Industrial robot path planning method and system based on adaptive control

Abstract

The invention discloses an industrial robot path planning method and system based on adaptive control, and the method comprises the steps: obtaining a work task of an industrial robot, and determining a plurality of intersection nodes according to a task starting point and a task terminal point; determining a working path by applying a path planning algorithm according to the plurality of intersection nodes; executing a working task according to the working path, and performing real-time sampling in the advancing process to obtain sampling data; performing operation according to the sampling data to generate a local path between every two intersection nodes; and executing the work task according to the work path and the local path. After the global working path is obtained through the optimal path algorithm, the road condition of the local path in the advancing process of the industrial robot is determined through real-time sampling of the local path, then the optimal solution of the local path is planned according to the sampling data, self-adaptive control over the path of the industrial robot is achieved, the advancing path can be updated in real time in combination with the real-time road condition, and the working efficiency is improved. Therefore, the industrial robot has good obstacle avoidance performance and can better complete work tasks.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to an industrial robot path planning method and system based on adaptive control. Background Technology

[0002] Current path planning methods for industrial robots first calculate the coordinates of obstacles relative to the industrial robot, then use inverse kinematics to determine the angles of each axis of the industrial robot, and finally plan the rotation of the industrial robot axes through function interpolation. This method requires multiple calculations and multiple planning steps, which is inefficient. Moreover, this method cannot accurately identify the current road conditions. Cloud-based computing algorithms based on historical road conditions cannot accurately identify obstacles that may appear in the current road conditions, resulting in low accuracy. Summary of the Invention

[0003] In view of the above problems, the present invention is proposed to provide an industrial robot path planning method and system based on adaptive control that overcomes or at least partially solves the above problems.

[0004] According to one aspect of the present invention, an industrial robot path planning method based on adaptive control is provided, comprising:

[0005] Obtain the work task of the industrial robot, and determine the task start and end point based on the work task;

[0006] Multiple intersection nodes are determined based on the task start point and the task end point;

[0007] The working path is determined based on the path planning algorithm applied to the multiple intersection nodes;

[0008] The work task is executed according to the work path. During the process, the path between every two intersection nodes is sampled in real time to obtain sampled data.

[0009] The sampled data is input into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes.

[0010] The work task is executed based on the work path and the local path.

[0011] According to another aspect of the present invention, an industrial robot path planning system based on adaptive control is provided, comprising:

[0012] The work path determination module is used to acquire the work task of the industrial robot, determine the task start point and task end point based on the work task, determine multiple intersection nodes based on the task start point and task end point, and determine the work path by applying a path planning algorithm based on the multiple intersection nodes.

[0013] The local path determination module is used to execute the work task according to the work path. During the journey, it performs real-time sampling of the path between every two intersection nodes to obtain sampling data; the sampling data is input into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes.

[0014] The task processing module is used to execute the work task based on the work path and the local path.

[0015] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0016] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described adaptive control-based industrial robot path planning method.

[0017] According to another aspect of the present invention, a computer storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described adaptive control-based industrial robot path planning method.

[0018] According to the present invention, an industrial robot path planning method and system based on adaptive control is proposed. The method involves acquiring the industrial robot's work task, determining the task start and end points based on the task, identifying multiple intersection nodes based on the task start and end points, applying a path planning algorithm to determine the work path based on the multiple intersection nodes, executing the work task according to the work path, and during the movement, sampling data is obtained in real time for the path between every two intersection nodes. The sampled data is then input into a pre-set local path optimization algorithm to generate local paths between every two intersection nodes. Finally, the work task is executed based on the work path and the local paths. This invention obtains the global work path through an optimal path algorithm, determines the local path conditions during the industrial robot's movement through real-time sampling of local paths, and then plans the optimal solution for the local path based on the sampled data. This achieves adaptive control of the industrial robot's path and can update the movement path in real time based on real-time road conditions, enabling the industrial robot to have good obstacle avoidance performance and better complete its work tasks.

[0019] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0021] Figure 1 A flowchart of an industrial robot path planning method based on adaptive control provided by an embodiment of the present invention is shown.

[0022] Figure 2 A schematic diagram of the structure of an industrial robot path planning system based on adaptive control provided by an embodiment of the present invention is shown.

[0023] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0024] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0025] Figure 1 A flowchart illustrating an embodiment of an industrial robot path planning method based on adaptive control according to the present invention is shown, as follows: Figure 1 As shown, the method includes the following steps:

[0026] Step S101: Obtain the industrial robot's work task, determine the task start point and task end point based on the work task, and determine multiple intersection nodes based on the task start point and task end point.

