KR102331315B1 - METHOD FOR A PARALLELIZATION ALGORITHM FOR REAL-TIME PATH PLANNING OF HIGH-DOFs ROBOT MANIPULATOR AND DEVICE THEREOF - Google Patents

Abstract

According to various embodiments of the present disclosure, a method of operating a manipulator device for improving a motion path includes a process of determining partial paths in an existing path, and determining joint combinations corresponding to each of the partial paths. and generating improved partial paths corresponding to each of the partial paths by performing path improvement on the joint combinations, and a path corresponding to each of the partial paths among the improved partial paths. The method may include determining partial paths having the greatest improvement effect, and changing the partial paths to corresponding partial paths having the greatest path improvement effect.

Description

A method and apparatus for implementing a parallel processing algorithm for real-time path generation of a high degree of freedom robot manipulator

The present disclosure relates to a method for implementing a parallel processing algorithm for real-time path generation of a high-depth of fields robot manipulator and an apparatus therefor.

Robot motion planning is one of the key areas of collaborative robot research. The sampling-based approach in motion planning is the most commonly used technique for industrial robots, which typically have a high level of configuration space. Using a sampling-based motion planning technique is excellent for handling high-degree-of-freedom construction space where it is difficult to find a path, but it may have the disadvantage that the planned path is generally not smooth and may generate partially unnecessary robot posture changes in the working space. Therefore, the planned path needs to be smoothed through post-processing and unnecessary changes in the posture of the robot included in the path need to be removed.

Among the post-processing path-smoothing techniques, there is an adaptive partial shortcuts (APSC) technique as a technique suitable for a robot having a high degree of freedom. Although the path improvement effect of the adaptive partial shortcuts (APSC) technique is excellent, it is not sufficient to apply it in a dynamic environment, and since it performs iterative path improvement, the problem that the overall computation time of the algorithm increases as the number of iterations increases have.

Based on the above discussion, the present disclosure provides a path improvement algorithm that is easy to apply in a dynamic environment through a fast path improvement post-processing process compared to existing post-processing path improvement techniques such as adaptive partial shortcuts (APSC). By proposing, a parallel processing algorithm implementation method and apparatus for real-time path generation of a high degree of freedom robot manipulator are provided.

According to various embodiments of the present disclosure, a method of operating a manipulator device for improving a motion path includes a process of determining partial paths in an existing path, and determining joint combinations corresponding to each of the partial paths. and generating improved partial paths corresponding to each of the partial paths by performing path improvement on the joint combinations, and a path corresponding to each of the partial paths among the improved partial paths. The method may include determining partial paths having the greatest improvement effect, and changing the partial paths to corresponding partial paths having the greatest path improvement effect.

According to various embodiments of the present disclosure, in a manipulator device for improving an operation path, the device includes at least one or more processors for path improvement, the at least one processor determines partial paths from an existing path, By determining joint combinations corresponding to each of the partial paths, and performing path improvement on the joint combinations, improved partial paths corresponding to each of the partial paths are generated, and among the improved partial paths, the It may be configured to determine partial paths having the greatest path improvement effect corresponding to each of the partial paths, and change the partial paths to partial paths having the largest path improvement effect.

According to embodiments of the present invention, if a parallel processing algorithm for real-time path generation of a high degree of freedom robot manipulator is used, a faster path improvement post-processing process is possible compared to existing post-processing path improvement techniques such as adaptive partial shortcuts (APSC). can

In addition, according to the embodiments of the present invention, the parallel processing algorithm for real-time path generation of the high degree of freedom robot manipulator is easy to apply in a dynamic environment in improving the post-processing path. Therefore, a robot system requiring human-robot cooperation is developed. can be used universally.

