Trajectory planning method and apparatus for operations of unmanned loader, and storage medium

Abstract

The present disclosure relates to a trajectory planning method and apparatus for operations of an unmanned loader, and a storage medium. The method comprises: acquiring the pose of a bucket tip of an unmanned loader, and on the basis of pose degree-of-freedom parameters of the bucket tip, describing a current pose and a target pose of the bucket tip; on the basis of the current pose and the target pose, planning a plurality of predicted trajectories of the bucket tip, wherein an operation time is discretized to obtain a plurality of target times, and for each target time, a pose change process of the bucket tip between an operation start time and the target time is segmented, a plurality of fitting modes are used to generate segmented trajectories, and the segmented trajectories are stitched to obtain the plurality of predicted trajectories; performing a validity check on each predicted trajectory to exclude invalid trajectories, in order to obtain valid trajectories; and performing adaptability evaluation on each valid trajectory, in order to output a valid trajectory having the lowest cost as a planned trajectory.

Description

Trajectory planning methods, devices, and storage media for unmanned loader operations

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202410818666.1, filed on June 21, 2024, entitled “Track planning method, apparatus and storage medium for unmanned loader operation”, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the fields of bulk earthwork engineering and intelligent driving technology, and specifically to an unmanned loader operation trajectory planning system and method. Background Technology

[0004] Loaders are the primary working equipment in bulk earthmoving scenarios, responsible for loading, unloading, and transferring materials. They are mainly used for shoveling and loading bulk materials such as soil, sand, gravel, lime, and coal. Loaders have the advantages of high operating speed and efficiency, which can greatly improve work efficiency and save labor costs. Loaders have good mobility and can operate flexibly in different working environments. They have a wide range of applications and can adapt to different working environments and needs.

[0005] Loaders are often used in harsh working conditions, which are highly dangerous, and manual operation of loaders is labor-intensive and inefficient. Unmanned loaders, on the other hand, can operate continuously 24 hours a day, eliminating the need for human labor, avoiding direct contact between personnel and hazardous environments, and can adapt to different working scenarios.

[0006] Summary of the Invention

[0007] This application proposes a trajectory planning method, system, and storage medium for unmanned loader operations.

[0008] According to a first aspect of the embodiments of this disclosure, a trajectory planning method for unmanned loader operations is provided, comprising: acquiring the pose of the bucket end of the unmanned loader, and describing the current pose and target pose of the bucket end based on the pose degree-of-freedom parameters of the bucket end; planning multiple predicted trajectories of the bucket end based on the current pose and target pose, wherein the operation time is discretized to obtain multiple target times, for each target time, the pose change process of the bucket end from the start time of the operation to the target time is segmented, and multiple fitting methods are used to generate segmented trajectories, and the segmented trajectories are spliced ​​together to obtain multiple predicted trajectories; performing a validity check on each predicted trajectory to exclude invalid trajectories, thereby obtaining valid trajectories; and performing an adaptive evaluation on each valid trajectory to output the valid trajectory with the lowest cost as the planned trajectory.

[0009] In some embodiments, the pose degree of freedom parameters include the height and tilt angle of the bucket end.

[0010] In some embodiments, the unmanned loader has a two-link structure, wherein the two links have a first length and a second length, and form a first joint and a second joint respectively relative to the origin of the unmanned loader, wherein the joint degree of freedom parameter of the first joint includes a first rotation angle, and the joint degree of freedom parameter of the second joint includes a second rotation angle.

[0011] In some embodiments, pose degree-of-freedom parameters are calculated based on a first length, a second length, a first rotation angle, and a second rotation angle.

[0012] In some embodiments, planning multiple predicted trajectories of the bucket end based on the current pose and the target pose further includes: for a first target time, time offsetting the operation start time and the first target time respectively, then segmenting the pose change process includes at least one of the following: a segment from the operation start time to the forward offset first target time, a segment from the forward offset first target time to the first target time; and a segment from the operation start time to the backward offset operation start time, a segment from the backward offset operation start time to the first target time.

[0013] In some embodiments, the fitting method used in the pose change process within the time offset is to keep the pose of the bucket end constant.

[0014] In some embodiments, the pose change process is fitted using a fifth-order polynomial in segments from the start time of the operation to the first target time of forward offset or in segments from the start time of the operation to the first target time of backward offset.

[0015] In some embodiments, the piecewise trajectory fitted by the fifth-order polynomial causes the bucket end to satisfy the following constraints: the height at the start of the operation is the height of the bucket end in the current pose; the height at the first target time is the height of the bucket end in the target pose; the velocity at the start of the operation is 0; the acceleration at the start of the operation is 0; the velocity at the first target time is 0; and the acceleration at the first target time is 0.

[0016] In some embodiments, the validity check for each predicted trajectory includes at least one of the following: checking whether the bucket end of the shovel collides with the ground in the pose corresponding to each predicted trajectory; and checking whether the target pose corresponding to each predicted trajectory is reachable from the bucket end.

[0017] In some embodiments, the validity check for each predicted trajectory includes inversely solving the first length and the second length based on the pose degree of freedom parameters of each predicted trajectory, in order to check whether the inversely solved first length and second length are within the valid range.