[0027] In an optional manner, step S101 further includes: connecting the task start point and the task end point with a line, taking the midpoint of the line as the center of a circle, and drawing a circle with the radius from the center of the circle to the task start point / task end point, and taking all the intersection nodes inside the circle as multiple intersection nodes of the work task.

[0028] In an optional approach, step S101 further includes: if there are no intersection nodes inside the circle, then take the midpoint of the connecting line as the center of the circle and expand the radius to draw a circle, and take all the intersection nodes inside the circle as multiple intersection nodes of the work task.

[0029] Step S102: Determine the working path based on the path planning algorithm applied to multiple intersection nodes.

[0030] In one alternative approach, the path planning algorithm is Dijkstra's algorithm. The core idea of ​​Dijkstra's algorithm is to guarantee the optimal solution under known conditions or all currently available conditions. If a better solution is obtained in subsequent iterations due to the addition of new conditions, the previous optimal solution is replaced. By continuously iterating and ensuring that the result of each iteration is the current optimal solution, the global optimal solution is obtained in the final iteration.

[0031] In an optional manner, step S102 further includes: Step 1: Mark the task starting point as the initial node and determine the initial node as the current point; Step 2: Calculate the distance from the current point to all unmarked adjacent intersection nodes and mark these adjacent intersection nodes; Step 3: Select the adjacent intersection node closest to the current point and mark it; and update the marked adjacent intersection nodes to the current point; Step 4: Repeat steps 2-3 until all intersection nodes are marked; Step 5: Connect all the marked current points in the above steps to generate the working path.

[0032] Specifically, each time, select the node closest to the task start point from the unmarked intersection nodes, mark it, and add it to the optimal path set; calculate the distance from the newly added intersection node A to its neighboring node B (excluding marked nodes), and update the current point.

[0033] Step S103: Execute the work task according to the work path. During the process, sample data is obtained by real-time sampling of the path between every two intersection nodes.

[0034] In an alternative approach, step S103 further includes: generating multiple candidate local paths for every two intersection nodes in the working path; and during the journey, sampling is performed on each candidate local path using laser and / or radar to obtain sampling data.

[0035] Specifically, local path planning generally involves regenerating a local path after global work path planning, combined with obstacle avoidance information. The work path planning generated by the above steps determines a global path from the task start point to the task end point. However, other situations may occur in actual work. Therefore, a trajectory tracking module can be pre-set in the industrial robot to actually track obstacle information, and a visual lidar information fusion module can be used to further process the obstacle avoidance part of the road conditions.

[0036] In this step, the rollout algorithm can be applied to every two intersection nodes to generate multiple candidate local paths, either parallel or divergent. The rollout algorithm is a decision-time planning algorithm based on simulation control. Rollout represents a trial or a trajectory. It uses real-time sampled data to obtain many simulated trajectories starting from the current state (there are multiple actions in the current state, so some simulated trajectories are obtained for each action). Then, the average of these trajectory returns is used to estimate the value of each action. When this estimate is accurate enough, the planning algorithm executes the action with the highest estimate. This action interacts with the environment, transitions to the next state, and the same method is used to plan the action for the next state. This process is repeated to obtain a complete candidate local path.

[0037] Step S104: Input the sampled data into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes.

[0038] In an alternative approach, step S104 further includes: for each candidate local path, applying a cost algorithm to calculate its cost; and based on the costs of multiple candidate local paths, comprehensively selecting the optimal solution as the local path between each pair of intersection nodes.

[0039] Based on the previously generated multiple candidate local paths and obstacle information obtained from the visual-LiDAR information fusion module, the output is the optimal local planning path. Specifically, three cost functions can be used to evaluate different local paths: priority cost, collision cost, and transition cost. Priority cost indicates that the middle local trajectory has the highest priority; in the absence of obstacles, the middle local trajectory is selected first. Collision cost is mainly divided into lateral cost and longitudinal cost. Lateral cost represents the horizontal distance of the local trajectory from the obstacle, and longitudinal cost represents the vertical distance of the local trajectory from the nearest obstacle. Transition cost restricts the vehicle from skipping multiple local paths, ensuring the smoothness of the vehicle's forward path. Depending on the vehicle's current position on the local path, switching to a nearby lane has a lower cost, while switching to a more distant lane has a higher cost.

