the globally optimal unloading trajectory; determining a mathematical model of the electro-hydraulic servo system based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader's working device; constructing displacement, velocity, and acceleration tracking errors based on the globally optimal unloading trajectory and hydraulic cylinder extension / retraction data from the state acquisition module, determining a trajectory tracking error model; determining a nonlinear integral sliding surface function based on the trajectory tracking error model; and determining a control instruction set based on the nonlinear integral sliding surface function through equivalent control terms and switching control terms with chatter suppression.

Description

Technical Field

[0001] This invention discloses a method, device, and medium for autonomous unloading of a loader, belonging to the field of loader unloading technology. Background Technology

[0002] Loaders are widely used in material handling operations in mining, ports, and construction projects. Traditionally, their unloading process relies heavily on manual operation. Existing research on automated unloading either merely replicates the trajectory of manual operation or adopts pure kinematic planning schemes. Moreover, trajectory planning and trajectory tracking control are often studied separately, without forming a systematic solution. At the same time, existing technologies generally do not fully consider the optimization of unloading energy consumption and the impact of materials on dump trucks. They also struggle to cope with the uncertain parameters of the loader's electro-hydraulic servo system and the significant external load disturbances. This results in problems such as poor trajectory consistency, large hydraulic shock, low automation, and weak environmental adaptability in unloading operations, failing to meet the high-intensity and high-reliability autonomous unloading operation requirements of unmanned loaders. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention proposes a method, device, and medium for autonomous unloading of loaders, which solves the technical problems of poor trajectory consistency, low unloading efficiency, and large hydraulic impact caused by the reliance on manual experience in traditional loader unloading operations.

[0004] The technical solution of the present invention is as follows:

[0005] According to a first aspect of the present invention, a method for autonomous unloading of a loader is provided. The method is applied to an autonomous unloading system for a loader, the autonomous unloading system for a loader including an environmental sensing module, a status acquisition module, a terminal, a vehicle control unit module, and an actuator module. The environmental sensing module, the status acquisition module, and the vehicle control unit module are electrically connected to the terminal, and the vehicle control unit module is electrically connected to the actuator module. The method includes:

[0006] Based on the 3D point cloud data and image information of the unloading area collected by the environmental perception module, the spatial constraints of the unloading target area are determined.

[0007] Based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device, the feasible solution space for unloading trajectory planning is determined.

[0008] Based on dynamic programming algorithm and feasible solution space, stage cost function and terminal cost function of unloading process are constructed to determine the global optimal unloading trajectory;

[0009] Based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader working device, the mathematical model of the electro-hydraulic servo system is determined.

[0010] Based on the global optimal unloading trajectory and the hydraulic cylinder extension and retraction data of the state acquisition module, displacement, velocity and acceleration tracking errors are constructed, a trajectory tracking error model is determined, and a nonlinear integral sliding surface function is determined based on the trajectory tracking error model.

[0011] Based on the nonlinear integral sliding mode surface function, a control instruction set is determined through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module.

[0012] Furthermore, based on the 3D point cloud data and image information of the unloading area collected by the environmental perception module, the spatial constraints of the unloading target area are determined, specifically including:

[0013] Based on the multi-source fusion results of 3D point cloud data and image information, the contour features and spatial coordinates of the dump truck are extracted to determine the effective unloading boundary of the dump truck's hopper.

[0014] Based on the effective unloading boundary of the truck bed and the operating safety distance requirements of the loader, the spatial coordinate range and geometric constraints of the unloading target area are determined, and the spatial constraint conditions are obtained.

[0015] Furthermore, based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device, the feasible solution space for unloading trajectory planning is determined, specifically including:

[0016] Based on the kinematic model of the loader's working device, a two-way mapping relationship between the spatial pose of the loader's working device and the displacement of the hydraulic cylinder in the actuator module is established.

[0017] Based on spatial constraints, the physical motion limits and anti-collision specifications of the loader's working device are used to determine the unloading start posture constraints, end posture constraints, and full-process motion range constraints. Based on multi-dimensional constraints, the feasible solution space is delineated.

[0018] Furthermore, based on the dynamic programming algorithm and feasible solution space, the stage cost function and terminal cost function of the unloading process are constructed to determine the globally optimal unloading trajectory, specifically including:

[0019] Based on the displacement and velocity of the hydraulic cylinder in the actuator module, the system state variables of the dynamic programming algorithm are determined, and based on the control input of the proportional servo valve, the control input variables of the dynamic programming algorithm are determined.

[0020] Based on the single-stage trajectory tracking accuracy and control input smoothness, the stage cost function is determined; based on the unloading terminal pose accuracy, the terminal cost function is determined; and an overall performance index function with the sum of the two as its core is constructed.

[0021] Based on the Bellman recursive formula and the objective of minimizing the overall performance index function, the optimal control input sequence for each discrete decision stage is determined by reverse recursion within the feasible solution space, thereby generating the globally optimal unloading trajectory.