1A and 1B are exemplary diagrams illustrating an operation path of a manipulator generated by an existing sampling-based path planning technique, according to various embodiments of the present disclosure;
FIG. 2 is an exemplary block diagram of a manipulator device for implementing a parallel processing algorithm for generating a real-time path of a high degree of freedom robot manipulator, according to various embodiments of the present disclosure;
3 is a flowchart illustrating parallel processing for real-time path improvement post-processing of a manipulator device, according to various embodiments of the present disclosure;
4 is an exemplary diagram of a graph showing performance of a parallel processing algorithm according to various embodiments of the present disclosure;
5 is an example of a flowchart for explaining implementation of a parallel processing algorithm for generating a real-time path of a manipulator according to various embodiments of the present disclosure;
6 is another example of a flowchart for explaining implementation of a parallel processing algorithm for generating a real-time path of a manipulator according to various embodiments of the present disclosure;

The present disclosure (disclosure) can apply various transformations and can have various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

In the following embodiments, terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

Terms used in the following examples are used only to describe specific examples, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the following embodiments, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more It should be understood that this does not preclude the possibility of addition or presence of other features or numbers, steps, operations, components, parts, or combinations thereof.

Embodiments of the present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in any number of hardware and/or software configurations that perform specific functions. For example, embodiments of the present invention may be implemented directly, such as memory, processing, logic, look-up table, etc., capable of executing various functions by the control of one or more microprocessors or other control devices. Circuit configurations may be employed. Similar to how components of an embodiment of the invention may be implemented as software programming or software elements, embodiments of the invention may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs. , C, C++, Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors. In addition, embodiments of the present invention may employ conventional techniques for electronic environment setting, signal processing, and/or data processing. Terms such as mechanism, element, means, and configuration may be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in association with a processor or the like.

A term that refers to a variable (eg, a parameter, a value) related to the display of data used in the following description, refers to an object (eg, an electronic device, a display device, a display device, etc.) used to perform the operation of the invention Terms that refer to components of a device (eg, circuit, module, controller, processor, collection unit, prediction unit, inference unit, support unit, processing unit, display unit, sensor, etc.) are exemplified for convenience of description. . Accordingly, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meanings may be used.

Among the post-processing path-smoothing techniques for improving the motion path of a manipulator, there is an adaptive partial shortcuts (APSC) technique as a technique suitable for a robot having a high degree of freedom.

number process One loop 2 Randomly select partial path from existing path
(Random selection of a partial segment Π _s ) 3 Renew your AWD using existing and reference paths
(Update AWD using Π and Π _ref ) 4 Select a fixed number of joints according to AWD
(Select a fixed number of joints according to AWD) 5 Improved partial path generation with improved partial path using linear interpolation for selected joints
(Perform smoothing on Π _s via linear interpolation on selected joints) 6 Determining whether an improved partial path is included in a collision-free composition space
(If Π' _s ∈ C _free , then) 7 Change partial path to improved partial path
(Replace Π _s with Π' _s )

Table 1 may show an exemplary description of an algorithm of an operation process according to the APSC technique of the manipulator. In this case, Π is an existing path (planned path), which is a path generated from a sampling-based path planning algorithm and may be composed of a series of nodes and trunks connecting adjacent nodes in the path. Π _ref is a reference path, and may be a straight path in a configuration space connecting the first and last nodes of Π that does not consider obstacles in the path. C _free can be a conflict-free configuration space. Π _s is a partial segment of path, and may be a path bordering on any two nodes among nodes in Π. Π' _s is an improved partial path, and may be a path generated by performing path improvement on _{Π s.} AWD is an adaptive weighting distribution (AWD), and may be a weight to reflect the effect of each joint on path improvement.

The conventional APSC technique may be an iterative process as shown in Table 1. First, referring to process 2, in order to select a partial path for which path improvement post-processing is to be performed for a given existing path Π, two nodes are randomly selected among the nodes of the path in the existing path Π, and the selected two nodes are used as boundaries. A partial path Π _s can be determined.