[0018] In some embodiments, adaptive evaluation of each valid trajectory includes: generating a set of data containing target time and pose degrees of freedom parameters for each valid trajectory; and calculating a combined cost of the set of data based on time weights and degree-of-freedom weights.

[0019] In some embodiments, adaptive evaluation of each valid trajectory further includes: calculating the stockpile inclination angle based on the inclined plane fitted to the working stockpile cross section; and calculating the adaptive cost of the data set relative to the stockpile inclination angle within a specified interval of the pose free end parameters.

[0020] In some embodiments, the sum of the combined cost and the adaptive cost is taken as the total trajectory cost, and the effective trajectory with the lowest total trajectory cost is selected as the output planned trajectory.

[0021] According to a second aspect of the embodiments of this disclosure, a trajectory planning device for unmanned loader operations is provided, comprising: a pose data acquisition unit configured to acquire the pose of the bucket end of the unmanned loader, and describe the current pose and target pose of the bucket end based on the pose degree-of-freedom parameters of the bucket end; a trajectory prediction unit configured to plan multiple predicted trajectories of the bucket end based on the current pose and the target pose, wherein the operation time is discretized to obtain multiple target times, for each target time, the pose change process of the bucket end from the start time of the operation to the target time is segmented, and multiple fitting methods are used to generate segmented trajectories, and the segmented trajectories are spliced ​​together to obtain multiple predicted trajectories; a trajectory validity check unit configured to perform a validity check on each predicted trajectory to exclude invalid trajectories, thereby obtaining valid trajectories; and a trajectory adaptability evaluation unit configured to perform an adaptability evaluation on each valid trajectory, and output the valid trajectory with the lowest cost as the planned trajectory.

[0022] According to a third aspect of the present disclosure, a trajectory planning device for unmanned loader operations is provided, comprising: a processor; and a memory storing computer-executable instructions, which, when executed by the processor, cause the processor to perform the trajectory planning method for unmanned loader operations according to a first aspect of the present disclosure.

[0023] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided storing computer-executable instructions that, when executed by a processor, cause the processor to implement the trajectory planning method for unmanned loader operations according to a first aspect of the present disclosure.

[0024] According to a fifth aspect of the present disclosure, a computer program product is provided, including computer program instructions that, when executed by a processor, implement the trajectory planning method for unmanned loader operations according to a first aspect of the present disclosure. Attached Figure Description

[0025] The foregoing and other features and advantages of this disclosure will become clear from the following description of embodiments illustrated in conjunction with the accompanying drawings. The drawings, incorporated herein and forming a part of the specification, are further used to explain the principles of this disclosure and to enable those skilled in the art to make and use it. Wherein:

[0026] Figure 1 shows a schematic diagram of the working mechanism of an unmanned loader according to an embodiment of the present disclosure;

[0027] Figure 2 shows a schematic block diagram of a trajectory planning device for unmanned loader operations according to an embodiment of the present disclosure;

[0028] Figures 3A to 3C illustrate schematic diagrams of degree-of-freedom parameter planning in a trajectory planning method for unmanned loader operations according to embodiments of the present disclosure;

[0029] Figure 4 shows a schematic diagram of trajectory adaptability evaluation in a trajectory planning method for unmanned loader operation according to an embodiment of the present disclosure;

[0030] Figure 5 shows a flowchart of a trajectory planning method for unmanned loader operations according to an embodiment of the present disclosure;

[0031] Figure 6 illustrates an exemplary configuration of a computing device that can implement embodiments of the present disclosure.

[0032] Note that in the embodiments described below, the same reference numerals are sometimes used across different figures to denote the same parts or parts with the same function, and repeated descriptions are omitted. In some cases, similar reference numerals and letters are used to denote similar items, so once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0033] For ease of understanding, the positions, dimensions, and extents of the structures shown in the accompanying drawings and other materials may not represent actual positions, dimensions, and extents. Therefore, this disclosure is not limited to the positions, dimensions, and extents disclosed in the accompanying drawings and other materials. Detailed Implementation

[0034] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0035] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the scope of this disclosure or its application or use. That is, the structures and methods herein are shown in an exemplary manner to illustrate different embodiments of the structures and methods in this disclosure. However, those skilled in the art will understand that they merely illustrate exemplary ways that can be used to implement this disclosure, and not exhaustive ways. Furthermore, the drawings are not necessarily drawn to scale, and some features may be enlarged to show details of specific components.

[0036] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0037] In bulk earthmoving projects, the quality of the unmanned loader's (UGC) loading trajectory directly affects loading efficiency and bucket fullness. Furthermore, irregular fluctuations in the material pile shape during operation also impact loading effectiveness. In summary, this disclosed technical solution addresses the problems of unreasonable loading trajectories, poor scalability of loading tasks under different process requirements, and poor environmental adaptability encountered during UGC loading operations. It proposes an adaptive loading trajectory planning device and method for UGCs. Specifically, through joint data acquisition, combined trajectory planning, trajectory validity checking, and trajectory adaptability evaluation, trajectory calculation between arbitrary poses within the feasible space is achieved. Adaptive adjustments are made based on process requirements and material pile shape, thereby improving the UGC's scenario adaptability and loading efficiency.