[0022] Furthermore, based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader's working device, the mathematical model of the electro-hydraulic servo system is determined, specifically including:

[0023] Based on the structural parameters of the proportional servo valve and the physical properties of the hydraulic oil, the flow equation of the proportional servo valve orifice is determined.

[0024] Based on the structural parameters and leakage characteristics of the hydraulic cylinder in the actuator module, the hydraulic cylinder flow continuity equation is determined;

[0025] Based on the balance relationship between the equivalent load, viscous damping and driving force of the hydraulic cylinder, the force balance equation of the hydraulic cylinder is determined.

[0026] Based on the coupling relationship of the three equations, the mathematical model of the electro-hydraulic servo system is determined.

[0027] Furthermore, based on the globally optimal unloading trajectory and the hydraulic cylinder extension / retraction data from the status acquisition module, displacement, velocity, and acceleration tracking errors are constructed, and a trajectory tracking error model is determined, specifically including:

[0028] Based on the globally optimal unloading trajectory, the desired displacement, desired velocity, and desired acceleration of the hydraulic cylinder are extracted;

[0029] Based on the hydraulic cylinder extension and retraction data collected by the status acquisition module, the actual displacement, actual velocity and actual acceleration of the hydraulic cylinder are calculated.

[0030] Based on the difference between the expected parameters and the actual parameters, the displacement tracking error, velocity tracking error and acceleration tracking error are determined respectively, and a trajectory tracking error model is constructed by coupling them.

[0031] Furthermore, based on the trajectory tracking error model, the nonlinear integral sliding mode surface function is determined, specifically including:

[0032] Based on the position tracking error and velocity tracking error in the trajectory tracking error model, a nonlinear integral term with saturation characteristics is introduced;

[0033] Based on the error convergence speed requirement, the sliding surface parameters are set, and the nonlinear integral sliding surface function is determined by the position tracking error, velocity tracking error and nonlinear integral term.

[0034] Furthermore, the control instruction set is determined through equivalent control terms and switching control terms with chatter suppression, specifically including:

[0035] Based on the ideal sliding mode dynamic characteristics, the time derivative of the nonlinear integral sliding surface function is set to 0, and the equivalent control term is determined through the mathematical model of the electro-hydraulic servo system.

[0036] Based on the power-law approach, a continuous saturation function is used to replace the sign function, and the boundary layer thickness is set by the chattering suppression requirement to determine the switching control term with chattering suppression.

[0037] Based on the superposition of equivalent control terms and switching control terms, the real-time control input is determined, and the real-time control input is converted into an instruction format that matches the communication protocol of the vehicle control unit module to obtain the control instruction set.

[0038] According to a second aspect of the present invention, a loader autonomous unloading device is provided, comprising:

[0039] The environmental perception module is used to determine the spatial constraints of the unloading target area based on the three-dimensional point cloud data and image information of the unloading area collected by the environmental perception module.

[0040] The pose constraint module is used to determine the feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device.

[0041] The trajectory planning module is used to construct the stage cost function and terminal cost function of the unloading process based on the dynamic programming algorithm and the feasible solution space, and to determine the globally optimal unloading trajectory.

[0042] The system modeling module is used to determine the mathematical model of the electro-hydraulic servo system based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader working device.

[0043] The sliding mode control module is used to construct displacement, velocity and acceleration tracking errors based on the globally optimal unloading trajectory and the hydraulic cylinder extension and retraction data from the state acquisition module, determine the trajectory tracking error model, and determine the nonlinear integral sliding surface function based on the trajectory tracking error model.

[0044] The control instruction module is used to determine the control instruction set based on the nonlinear integral sliding mode surface function, through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module.

[0045] According to a third aspect of the present invention, a terminal is provided, comprising:

[0046] One or more processors;

[0047] Memory for storing the one or more processor-executable instructions;

[0048] Wherein, the one or more processors are configured as follows:

[0049] Perform the method described in the first aspect of the embodiments of the present invention.

[0050] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to perform the method described in the first aspect of the present invention.

[0051] According to a fifth aspect of the present invention, an application product is provided that, when the application product is running on a terminal, causes the terminal to execute the method described in the first aspect of the present invention.

[0052] The beneficial effects of this invention are as follows:

[0053] This invention provides a method, device, and medium for autonomous unloading of loaders. It accurately determines the unloading target area constraints through environmental perception, and obtains the globally optimal unloading trajectory using a dynamic programming algorithm. Simultaneously, it constructs a high-precision, robust trajectory tracking control system based on sliding mode control, achieving systematic and automated closed-loop control of loader unloading trajectory planning and tracking. This effectively improves the consistency and repeatability of the unloading trajectory, significantly reduces pressure shocks and mechanical vibrations in the hydraulic system, and extends the service life of hydraulic components and mechanical structures. The designed sliding mode control law, through equivalent control terms and switching control terms with chatter suppression, greatly improves the system's robustness to model uncertainties and external load disturbances, ensuring stable operation during the unloading process. The entire method does not rely on manual operating experience, optimizes energy consumption during unloading operations, reduces the impact of materials on the dump truck, and improves the efficiency and safety of unloading operations. It has strong adaptability to the operating environment and can meet the high-intensity, repetitive autonomous unloading operation requirements of unmanned loaders in scenarios such as mines and ports, promoting the unmanned and intelligent development of loader operations.