[0040] Step S105: Execute the work task based on the working path and local path.

[0041] The method in this embodiment acquires the industrial robot's work task, determines the task start and end points based on the task, identifies multiple intersection nodes based on the task start and end points, applies a path planning algorithm to determine the work path based on the multiple intersection nodes, and executes the work task according to the work path. During the movement, real-time sampling is performed on the path between every two intersection nodes to obtain sampled data. The sampled data is input into a pre-set local path optimization algorithm for calculation to generate local paths between every two intersection nodes. The work task is then executed based on the work path and the local paths. This method obtains the global work path through an optimal path algorithm, determines the local path conditions during the industrial robot's movement through real-time sampling of local paths, and then plans the optimal solution for the local path based on the sampled data. This achieves adaptive control of the industrial robot's path and can update the movement path in real time based on real-time road conditions, enabling the industrial robot to have good obstacle avoidance performance and better complete its work tasks.

[0042] Figure 2 A schematic diagram of an embodiment of an industrial robot path planning system based on adaptive control according to the present invention is shown. Figure 2 As shown, the device includes: a working path determination module 201, a local path determination module 202, and a task processing module 203.

[0043] The work path determination module 201 is used to acquire the work task of the industrial robot, determine the task start point and task end point based on the work task, determine multiple intersection nodes based on the task start point and task end point, and determine the work path by applying a path planning algorithm based on the multiple intersection nodes.

[0044] In an alternative approach, the work path determination module 201 is further configured to: connect the task start point and the task end point, use the midpoint of the connection as the center of the circle, draw a circle with the radius from the center of the circle to the task start point / task end point, and use all the intersection nodes within the circle as multiple intersection nodes of the work task.

[0045] In an alternative approach, the work path determination module 201 is further configured to: if there are no intersection nodes within the circle, use the midpoint of the connecting line as the center of the circle and expand the radius to draw a circle, and use all intersection nodes within the circle as multiple intersection nodes for the work task.

[0046] In one alternative approach, the path planning algorithm is Dijkstra's algorithm.

[0047] In an optional manner, the work path determination module 201 is further configured to: Step 1: Mark the task starting point as the initial node and determine the initial node as the current point; Step 2: Calculate the distance from the current point to all unmarked adjacent intersection nodes and mark these adjacent intersection nodes; Step 3: Select the adjacent intersection node closest to the current point and mark it; and update the marked adjacent intersection nodes to the current point; Step 4: Repeat steps 2-3 until all intersection nodes are marked; Step 5: Connect all the marked current points in the above steps to generate the work path.

[0048] The local path determination module 202 is used to perform work tasks based on the work path. During the journey, it performs real-time sampling of the path between every two intersection nodes to obtain sampling data. The sampling data is then input into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes.

[0049] In an alternative approach, the local path determination module 202 is further configured to: generate multiple candidate local paths for every two intersection nodes in the working path; and during the journey, sample each candidate local path using laser and / or radar to obtain sampled data.

[0050] In an optional embodiment, the local path determination module 201 is further configured to: calculate the cost of each candidate local path using a cost algorithm; and select the optimal solution as the local path between each pair of intersection nodes based on the costs of multiple candidate local paths. The cost algorithm includes at least: a priority cost algorithm, a collision cost algorithm, and / or a transition cost algorithm. The priority cost algorithm indicates that the intermediate local trajectory has the highest priority, and in the absence of obstacles, the intermediate local trajectory is selected first. The collision cost algorithm is used to calculate the obstacle cost of the local path. The transition cost algorithm is used to prevent the industrial robot from skipping multiple local paths, ensuring the smoothness of the industrial robot's forward path.

[0051] Task processing module 203 is used to execute work tasks based on the working path and local path.

[0052] The system in this embodiment acquires the industrial robot's work task, determines the task start and end points based on the task, identifies multiple intersection nodes based on the task start and end points, applies a path planning algorithm to determine the work path based on the multiple intersection nodes, and executes the work task according to the work path. During the movement, real-time sampling is performed on the path between every two intersection nodes to obtain sampled data. The sampled data is input into a pre-set local path optimization algorithm for calculation to generate local paths between every two intersection nodes. The work task is then executed based on the work path and the local paths. After obtaining the global work path through the optimal path algorithm, this system determines the local path conditions during the industrial robot's movement through real-time sampling of local paths, and then plans the optimal solution for the local path based on the sampled data. This achieves adaptive control of the industrial robot's path and can update the movement path in real time based on real-time road conditions, enabling the industrial robot to have good obstacle avoidance performance and better complete its work tasks.