[0038] The trajectory planning method and apparatus for unmanned loader operations according to various embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It will be understood that actual trajectory planning methods for unmanned loader operations may include other steps, but to avoid obscuring the essential points of the present disclosure, these other steps will not be discussed herein, and the accompanying drawings do not show them. Furthermore, for reference only, terms such as "first," "second," "third," "fourth," etc., as used herein, are used to distinguish multiple subjects and are not intended to be limiting. For example, unless the context clearly indicates otherwise, the words "first," "second," "third," "fourth," and other such numerical terms relating to structures or elements do not imply order or sequence.

[0039] Referring first to Figure 1, which shows a schematic diagram of the working mechanism of an unmanned loader according to an embodiment of the present disclosure. Generally, the operation of an unmanned loader requires real-time monitoring of the pose of the bucket end, and the pose state can be described using the degree of freedom parameters of the bucket end. Common unmanned loaders have a two-link structure, and their working mechanism is shown in Figure 1. The rocker arm and boom are simplified to links 1010 and 1020, respectively, whose movement is controlled by the rocker arm drive rod 110 and the boom drive rod 120, and the bucket 113 is mounted on the link 1020. Thus, the links 1010 and 1020 form two joints relative to the origin of the unmanned loader that affect the pose of the bucket end O2, denoted as the first joint O0 and the second joint O1. The first joint O0 rotates in the plane (x0, y0), and the second joint O1 rotates in the plane (x1, y1), and the angle of rotation is described using the joint degree of freedom parameters. Specifically, let the lengths of connecting rods 1010 and 1020 be the first length a1 and the second length a2, respectively; let the joint degree-of-freedom parameters of the first joint O0 and the second joint O1 be the first rotation angle θ1 and the second rotation angle θ2, respectively; and let the pose degree-of-freedom parameters of the bucket end O2 include its height y and tilt angle θ; then the transformation model between the pose of the bucket end O2 and the parameters of the two joints satisfies the following formula (1):

[0040] The inverse solution of the model is given by the following formula (2):

[0041] In one non-limiting embodiment, the unmanned loader is equipped with joint sensors at various joints (such as the first joint O0 and the second joint O1), and the rotation angles of each joint (such as the first rotation angle θ1 and the second rotation angle θ2) are obtained by the joint sensors. For the start time t of the current operation... start and end time t end In other words, the current pose (y) can be obtained based on formula (1). start ,θ start ) and target pose (y end ,θ end The trajectory planning method of the embodiments of this disclosure provides how to plan the motion trajectory of the bucket end from the current pose to the target pose.

[0042] Next, please refer to Figure 2, which shows a schematic block diagram of a trajectory planning device for unmanned loader operations according to an embodiment of the present disclosure.

[0043] In some embodiments, the trajectory planning method for unmanned loader operations can be implemented by a trajectory planning device 2000, which may include a processor 2100. The processor 2100 of the device 2000 can provide various functions of the trajectory planning device 2000. A processor can refer to various implementations of digital circuit systems, analog circuit systems, or mixed-signal (analog and digital combination) circuit systems that perform functions in a computing system. Processing circuitry may include circuitry such as integrated circuits (ICs), application-specific integrated circuits (ASICs), portions or circuitry of a single processor core, an entire processor core, a single processor, programmable hardware devices such as field-programmable gate arrays (FPGAs), and / or systems comprising multiple processors.

[0044] In some embodiments, the trajectory planning device 2000 for unmanned loader operations may further include a memory (not shown). The memory of the device 2000 may store information generated by the processor 2100, as well as programs and data for processor operation. The memory may be volatile memory and / or non-volatile memory. For example, the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Generally, the processor may be configured to execute instructions stored in the memory to implement the trajectory planning method for unmanned loader operations as described above.

[0045] Specifically, as shown in FIG2, in some embodiments, the trajectory planning device 2000 for unmanned loader operations according to embodiments of the present disclosure may include a pose data acquisition unit 2010, a trajectory prediction unit 2020, a trajectory validity check unit 2030, and a trajectory adaptability evaluation unit 2040. It should be understood that the various functional units of the trajectory planning device for unmanned loader operations shown in FIG2 are merely logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. In actual implementation, the above modules may be implemented as independent physical entities, or may be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.).

[0046] In some embodiments, the pose data acquisition unit 2010 is configured to acquire the pose of the bucket end-effector O2 of the unmanned loader, and describe the current pose (y, θ) of the bucket end-effector O2 based on the pose degree-of-freedom parameters (y, θ) of the bucket end-effector O2. start ,θ start ) and target pose (y end ,θ endAs shown in Figure 1 and Formula (1), the position of the bucket end O2 can be obtained based on the lengths a1 and a2 of the connecting rods and the measured values ​​θ1 and θ2 of the joint rotation angles.