[0054] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0055] Figure 1 This is a structural diagram illustrating an autonomous unloading system for a loader according to an exemplary embodiment.

[0056] Figure 2 This is a partial structural diagram of a loader autonomous unloading system according to an exemplary embodiment.

[0057] Figure 3 This is a flowchart illustrating an autonomous unloading method for a loader according to an exemplary embodiment.

[0058] Figure 4This is a flowchart illustrating an autonomous unloading method for a loader according to an exemplary embodiment.

[0059] Figure 5 This is a schematic block diagram illustrating the structure of an autonomous unloading device for a loader according to an exemplary embodiment.

[0060] Figure 6 This is a schematic block diagram of a terminal structure according to an exemplary embodiment. Detailed Implementation

[0061] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. 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.

[0062] In the description of this invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0063] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0064] This invention provides a method for autonomous unloading of materials by a loader, which is implemented by a terminal, including at least a CPU.

[0065] Example 1: An exemplary embodiment illustrates a method for autonomous unloading of a loader, the method being applied to an autonomous unloading system for a loader, such as... Figure 1 and Figure 2As shown, the loader's autonomous unloading system includes an environmental perception module 2, a status acquisition module, a terminal 3, a vehicle control unit module 1, and an actuator module. The environmental perception module 2, status acquisition module, and vehicle control unit module 1 are electrically connected to the terminal 3, and the vehicle control unit module 1 is electrically connected to the actuator module. The environmental perception module 2 includes a camera 103 and a radar 101, used to collect environmental information of the unloading area in front of the loader, acquiring images and point cloud data of the unloading area. The status acquisition module includes a boom cylinder displacement sensor 6 and a bucket cylinder displacement sensor 4, used to collect displacement status information of the loader's working device. The terminal 3 processes the data acquired by the environmental perception module 2 and the status acquisition module to complete unloading trajectory planning and control quantity calculation. The vehicle control unit module 1 receives control commands output by the decision and control terminal module and converts them into drive signals for proportional servo valves. The actuator module includes a boom hydraulic cylinder 7 and a bucket hydraulic cylinder 5, used to complete unloading operations under VCU control. The loader's autonomous unloading method is as follows: Figure 3 and Figure 4 As shown, it includes:

[0066] Step 101: Based on the 3D point cloud data and image information of the unloading area collected by the environmental perception module, determine the spatial constraints of the unloading target area. The specific steps are as follows:

[0067] The loader uses a front-mounted camera and LiDAR to perceive the unloading area in real time, acquiring point cloud data within the area. Based on this point cloud data, the spatial position and attitude of the dump truck are identified, and the spatial pose information of the truck bed is extracted, including the truck bed's spatial position, orientation, and boundary range, providing spatial constraints for subsequent unloading trajectory planning. After completing the unloading area perception and target pose acquisition, the process proceeds to the next step.

[0068] Step 102: Based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device, the feasible solution space for unloading trajectory planning is determined. The specific steps are as follows:

[0069] A kinematic model of the loader's working device is established to describe the geometric relationships and motion laws among the various actuators, thus providing a unified pose expression for unloading trajectory planning. By modeling the motion relationships of the boom, connecting rod, and bucket, the spatial motion of the loader during unloading is transformed into a computable mathematical model.

[0070] The kinematic model of the working device is used to map the pose constraints in the unloading task into the displacement variables of key hydraulic cylinders, enabling the unloading trajectory planning process to be solved directly based on the displacement space of the hydraulic cylinders. Based on this model, the host computer can plan the motion trajectory of the loader's working device while satisfying the unloading start pose, unloading end pose, and safe movement range constraints. Specifically:

[0071] Step 2.1) Select the boom hydraulic cylinder and bucket hydraulic cylinder in the loader's working device as the research objects, and use the displacement of the hydraulic cylinder as the system state variable. Define the system state vector as:

[0072]

[0073] in, Indicates the first The displacement state of each hydraulic cylinder.