[0053] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute an industrial robot path planning method based on adaptive control in any of the above-described method embodiments.

[0054] Figure 3 The diagram shows a structural schematic of an embodiment of the computing device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0055] like Figure 3 As shown, the computing device may include:

[0056] Processor, Communications Interface, Memory, and Communications Bus.

[0057] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other network elements, such as clients or other servers. The processor executes programs, specifically the steps described in the embodiment of the adaptive control-based industrial robot path planning method.

[0058] Specifically, the program may include program code, which includes computer operation instructions.

[0059] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The server may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0060] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0061] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0062] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0063] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0064] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0065] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0066] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0067] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for path planning of an industrial robot based on adaptive control, characterized in that, include: Obtain the work task of the industrial robot, and determine the task start and end point based on the work task; Multiple intersection nodes are determined based on the task start point and the task end point; The working path is determined based on the path planning algorithm applied to the multiple intersection nodes; The work task is executed according to the work path. During the process, the path between every two intersection nodes is sampled in real time to obtain sampled data. The sampled data is input into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes. The work task is executed based on the work path and the local path.

2. The method according to claim 1, characterized in that, The step of determining multiple intersection nodes based on the task start point and the task end point further includes: A line is drawn connecting the task start point and the task end point. The midpoint of the line is used as the center of a circle, and the radius from the center of the circle to the task start point / task end point is used to draw a circle. All the intersection nodes within the circle are used as multiple intersection nodes of the task.

3. The method according to claim 2, characterized in that, The method further includes: If there are no intersection nodes within the circle, then the midpoint of the connecting line is used as the center of the circle, and the radius is expanded to draw a circle. All intersection nodes within the circle are used as multiple intersection nodes for the task.

4. The method according to claim 1, characterized in that, The path planning algorithm is Dijkstra's algorithm.

5. The method according to claim 4, characterized in that, The step of determining the working path based on the path planning algorithm applied to the multiple intersection nodes further includes: Step 1: Mark the task starting point as the initial node, and determine the initial node as the current point; Step 2: Calculate the distance from the current point to all unmarked adjacent intersection nodes, and mark these adjacent intersection nodes; Step 3: Select the nearest adjacent intersection node to the current point and mark it; then update the marked adjacent intersection node to the current point; Step 4: Repeat steps 2-3 until all intersection nodes are marked; Step 5: Connect all the marked current points from the above steps to generate the working path.

6. The method according to claim 1, characterized in that, The step of executing the work task according to the work path, and obtaining sampled data in real time for the path between every two intersection nodes during the journey, further includes: For every two intersection nodes in the working path, generate multiple candidate local paths; During the journey, laser and / or radar are used to sample each candidate local path to obtain sampled data.

7. The method according to claim 1, characterized in that, The step of inputting the sampled data into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes further includes: For each candidate local path, a cost algorithm is applied to calculate its cost; Based on the costs of multiple candidate local paths, the optimal solution is selected as the local path between every two intersection nodes; wherein, the cost algorithm includes at least: priority cost algorithm, collision cost algorithm and / or transition cost algorithm; The priority cost algorithm means that the middle local trajectory has the highest priority, and the middle local trajectory is selected first when there are no obstacles. The collision cost algorithm is used to calculate the cost of local path obstacles; The transition cost algorithm is used to prevent the industrial robot from skipping multiple local paths, thus ensuring the smoothness of the industrial robot's forward path.

8. An industrial robot path planning system based on adaptive control, characterized in that, include: The work path determination module is used to acquire the work tasks of the industrial robot and determine the task start point and task end point based on the work tasks. Multiple intersection nodes are determined based on the task start point and the task end point; a path planning algorithm is applied to determine the working path based on the multiple intersection nodes; The local path determination module is used to execute the work task according to the work path. During the journey, it performs real-time sampling of the path between every two intersection nodes to obtain sampling data; the sampling data is input into a pre-set local path optimization algorithm to generate a local path between every two intersection nodes. The task processing module is used to execute the work task based on the work path and the local path.

9. A computing device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform an operation corresponding to the adaptive control-based industrial robot path planning method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The storage medium stores at least one executable instruction, which causes the processor to perform an operation corresponding to the adaptive control-based industrial robot path planning method as described in any one of claims 1-7.

Images