[0047] In some embodiments, the trajectory prediction unit 2020 is configured to plan multiple predicted trajectories for the bucket end face based on the current pose and the target pose. Referring to Figures 3A and 3B, which illustrate several results of pose degree-of-freedom parameters when planning the trajectory between the current pose and the target pose, Figure 3A shows the results from the start time t. start Figure 3B shows the curves of the change of the tilt angle θ between the two end times t0 and t1, respectively. start The curves showing the change in height y between the two end times t0 and t1.

[0048] Specifically, the trajectory prediction unit 2020 first discretizes the operation time to obtain multiple target times, such as the start time t of the current operation. start and end time t end Subdivided into n target times t i ={t0,t1,…t n-1}. Subsequently, for each target time t i The bucket end will be at the start time t of the operation. start To the target time t i The pose change process is segmented, and various fitting methods are used to generate segmented trajectories. The fitting can be linear or nonlinear regression, and the function used includes, but is not limited to, polynomial, exponential, or other possible curve functions. Then, these segmented trajectories are stitched together to obtain multiple predicted trajectories.

[0049] In some embodiments, the trajectory prediction unit 2020 segments the bucket end pose change process, including the starting time t. start To the target time t i The time intervals are divided into segments. Taking a fixed value i as an example, for the first target time t... i For the starting time t, respectively start and the first target time t i Perform a time offset. As shown in Figure 3C, the time offset includes adjusting the starting time t. start Shift backward by Δt, and set the first target time t. i Shift forward by Δt. Therefore, for the entire time interval t... start →t i The segmentation method may include at least one of the following: from the start time of the task to the first target time t to be shifted forward. start →t i -Δt and the time from the first target time to the first target time t (shifted forward) i-Δt→t i ; and the shift from the start time of the task to the start time t of the task shifted backward. start →t start +Δt and the time from the start of the backward shifted task to the first target time t start +Δt→t i Based on this, the pose change process of the bucket end within each time segment is fitted, that is, the pose degree of freedom parameters are planned, thereby obtaining (t start ,θ start )→(t i ,θ etd ) and (t start ,y start )→(t i ,y end (Multiple predicted trajectories)

[0050] In the planning of the predicted trajectory, the fitting method used for the pose change process within the time offset can be such that the pose of the bucket end remains unchanged. That is, in a non-limiting embodiment, t i -Δt→t i within and / or and t start →t start Within +Δt and / or Furthermore, the fitting method used for the portion of the pose change process outside the time offset can be a fifth-order polynomial. That is, in another non-limiting embodiment, t start →t i -Δt and t start +Δt→t i The pose degree of freedom parameters can be expressed as a curve as shown in formula (3):

[0051] x(t) = a0 + a1t + a2t 2 +a3t 3 +a4t 4 ……(3)

[0052] Furthermore, constraints are added to ensure that the segmented trajectory satisfies the following condition: the bucket end point at the start time t of the operation. start pose degree of freedom parameter x(t) start ) represents the pose degree of freedom parameter x of the bucket end cap in the current pose. start ; at the first target time t i pose degree of freedom parameter x(t) i ) represents the pose degree of freedom parameter x of the bucket end in the target pose. end At the start time t of the task startThe speed is 0; at the start time t of the operation start The acceleration is 0; at the first target time t i The velocity is 0; and at the first target time t i The acceleration is 0. That is, the constraint is embodied in the following formula (4):

[0053] Furthermore, by stitching together the two fitted segmented trajectories mentioned above, the pose change process at time t can be obtained. start →t i The complete predicted trajectory within. Figure 3C shows the pair of t curves as a reference curve. start →t i The curve x is obtained by directly fitting a fifth-order polynomial. i0 , and for t start →t i The predicted trajectory x is the combination of the curve fitted by a fifth-order polynomial at time offset Δt and the straight line within the time offset Δt. i1 and against t start +Δt→t i The predicted trajectory x is the combination of the curve fitted by a fifth-order polynomial and the straight line within the time offset Δt. i2 Additionally, the first target time t i of (t) i ,θ) and (t i By further combining pairs of y, we can obtain the corresponding time t. i of (t) i The trajectory of ,y,θ).

[0054] In some embodiments, the trajectory validity checking unit 2030 is configured to perform a validity check on each predicted trajectory to exclude invalid trajectories, thereby obtaining valid trajectories. Specifically, checking the aforementioned generated trajectories includes at least one of the following: traversing each trajectory and checking whether the bucket end of each predicted trajectory collides with the ground in the corresponding pose (collision check); and traversing each trajectory and checking whether the target pose corresponding to each predicted trajectory is reachable from the bucket end (reachability check).