[0074] Step 2.1), using the proportional servo valve spool input current as the system control input, define the control input vector as:

[0075]

[0076] After completing the motion modeling of the loader's working device, based on the kinematic model of the loader's working device, the geometric structure and motion connection relationship of the core components of the working device, such as the boom, connecting rod, and bucket, are accurately modeled. The positions of the hinge points, the constraints of the rotating pairs, and the motion transmission laws between each component are clarified. The spatial pose motion of the loader's working device is decomposed into the linear extension and retraction motion of the boom hydraulic cylinder and the bucket hydraulic cylinder. A two-way forward and inverse kinematic mapping relationship is established between the pose parameters of the loader's working device in three-dimensional space and the extension and retraction displacements of the boom hydraulic cylinder and the bucket hydraulic cylinder in the actuator module. The forward mapping is based on the real-time extension and retraction displacement of the hydraulic cylinder to obtain the corresponding spatial pose state of the loader's working device. The inverse mapping is based on the target spatial pose of the loader's working device to obtain the target extension and retraction displacements required by the boom hydraulic cylinder and the bucket hydraulic cylinder. This realizes the mutual conversion and accurate calculation of the spatial pose of the working device and the displacement of the hydraulic cylinder, providing a unified pose expression and a calculable displacement variable basis for subsequent unloading trajectory planning.

[0077] Based on the spatial constraints of the unloading target area, and combined with the established two-way mapping relationship between the spatial pose of the working device and the displacement of the hydraulic cylinder, and according to the physical motion limits and collision avoidance safety specifications of the loader's working device, the multi-dimensional pose constraints of the entire unloading operation process are determined sequentially: First, the unloading start pose constraint, that is, when the loader enters the unloading process after completing the material loading, the spatial pose and hydraulic cylinder displacement constraints corresponding to the initial boom lifting height and bucket retraction angle of the working device are determined to ensure that the initial state meets the action start requirements of the unloading operation; Second, the unloading end pose constraint, that is, when the loader completes the material unloading, the spatial pose and hydraulic cylinder displacement constraints corresponding to the bucket tilting angle and boom lifting height are determined to ensure that the material can be accurately unloaded into the dump truck hopper without spillage or collision; Third, the full-process motion range constraint, that is, the upper and lower limits of the spatial motion of the boom and bucket, and the limit constraints of the hydraulic cylinder extension stroke during the unloading operation, to avoid collisions between the working device and the dump truck and the surrounding working environment, while avoiding the extreme working conditions of the hydraulic system and mechanical structure to prevent equipment damage. Using the unloading start pose constraint, end pose constraint, and full-process motion range constraint as boundary conditions, the spatial pose constraint is transformed into the numerical constraint range of the hydraulic cylinder displacement through the bidirectional mapping between the spatial pose of the working device and the displacement of the hydraulic cylinder. Finally, the feasible solution space of the unloading trajectory planning is defined, ensuring that the subsequent trajectory planning results based on the dynamic programming algorithm are all within the safe, compliant, and feasible range.

[0078] Step 103: Based on the dynamic programming algorithm and the feasible solution space, construct the stage cost function and terminal cost function of the unloading process, and determine the globally optimal unloading trajectory. The specific steps are as follows:

[0079] Using the key pose parameters of the working device during the unloading process of the loader as the system state variables, the discrete state vector is defined as:

[0080]

[0081] in, Indicates the first The positional and orientation variables of the loader's working device in each discrete stage. This represents the corresponding velocity variable.

[0082] Define the discrete control input as:

[0083]

[0084] The continuous time interval of the unloading process Divided into Each discrete stage is defined as its discrete time point:

[0085]

[0086] in, For each discrete moment, the system state is denoted as: .

[0087] Based on the kinematic relationship of the loader's working device, the discrete state transition equation of the system is established:

[0088]

[0089] Among them, the function Indicates the current state of the system. and control input Transition to the next stage state under the influence of the action The mapping relationship.

[0090] To comprehensively consider both the tracking accuracy and control stability of the unloading trajectory, the stage cost function is constructed as follows:

[0091]

[0092] in: For the first Reference status for the stage; This is the weighting matrix for the state error; To control the input weighting matrix.

[0093] To improve the accuracy of the terminal state during the final stage of the unloading process, the terminal cost function is constructed as follows:

[0094]

[0095] in: This represents the desired unloading termination state; This is the weighted matrix for the terminal state.

[0096] The overall performance index function for unloading trajectory planning is defined as follows:

[0097]

[0098] The goal of dynamic programming is to find a solution that satisfies the system constraints and makes the performance index function... The optimal control sequence that achieves the minimum value.

[0099] Introducing a value function Its recursive relation is expressed as:

[0100]

[0101] The terminal conditions are:

[0102]

[0103] Through the above recursive process, the optimal control input sequence for each discrete stage is obtained, and the optimal trajectory for the loader unloading process is generated.

[0104] Step 104: Based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader's working device, determine the mathematical model of the electro-hydraulic servo system. The specific content is as follows:

[0105] After obtaining the optimal unloading trajectory of the loader, in order to achieve precise control of the boom and bucket movements, a mathematical model of the electro-hydraulic servo system of the loader's working device is established to describe the dynamic relationship between the control input and the motion state of the hydraulic cylinder.

[0106] The loader's working device uses a proportional servo valve to control the movement of the hydraulic cylinders. Its electro-hydraulic servo system model includes the proportional servo valve flow equation, the hydraulic cylinder continuity equation, and the hydraulic cylinder force balance equation. Specifically:

[0107] The flow equation for the proportional servo valve orifice is established as follows:

[0108]

[0109] in: This refers to the flow rate at the valve orifice of the proportional servo valve. For flow coefficient; This refers to the effective width of the valve port; This refers to the valve core displacement of the proportional servo valve. Provide oil pressure for the hydraulic system; This refers to the pressure inside the hydraulic cylinder cavity; This refers to the density of the hydraulic oil.

[0110] The flow continuity equation within the hydraulic cylinder cavity is established as follows:

[0111]

[0112] in: This refers to the effective working area of ​​the hydraulic cylinder. The speed of the hydraulic cylinder piston; This is the equivalent leakage coefficient of the hydraulic system; This refers to the pressure inside the hydraulic cylinder cavity.

[0113] The piston of a hydraulic cylinder satisfies a force balance relationship during its movement, and its dynamic equation is expressed as:

[0114]

[0115] in: The equivalent mass of the hydraulic cylinder and its driven working device; This refers to the acceleration of the hydraulic cylinder piston. It is the equivalent viscous damping coefficient; This refers to the external load force acting on the hydraulic cylinder.

[0116] A mathematical model of the electro-hydraulic servo system of the loader working device is established using the above equations.

[0117] Step 105: Based on the globally optimal unloading trajectory and the hydraulic cylinder extension / retraction data from the state acquisition module, construct the displacement, velocity, and acceleration tracking errors, determine the trajectory tracking error model, and based on the trajectory tracking error model, determine the nonlinear integral sliding surface function. The specific details are as follows:

[0118] Based on the optimal unloading trajectory, a trajectory tracking error model for the loader's working device is constructed. A sliding surface function is built based on position error, velocity error, and error integral terms to describe the desired dynamic characteristics of the system. The trajectory tracking problem is transformed into a sliding mode arrival and holding problem using this sliding surface. Specifically:

[0119] Step 5.1), define the hydraulic cylinder displacement tracking error as:

[0120]

[0121] The first derivative of the error is defined as:

[0122]

[0123] The second derivative of the error is defined as:

[0124]

[0125] in: , , These are the actual displacement, velocity, and acceleration of the hydraulic cylinder, respectively. , , These represent the expected displacement, velocity, and acceleration corresponding to the planned trajectory.

[0126] The linear sliding surface function is constructed as follows:

[0127]

[0128] in: , The positive sliding surface parameter is used to adjust the convergence speed of system error.

[0129] Furthermore, to eliminate the steady-state error of the system, an integral term is introduced, and the integral sliding surface function is constructed as follows:

[0130]

[0131] in, This is the integral gain coefficient.

[0132] Furthermore, to suppress integral saturation and enhance system robustness, a nonlinear integral function is introduced, resulting in a nonlinear integral sliding surface function:

[0133]

[0134] in, It is a nonlinear function with saturation characteristics.

[0135] After completing the construction of the sliding surface, proceed to the next step.

[0136] Step 106: Based on the nonlinear integral sliding mode surface function, a control instruction set is determined through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module. The specific steps are as follows:

[0137] Based on the sliding mode surface function, a sliding mode control law is designed, and the control input is decomposed into equivalent control terms and switching control terms. Power-law approach and saturation function are used to suppress sliding mode chattering, improving system stability and control smoothness. The sliding mode control law is used to calculate the control input of the loader's working device. Specifically:

[0138] The control input is decomposed into an equivalent control term and a switching control term, and its expression is:

[0139]

[0140] in: Equivalent control item; To switch control items.

[0141] Construct an equivalent control term, under ideal conditions, by setting the derivative of the sliding surface to satisfy:

[0142]

[0143] The general form of the equivalent control term can be obtained:

[0144]

[0145] in, It is a continuous function determined by the system model.

[0146] To construct the switching control term and ensure that the system state reaches the sliding surface within a finite time, an exponential reaching law is selected.

[0147]

[0148] in: To approach the gain; It is a power exponent; It is a symbolic function.

[0149] To reduce sliding mode chattering, the sign function is replaced with a saturation function, resulting in:

[0150]

[0151] in, This represents the boundary layer thickness.

[0152] The final sliding mode control law is expressed as:

[0153]

[0154] After completing the sliding mode control law design, the system stability is analyzed based on the sliding mode control law to verify the convergence of the control system under disturbance conditions. The calculated control quantity is then converted into a rocker arm opening command to drive the boom and bucket to complete the unloading operation. Specifically:

[0155] The Lyapunov function is chosen as follows:

[0156]

[0157] Taking its time derivative, we get:

[0158]

[0159] Combining the sliding mode control law, we can obtain:

[0160]

[0161] This demonstrates that under the designed sliding mode control, the electro-hydraulic servo system of the loader's working device has good stability and convergence.