[0055] Specifically, non-restrictive implementations of collision checking include those based on the obtained (t) iThe trajectory of the bucket end is determined to be invalid if the predicted trajectory contains a point with a height of y = 0. Reachability checks are often used when the motion trajectory of the bucket end is affected by the motion of multiple joints (such as the two-link structure shown in Figure 1). The trajectory planning of the bucket end is limited by factors such as the joint degrees of freedom and / or size of each joint. For the two-link mechanism in Figure 1, one non-limiting implementation is to inversely solve the values ​​of the first and second rotation angles according to formula (2) based on the pose degree of freedom parameters of each predicted trajectory, and then obtain the first and second lengths of the link to check whether the inversely solved first and second lengths are within the valid range, such as whether they meet the length limits of the two links; and / or check whether the inversely solved first and second rotation angles meet the rotation limits at the two joints. Alternatively, another non-limiting implementation is to calculate the reachable pose range of the bucket end based on the length limits of a1 and a2 and the rotation limits of θ1 and θ2, thereby determining that the predicted trajectory containing pose degree of freedom parameters exceeding the reachable pose range is invalid.

[0056] In some embodiments, the trajectory adaptability evaluation unit 2040 is configured to perform an adaptive evaluation on each valid trajectory and output the valid trajectory with the lowest cost as the planned trajectory. Specifically, after the trajectory validity check unit 2030 performs a validity constraint check on the predicted trajectory planned by the trajectory prediction unit 2020, the selected valid trajectories generate the target time t for each valid trajectory. i有效 Data set with pose degree of freedom parameters (t) i有效 ,y,θ), and set the adaptive evaluation rules for this data set.

[0057] In a non-limiting embodiment, the trajectory adaptability evaluation unit 2040 calculates the combined cost of the data set based on time weight and degree of freedom weight. That is, the adaptability evaluation rules include at least the principle of minimum time consumption, the principle of minimum trajectory velocity, and the principle of minimum acceleration, each corresponding to a weight w. t w v and w a Then the combined cost comb It can be expressed as follows: (5)

[0058] That is, according to the time weight w t With the weights of the degrees of freedom w v and w a Calculate the data set (t) corresponding to each valid trajectory. i有效 The combined cost of y,θ) combThe minimum value is taken to determine the effective trajectory with the lowest cost. The trajectory can comprehensively achieve the effects of the shortest operation time and the smallest trajectory velocity and acceleration of the positional freedom. In other words, it is mainly used to evaluate whether the trajectory makes the bucket end move as smoothly as possible while controlling the operation time.

[0059] Furthermore, it is necessary to examine the adaptation relationship between the movement trajectory of the bucket end and the working stockpile. Specifically, the trajectory adaptation assessment unit 2040 is configured to calculate the stockpile inclination angle based on the inclined plane fitted to the working stockpile cross-section; and to calculate the adaptation cost of the aforementioned effective trajectory data set relative to the stockpile inclination angle within a specified interval of the pose free end parameters.

[0060] Please refer to Figure 4, which illustrates a schematic diagram of trajectory adaptability evaluation in a trajectory planning method for unmanned loader operations according to an embodiment of the present disclosure. The fitting slope 420 is obtained by fitting the material pile cross-section 410, and the material pile inclination angle θ between the material pile cross-section 410 and the ground 400 is calculated accordingly. ref Therefore, the aforementioned effective trajectory is evaluated based on the shape of the material pile. In a non-limiting embodiment, according to the requirements of the loading process, the lifting height range corresponding to the bucket angle being maintained during the loading operation can be defined, described by the pose degree of freedom parameter y and denoted as the specified range [y0, y1]. At this time, the trajectory (t) is traversed. i有效 Given y, θ), calculate the adaptive cost for trajectory points within the interval [y0, y1]. When the cost weight is set to w... Δθ At that time, the cost of adaptation adapt It can be expressed as follows: (6)

[0061] That is, within the specified interval [y0, y1] of the pose degree of freedom parameters, the data set (t) corresponding to each valid trajectory is calculated. i有效 The adaptation cost of (y,θ) adapt By taking the minimum value, the effective trajectory with the lowest cost is determined. This trajectory can achieve the effect of making the inclination angle of the bucket end movement trajectory as close as possible to the inclination angle of the material pile while meeting the requirements of the loading process.

[0062] Furthermore, the trajectory adaptation evaluation unit 2040 uses the sum of the combined cost and the adaptation cost as the total trajectory cost, and selects the effective trajectory with the lowest total trajectory cost as the output planned trajectory. That is, the final trajectory cost is... final It can be expressed as follows: (7)

[0063] cost final =cost comb +cost adapt ……(7)

[0064] Based on the calculation results, the total cost of the trajectory is sorted, and the trajectory with the lowest cost is selected as the output planned trajectory. That is, the trajectory that will not cause collisions, is reachable at all points, makes the loading operation smooth and stable, and is adapted to the shape of the material pile is selected from multiple predicted trajectories.

[0065] Additionally, the trajectory planning device 2000 for unmanned loader operations can also have built-in or external input and output units (not shown in the figures). The input unit may include devices for users or administrators to input various data or instructions, such as buttons, touchpads, keyboards, microphones, switches, and other devices capable of receiving input via methods such as sound and motion. Furthermore, for example, the input unit may be a remote control device with infrared light or other radio waves, or a mobile device suitable for operation of the trajectory planning device 2000. Based on, for example, data or instructions input by the user, the input unit generates input signals and supplies these signals to other functional units within the trajectory planning device 2000.