[0162] Based on the control quantity output by the sliding mode controller, the target displacement change of the boom hydraulic cylinder and the bucket hydraulic cylinder is calculated, and the target displacement change is converted into a joystick opening control command equivalent to that of a manually operated joystick.

[0163] The joystick opening control command is sent to the vehicle control unit (VCU). Based on the received joystick opening control command, the VCU outputs the corresponding proportional servo valve drive signal to control the boom hydraulic cylinder and bucket hydraulic cylinder to perform corresponding extension and retraction actions, so that the loader working device completes the unloading operation according to the planned trajectory.

[0164] Furthermore, based on the 3D point cloud data and image information of the unloading area collected by the environmental perception module, the spatial constraints of the unloading target area are determined. Specifically, this includes: extracting the contour features and spatial coordinates of the dump truck based on the multi-source fusion results of the 3D point cloud data and image information, and determining the effective unloading boundary of the dump truck's bucket; and determining the spatial coordinate range and geometric constraints of the unloading target area based on the effective unloading boundary of the bucket and the loader's operating safety distance requirements, thus obtaining the spatial constraint conditions.

[0165] Furthermore, based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device, the feasible solution space for unloading trajectory planning is determined. Specifically, this includes: establishing a two-way mapping relationship between the spatial pose of the loader's working device and the displacement of the hydraulic cylinder in the actuator module based on the kinematic model of the loader's working device; determining the unloading start pose constraint, end pose constraint, and full-process motion range constraint based on the spatial constraints, through the physical motion limits and anti-collision specifications of the loader's working device; and delineating the feasible solution space based on multi-dimensional constraints.

[0166] Furthermore, based on the dynamic programming algorithm and the feasible solution space, the stage cost function and terminal cost function of the unloading process are constructed to determine the globally optimal unloading trajectory. Specifically, this includes: determining the system state variables of the dynamic programming algorithm based on the displacement and velocity of the hydraulic cylinder in the actuator module; determining the control input variables of the dynamic programming algorithm based on the control input of the proportional servo valve; determining the stage cost function based on the single-stage trajectory tracking accuracy and control input smoothness; determining the terminal cost function based on the unloading terminal pose accuracy; and constructing an overall performance index function with the sum of the two as its core. Based on the Bellman recursive formula and the recursion of the overall performance index function, the solution is obtained by reverse recursion in the feasible solution space to determine the optimal control input sequence for each discrete decision stage, thereby generating the globally optimal unloading trajectory.

[0167] Furthermore, based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader's working device, the mathematical model of the electro-hydraulic servo system is determined, specifically including: determining the valve orifice flow equation of the proportional servo valve based on the structural parameters of the proportional servo valve and the physical properties of the hydraulic oil; determining the hydraulic cylinder flow continuity equation based on the structural parameters and leakage characteristics of the hydraulic cylinder in the actuator module; determining the hydraulic cylinder force balance equation based on the equivalent load, viscous damping, and driving force balance relationship of the hydraulic cylinder; and determining the mathematical model of the electro-hydraulic servo system based on the coupling relationship of the three equations.

[0168] Furthermore, based on the globally optimal unloading trajectory and the hydraulic cylinder extension / retraction data from the state acquisition module, displacement, velocity, and acceleration tracking errors are constructed, and a trajectory tracking error model is determined. Specifically, this includes: extracting the desired displacement, desired velocity, and desired acceleration of the hydraulic cylinder based on the globally optimal unloading trajectory; calculating the actual displacement, actual velocity, and actual acceleration of the hydraulic cylinder based on the hydraulic cylinder extension / retraction data acquired by the state acquisition module; and determining the displacement tracking error, velocity tracking error, and acceleration tracking error based on the difference between the desired parameters and the actual parameters, and then coupling them to construct a trajectory tracking error model.

[0169] Furthermore, based on the trajectory tracking error model, the nonlinear integral sliding surface function is determined, specifically including: introducing a nonlinear integral term with saturation characteristics based on the position tracking error and velocity tracking error in the trajectory tracking error model; setting the sliding surface parameters based on the error convergence speed requirements; and determining the nonlinear integral sliding surface function through the position tracking error, velocity tracking error, and nonlinear integral term.

[0170] Furthermore, the control instruction set is determined through equivalent control terms and switching control terms with chatter suppression. Specifically, this includes: based on the ideal sliding mode dynamic characteristics, setting the time derivative of the nonlinear integral sliding surface function to 0, and determining the equivalent control terms through the mathematical model of the electro-hydraulic servo system; based on the power-law approach, replacing the sign function with a continuous saturated function, and setting the boundary layer thickness according to chatter suppression requirements, determining the switching control terms with chatter suppression; and based on the superposition result of the equivalent control terms and the switching control terms, determining the real-time control input, and converting the real-time control input into an instruction format that matches the communication protocol of the vehicle control unit module to obtain the control instruction set.

[0171] Example 2: Figure 5 An exemplary embodiment of a loader's autonomous unloading device is shown, comprising:

[0172] The environmental perception module 210 is used to determine the spatial constraints of the unloading target area based on the three-dimensional point cloud data and image information of the unloading area collected by the environmental perception module.

[0173] The pose constraint module 220 is used to determine the feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader working device.

[0174] The trajectory planning module 230 is used to construct the stage cost function and terminal cost function of the unloading process based on the dynamic programming algorithm and the feasible solution space, and to determine the globally optimal unloading trajectory.

[0175] System modeling module 240 is used to determine the mathematical model of the electro-hydraulic servo system based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader working device.

[0176] The sliding mode control module 250 is used to construct displacement, velocity and acceleration tracking errors based on the global optimal unloading trajectory and the hydraulic cylinder extension and retraction data of the state acquisition module, determine the trajectory tracking error model, and determine the nonlinear integral sliding mode surface function based on the trajectory tracking error model.

[0177] The control instruction module 260 is used to determine the control instruction set based on the nonlinear integral sliding mode surface function, through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module.

[0178] Example 3

[0179] Figure 6 This is a structural block diagram of a terminal provided in an embodiment of this application. The terminal can be the terminal in the above embodiments. The terminal 300 can be a portable mobile terminal, such as a smartphone or tablet computer. The terminal 300 may also be referred to as user equipment, portable terminal, or other names.

[0180] Typically, terminal 300 includes a processor 301 and a memory 302.

[0181] Processor 301 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 301 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 301 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 301 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 301 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0182] The memory 302 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 302 are used to store at least one instruction, which is executed by the processor 301 to implement a loader autonomous unloading method provided in this application.

[0183] Example 4

[0184] In an exemplary embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements a loader autonomous unloading method as provided in all embodiments of the present application.

[0185] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0186] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0187] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0188] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0189] Example 5

[0190] In an exemplary embodiment, an application product is also provided, including one or more instructions that can be executed by the processor 301 of the aforementioned device to complete the aforementioned loader autonomous unloading method.

[0191] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. It can be applied to various fields suitable for the present invention. Other modifications can be readily made by those skilled in the art. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and examples shown and described herein.

Claims

1. A method for autonomous unloading of materials by a loader, characterized in that, The method is applied to a loader autonomous unloading system, which includes an environmental sensing module, a status acquisition module, a terminal, a vehicle control unit module, and an actuator module. The environmental sensing module, status acquisition module, and vehicle control unit module are electrically connected to the terminal, and the vehicle control unit module is electrically connected to the actuator module. The method includes: Based on the three-dimensional point cloud data and image information of the unloading area collected by the environmental perception module, the spatial constraints of the unloading target area are determined. Based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device, the feasible solution space for unloading trajectory planning is then determined. Based on the dynamic programming algorithm and the feasible solution space, the stage cost function and terminal cost function of the unloading process are constructed to determine the globally optimal unloading trajectory. Based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader working device, the mathematical model of the electro-hydraulic servo system is determined. Based on the global optimal unloading trajectory and the hydraulic cylinder extension and retraction data of the state acquisition module, displacement, velocity and acceleration tracking errors are constructed, a trajectory tracking error model is determined, and a nonlinear integral sliding surface function is determined based on the trajectory tracking error model. Based on the nonlinear integral sliding mode surface function, a control instruction set is determined through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module.

2. The loader autonomous unloading method according to claim 1, characterized in that, The spatial constraints of the unloading target area, determined based on the three-dimensional point cloud data and image information of the unloading area collected by the environmental perception module, specifically include: Based on the multi-source fusion results of the three-dimensional point cloud data and image information, the contour features and spatial coordinates of the dump truck are extracted to determine the effective unloading boundary of the dump truck's hopper. Based on the effective unloading boundary of the truck bed and the operating safety distance requirements of the loader, the spatial coordinate range and geometric constraints of the unloading target area are determined, and the spatial constraint conditions are obtained.

3. The loader autonomous unloading method according to claim 1, characterized in that, The determination of the feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader's working device specifically includes: Based on the kinematic model of the loader working device, a two-way mapping relationship between the spatial pose of the loader working device and the displacement of the hydraulic cylinder in the actuator module is established. Based on the aforementioned spatial constraints, the physical motion limits and anti-collision specifications of the loader's working device are used to determine the unloading start posture constraints, end posture constraints, and full-process motion range constraints. Based on these multi-dimensional constraints, the feasible solution space is delineated.