[0066] The output unit includes devices capable of outputting visual or auditory information to users or administrators of the trajectory planning device 2000. For example, the output unit includes a display screen, speaker, buzzer, projector, lamp, etc. The display device included in the output unit can be a device with a conventional display, or a device that displays visual information to other systems. Based on this, the trajectory planning device 2000 can display pose calculation results and various generated trajectory data as visual information such as graphic data or auditory information such as voice prompts, so that users or administrators can obtain relevant information or adjust their operations accordingly.

[0067] Next, please refer to Figure 5, which shows a flowchart of a trajectory planning method 5000 for unmanned loader operations according to an embodiment of the present disclosure. In step S501, the pose of the bucket end effector of the unmanned loader is obtained, and the current pose and target pose of the bucket end effector are described based on the pose degree-of-freedom parameters of the bucket end effector. In step S502, multiple predicted trajectories of the bucket end effector are planned based on the current pose and target pose. Specifically, planning the predicted trajectory may include discretizing the operation time to obtain multiple target times; for each target time, segmenting the pose change process of the bucket end effector from the start time of the operation to that target time, and using multiple fitting methods to generate segmented trajectories; and stitching the segmented trajectories together to obtain multiple predicted trajectories. Next, in step S503, each predicted trajectory is checked for validity to eliminate invalid trajectories, thereby obtaining valid trajectories. In step S504, each valid trajectory is evaluated for adaptability, and the valid trajectory with the lowest cost is output as the planned trajectory.

[0068] It should be understood that the division of the steps in Figure 5 is for illustrative purposes only and not for limiting the embodiments of this application. These steps can be completed individually by the entities shown in the figure, by two or more entities working together, or by an external system (not shown) cooperating with the entities shown in the figure. They are not limited to the allocation method shown in the figure. They can be completed sequentially according to the order shown in the figure or in parallel if they conform to the data flow direction and system operation rules. They can be completed step by step or in combination.

[0069] This disclosure also provides a trajectory planning device for unmanned loader operations, which may include a processor and a memory storing computer-executable instructions that, when executed by the processor, cause the processor to perform a trajectory planning method for unmanned loader operations according to any of the foregoing embodiments of this disclosure. The processor may be a central processing unit (CPU) of the trajectory planning device, which may be any type of general-purpose processor, or it may be a processor specifically designed for trajectory planning in unmanned loader operations, such as an application-specific integrated circuit (“ASIC”). The memory may include various computer-readable media accessible by the processor.

[0070] This disclosure also provides a non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by a processor, cause the processor to implement the trajectory planning method for unmanned loader operations according to any of the foregoing embodiments of this disclosure.

[0071] This disclosure also provides a computer program product including computer-executable instructions that, when executed by a processor, cause the processor to implement the trajectory planning method for unmanned loader operations according to any of the foregoing embodiments of this disclosure.

[0072] Figure 6 illustrates an exemplary configuration of a computing device that can implement embodiments of the present disclosure. The computing device includes one or more processors 601, an input / output interface 605 connected to the processors 601 via a bus 604, and memories 602 and 603 connected to the bus 604. In some embodiments, memory 602 may be read-only memory (ROM), and memory 603 may be random access memory (RAM).

[0073] Processor 601 can be any type of processor and may include, but is not limited to, one or more general-purpose processors or special-purpose processors (such as dedicated processing chips). Memory 602 and 603 can be any non-transitory storage device capable of storing data and may include, but is not limited to, disk drives, optical storage devices, solid-state storage, floppy disks, flexible disks, hard disks, magnetic tapes or any other magnetic media, compressed disks or any other optical media, cache memory and / or any other storage chip or module, and / or any other medium from which a computer can read data, instructions and / or code.

[0074] Bus 604 may include, but is not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0075] In some embodiments, the input / output interface 605 is connected to the following units: an input unit 606 configured with input devices such as a keyboard and mouse for user input of operation commands; an output unit 607 that outputs images of the processing operation screen and processing results to a display device; a storage unit 608 including a hard disk drive for storing programs and various data; and a communication unit 609 including a local area network (LAN) adapter and performing communication processing via a network such as the Internet. Additionally, a drive 610 is connected, which reads data from and writes data to the removable storage medium 611.

[0076] The various aspects, implementations, specific implementations, or features of the foregoing embodiments may be used individually or in any combination. The various aspects of the foregoing embodiments may be implemented by software, hardware, or a combination of hardware and software.

[0077] For example, the aforementioned embodiments can be embodied in computer-readable code on a computer-readable medium. A computer-readable medium is any data storage device capable of storing data that can subsequently be read by a computer system. Examples of computer-readable media include read-only memory, random access memory, CD-ROM, DVD, magnetic tape, hard disk drive, solid-state drive, and optical data storage devices. Computer-readable media can also be distributed across network-coupled computer systems, allowing the computer-readable code to be stored and executed in a distributed manner.

[0078] For example, the aforementioned implementation scheme can take the form of hardware circuits. Hardware circuits can include any combination of combinational logic circuits, clock storage devices (such as floppy disks, flip-flops, latches, etc.), finite state machines, memories such as static random access memory or embedded dynamic random access memory, custom-designed circuits, programmable logic arrays, etc.

[0079] In one implementation, the hardware circuit according to this disclosure can be implemented by coding and designing one or more integrated circuits or by combining discrete circuits using a hardware description language (HDL) such as Verilog or VHDL.

[0080] In summary, the advantages of the embodiments according to this disclosure are that by directly planning the trajectory of the bucket angle and lifting height, different loading process requirements can be adapted; by discretizing the time and planning the target degrees of freedom separately, the working trajectory between any pose in the feasible space can be obtained; and by adapting the material pile shape and adaptively evaluating the trajectory, different material pile shapes can be adapted to obtain the optimal loading effect.

[0081] It should be recognized that the above advantages do not need to be concentrated in one or a few specific embodiments, but can be partially distributed in different embodiments according to this disclosure. Embodiments according to this disclosure may have one or some of the above advantages, or alternatively or additionally have other advantages.

[0082] The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to limit the scope of this disclosure. Unless the context explicitly indicates otherwise, the singular forms “a” and “the” as used herein are intended to include the plural forms as well. It should also be understood that the word “comprising”, as used herein, indicates the presence of the indicated feature, integral, step, operation, unit, and / or component, but does not preclude the presence or addition of one or more other features, integrals, steps, operations, units, and / or components, and / or combinations thereof. Furthermore, in the description of this disclosure, the terms “first,” “second,” etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or order. Additionally, in the description of this disclosure, unless otherwise stated, “a plurality of” means two or more.

[0083] In this specification, references to "embodiment" or similar expressions mean that a specific feature, structure, or characteristic described in connection with that embodiment is included in at least one specific embodiment of this disclosure. Therefore, the use of phrases such as "in an embodiment of this disclosure" and similar expressions in this specification does not necessarily refer to the same embodiment.

[0084] Those skilled in the art will understand that this disclosure can be implemented in various forms, such as a completely hardware embodiment, a completely software embodiment (including firmware, resident software, microprogram code, etc.), or a software and hardware embodiment, hereinafter referred to as a "circuit," "module," "unit," or "system." Furthermore, this disclosure can also be implemented in any tangible media as a computer program product having computer-usable program code stored thereon.

[0085] The description herein is based on flowcharts and / or block diagrams of systems, apparatuses, methods, and computer program products according to specific embodiments of this disclosure. It will be understood that each block in each flowchart and / or block diagram, and any combination of blocks in the flowcharts and / or block diagrams, can be implemented using computer program instructions. These computer program instructions are executable by a machine comprising a processor of a general-purpose computer or a special-purpose computer, or other programmable data processing means, and are processed by the computer or other programmable data processing means to perform the functions or operations described in the flowcharts and / or block diagrams.

[0086] The accompanying drawings illustrate flowcharts and block diagrams showing the architecture, functionality, and operation of systems, apparatuses, methods, and computer program products achievable according to various embodiments of the present disclosure. Thus, each block in a flowchart or block diagram may represent a module, segment, or portion of program code, including one or more executable instructions to implement a specified logical function. It should also be noted that in some other embodiments, the functions described in a block may not be performed in the order shown in the figures. For example, two blocks illustrated as connected may actually be executed simultaneously, or in some cases, depending on the functions involved, they may be executed in the reverse order shown in the figures. Furthermore, it should be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, may be implemented by a system based on dedicated hardware, or by a combination of dedicated hardware and computer instructions, to perform specific functions or operations.

[0087] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to market technology of the embodiments, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A trajectory planning method for unmanned loader operations, comprising: The pose of the bucket end of the unmanned loader is obtained, and the current pose and target pose of the bucket end are described based on the pose degree of freedom parameters of the bucket end. Based on the current pose and the target pose, multiple predicted trajectories for the bucket end are planned, wherein... Discretize the task time to obtain multiple target times. For each target time, the pose change process of the bucket end cap from the start time of the operation to that target time is segmented, and multiple fitting methods are used to generate segmented trajectories. The segmented trajectories are spliced ​​together to obtain multiple predicted trajectories; Each predicted trajectory is checked for validity to eliminate invalid trajectories, thereby obtaining valid trajectories; as well as Each valid trajectory is adaptively evaluated, and the trajectory with the lowest output cost is selected as the planned trajectory.

2. The trajectory planning method according to claim 1, wherein: The pose freedom parameters include the height and tilt angle of the bucket end.

3. The trajectory planning method according to claim 2, wherein: The unmanned loader has a two-link structure, wherein the two links have a first length and a second length respectively, and form a first joint and a second joint respectively relative to the origin of the unmanned loader. The joint degree of freedom parameters of the first joint include a first rotation angle, and the joint degree of freedom parameters of the second joint include a second rotation angle.

4. The trajectory planning method according to claim 3, wherein: The first and second turning angles are obtained by the joint sensors of the unmanned loader.

5. The trajectory planning method according to claim 3 or 4, wherein: The pose degree of freedom parameters are calculated based on the first length, the second length, the first rotation angle, and the second rotation angle.