4. The loader autonomous unloading method according to claim 1, characterized in that, The process of constructing stage cost functions and terminal cost functions for the unloading process based on dynamic programming algorithm and feasible solution space, and determining the globally optimal unloading trajectory, specifically includes: Based on the displacement and velocity of the hydraulic cylinder in the actuator module, the system state variables of the dynamic programming algorithm are determined, and based on the control input of the proportional servo valve, the control input variables of the dynamic programming algorithm are determined. Based on the single-stage trajectory tracking accuracy and control input smoothness, the stage cost function is determined; based on the unloading terminal pose accuracy, the terminal cost function is determined; and an overall performance index function with the sum of the two as its core is constructed. Based on the Bellman recursive formula and the overall performance index function minimization objective, the optimal control input sequence for each discrete decision stage is determined by reverse recursion within the feasible solution space, thereby generating the globally optimal unloading trajectory.

5. The loader autonomous unloading method according to claim 1, characterized in that, The electro-hydraulic drive architecture based on the proportional servo valve-controlled hydraulic cylinder of the loader's working device determines the mathematical model of the electro-hydraulic servo system, specifically including: Based on the structural parameters of the proportional servo valve and the physical properties of the hydraulic oil, the valve orifice flow equation of the proportional servo valve is determined. Based on the structural parameters and leakage characteristics of the hydraulic cylinder in the actuator module, the hydraulic cylinder flow continuity equation is determined; Based on the equivalent load, viscous damping and driving force balance relationship of the hydraulic cylinder, the force balance equation of the hydraulic cylinder is determined. Based on the coupling relationship of the three equations, the mathematical model of the electro-hydraulic servo system is determined.

6. The loader autonomous unloading method according to claim 1, characterized in that, Based on the hydraulic cylinder extension and retraction data from the globally optimal unloading trajectory and the state acquisition module, a displacement, velocity, and acceleration tracking error model is constructed, and a trajectory tracking error model is determined, specifically including: Based on the globally optimal unloading trajectory, the desired displacement, desired velocity, and desired acceleration of the hydraulic cylinder are extracted; Based on the hydraulic cylinder extension and retraction data collected by the state acquisition module, the actual displacement, actual velocity, and actual acceleration of the hydraulic cylinder are calculated. Based on the difference between the expected parameters and the actual parameters, the displacement tracking error, velocity tracking error and acceleration tracking error are determined respectively, and the trajectory tracking error model is constructed by coupling them together.

7. The loader autonomous unloading method according to claim 1, characterized in that, The determination of the nonlinear integral sliding surface function based on the trajectory tracking error model specifically includes: Based on the position tracking error and velocity tracking error in the trajectory tracking error model, a nonlinear integral term with saturation characteristics is introduced; Based on the error convergence speed requirement, the sliding surface parameters are set, and the nonlinear integral sliding surface function is determined by the position tracking error, velocity tracking error, and nonlinear integral term.

8. The loader autonomous unloading method according to claim 1, characterized in that, The control instruction set is determined through equivalent control terms and switching control terms with chatter suppression, specifically including: Based on the ideal sliding mode dynamic characteristics, the time derivative of the nonlinear integral sliding surface function is set to 0, and the equivalent control term is determined through the mathematical model of the electro-hydraulic servo system. Based on the power-law approach, a continuous saturation function is used to replace the sign function, and the boundary layer thickness is set by the chattering suppression requirement to determine the switching control term with chattering suppression. Based on the superposition result of the equivalent control term and the switching control term, the real-time control input is determined, and the real-time control input is converted into an instruction format that matches the communication protocol of the vehicle control unit module to obtain the control instruction set.

9. A loader's autonomous unloading device, characterized in that, include: The environmental perception module is used to determine the spatial constraints of the unloading target area based on the three-dimensional point cloud data and image information of the unloading area collected by the environmental perception module. The pose constraint module is used to determine the feasible solution space for unloading trajectory planning based on the spatial constraints of the unloading target area and the kinematic model of the loader working device. The trajectory planning module is used to construct the stage cost function and terminal cost function of the unloading process based on the dynamic programming algorithm and the feasible solution space, and to determine the globally optimal unloading trajectory. The system modeling module is used to determine the mathematical model of the electro-hydraulic servo system based on the electro-hydraulic drive architecture of the proportional servo valve-controlled hydraulic cylinder of the loader working device. The sliding mode control module is used to construct displacement, velocity and acceleration tracking errors based on the global optimal unloading trajectory and the hydraulic cylinder extension and retraction data of the state acquisition module, determine the trajectory tracking error model, and determine the nonlinear integral sliding surface function based on the trajectory tracking error model. The control instruction module is used to determine a control instruction set based on the nonlinear integral sliding mode surface function, through equivalent control terms and switching control terms with chatter suppression. The control instruction set is used to control the vehicle control unit module to send the target execution drive signal to the actuator module.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When executed by the processor, the program instructions implement the steps of the loader autonomous unloading method according to any one of claims 1 to 8.

Images