6. The trajectory planning method according to claim 1, wherein, The method of planning multiple predicted trajectories of the bucket end based on the current pose and the target pose also includes: For the first target time, by applying time offsets to both the operation start time and the first target time, the pose change process can be segmented into at least one of the following: The segmentation from the start time of the task to the first target time forward, and from the first target time forward to the first target time; and The segments are defined as follows: from the start time of the task to the start time of the task shifted backward, and from the start time of the task shifted backward to the first target time.

7. The trajectory planning method according to claim 6, wherein, The pose change process within the time offset uses a fitting method that keeps the pose of the bucket end constant.

8. The trajectory planning method according to claim 6 or 7, wherein, The pose change process uses a fifth-order polynomial for the segment from the start time of the operation to the first target time of forward shift or the segment from the start time of the operation to the first target time of backward shift.

9. The trajectory planning method according to claim 8, wherein, The piecewise trajectory fitted by the fifth-order polynomial ensures that the bucket end satisfies the following constraints: The pose degree of freedom parameters at the start time of the operation are the pose degree of freedom parameters of the bucket end in the current pose; The pose degree of freedom parameters at the first target time are the pose degree of freedom parameters of the bucket end at the target pose; The speed at the start of the operation is 0; The acceleration is 0 at the start of the operation; The velocity at the first target time is 0; and The acceleration is 0 at the first target time.

10. The trajectory planning method according to claim 1, wherein, The validity check for each predicted trajectory includes at least one of the following: Check whether the bucket end collides with the ground in the pose corresponding to each predicted trajectory; and Check whether the target pose corresponding to each predicted trajectory is reachable from the bucket end.

11. The trajectory method according to claim 5, wherein, The validity check for each predicted trajectory includes inversely solving the first and second lengths based on the pose degree-of-freedom parameters of each predicted trajectory, to check whether the inversely solved first and second lengths are within the valid range.

12. The trajectory method according to claim 1, wherein, The adaptive evaluation of each valid trajectory includes: Generate a data set of target time and pose degrees of freedom parameters for each valid trajectory; and The combined cost of the data set is calculated based on the time weight and the degree of freedom weight.

13. The trajectory method according to claim 12, wherein, The adaptive evaluation of each valid trajectory also includes: The inclination angle of the stockpile is calculated based on the inclined plane fitted to the cross-section of the stockpile; and Calculate the adaptive cost of the data set relative to the pile tilt angle within a specified range of the pose free end parameters.

14. The trajectory method according to claim 13, wherein, The sum of the combined cost and the adaptive cost is taken as the total trajectory cost, and the effective trajectory with the lowest total trajectory cost is selected as the output planned trajectory.

15. A trajectory planning device for unmanned loader operations, comprising: The pose data acquisition unit is configured to acquire the pose of the bucket end of the unmanned loader, and describe the current pose and target pose of the bucket end based on the pose degree of freedom parameters of the bucket end. The trajectory prediction unit is configured to plan multiple predicted trajectories for the bucket end face based on the current pose and the target pose, wherein... Discretize the task time to obtain multiple target times. For each target time, the pose change process of the bucket end cap from the start time of the operation to that target time is segmented, and multiple fitting methods are used to generate segmented trajectories. The segmented trajectories are spliced ​​together to obtain multiple predicted trajectories; The trajectory validity check unit is configured to perform a validity check on each predicted trajectory to exclude invalid trajectories, thereby obtaining valid trajectories; as well as The trajectory adaptation evaluation unit is configured to perform an adaptation evaluation on each valid trajectory and output the valid trajectory with the lowest cost as the planned trajectory.

16. The trajectory planning apparatus according to claim 15, wherein the trajectory prediction unit is further configured to: For the first target time, time offsets are applied to both the operation start time and the first target time, thereby segmenting the pose change process in at least one of the following ways: The segmentation from the start time of the task to the first target time forward, and from the first target time forward to the first target time; and The segments are defined as follows: from the start time of the task to the start time of the task shifted backward, and from the start time of the task shifted backward to the first target time.

17. The trajectory planning apparatus according to claim 15, wherein the trajectory adaptability evaluation unit is further configured to: Generate a data set of target time and pose degree of freedom parameters for each valid trajectory, and calculate the combined cost of the data set based on time weight and degree of freedom weight; The inclination angle of the stockpile is calculated based on the inclined plane fitted to the cross-section of the working stockpile, and the adaptive cost of the data set relative to the inclination angle of the stockpile is calculated within a specified interval of the free end parameters of the pose; and The sum of the combined cost and the adaptive cost is taken as the total trajectory cost, and the effective trajectory with the lowest total trajectory cost is selected as the output planned trajectory.

18. A trajectory planning device for unmanned loader operations, comprising: processor; as well as A memory storing computer-executable instructions, which, when executed by the processor, cause the processor to perform the trajectory planning method for unmanned loader operations according to any one of claims 1 to 14.

19. A non-transitory computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, cause the processor to implement the trajectory planning method for unmanned loader operations as described in any one of claims 1 to 14.

20. A computer program product comprising computer-executable instructions that, when executed by a processor, cause the processor to implement the trajectory planning method for unmanned loader operations as described in any one of claims 1 to 14.

Images