To perform path improvement on the selected partial path Π _s , we can select a joint of the robot and generate _{a new partial path Π' s for this joint by using linear interpolation.} Referring to steps 3 to 5, the number of joints to be selected may be predetermined and fixed. Also, joints can be selected according to AWD to reflect the effect of each joint on path improvement. The AWD can be updated at every iteration so that a joint with a path difference between Π and Π _{s greater than that of other joints is selected.} Referring to steps 6 to 7 _{, the validity judgment is performed by determining whether the new partial path Π' s} is free from collision with an external obstacle, and if free, the partial path Π _s of the existing path Π is converted to Π' _s Can be replaced. In this technique, by repeating steps 1 to 7, the operation path of the manipulator can be gradually improved.

As described above, the conventional APSC technique has an excellent path improvement effect, but may not be sufficient to be applied in a dynamic environment. Basically, since the APSC technique performs iterative path improvement, the overall computation time of the algorithm may increase as the number of iterations increases. Referring to Table 1, a main process contributing to the number of iterations may be a collision check part of processes 6 to 7 . Improvements path Π _'s probability there is no conflict can be highly dependent on the selected portion of the path Π _s, the process of joints are selected to perform the path improvement for the selected partial path Π _s also important on the path to improve times can Since the algorithm of APSC method selects a fixed number of joints using AWD for joint selection, the probability that the combination of joints selected for a _{given partial path Π s} is not the best choice for the _{selected partial path Π s is low.} Because it is high, there is a high probability that it will not pass the collision check step in process 6.

Therefore, the parallel processing algorithm proposed in the present disclosure can provide an algorithm for processing path improvement for multiple partial paths in parallel compared to the existing technique for performing path improvement for one partial path at every iteration step. In addition, in contrast to selecting a fixed number of joints at random according to a weight distribution (eg, AWD in APSC), path improvement works by simultaneously exploring all possible joint combinations in parallel and selecting the joint with maximum efficiency without collision. It is possible to provide an algorithm that can dramatically reduce the iterative calculation process required for

1A and 1B are exemplary diagrams illustrating an operation path of a manipulator generated by an existing sampling-based path planning technique, according to various embodiments of the present disclosure; Referring to FIG. 1A , an example 100a of a six-degree-of-freedom robotic manipulator device and a conventional path of the device is shown. The existing path Π shown in (a) of FIG. 1A may be an operation path having the first node 1 to the last node 15 as a boundary. Referring to FIG. 1B , an example 100b of partial paths bounded by a 6 degree of freedom robotic manipulator device and any two nodes in an existing path of the device is shown. _{The partial path Π s} shown in (b) of FIG. 1B may be an operation path bordering on nodes 1 to 4 in the existing path, and the partial path Π _s shown in (c) is, in the existing path, nodes 4 to 11 It may be an operation path bordering on , and the partial path Π _s shown in (d) may be an operation path bordering on nodes 8 to 15 in the existing path.

When using the APSC technique, if the partial path Π _s is different, the maximum number of joints that can generate the improved partial path Π' _{s without collision may be different.} ), the maximum number of joints that can generate an improved partial path without collision may be different for each partial path.

number of joints/
Total number of joint combinations Number of joint combinations that can improve the path without collision 1b (b) 1b (c) 1b (d) 1/6 5 3 2 2/15 11 2 2 3/20 13 0 2 4/15 9 0 One 5/6 4 0 0 6/1 One 0 0

Table 2 shows the number of joint combinations for which path improvement is possible for partial paths. Referring to Table 2, the number of joint combinations capable of successfully improving the route without collision for each of the selected joints for the partial routes of FIG. 1B may be represented. For example, in the case of the partial path in (b) of Fig. 1b, the _{maximum number of selectable joints for Π' s} without collision is 6, in (c), 2, and in (d), 4 have. For example, in the APSC technique, since the number of joints to be selected is fixed and the number of joints to be selected is fixed, when the number of joints to be selected is fixed to three, the partial path of FIG. Since it is not possible to generate an improved partial path by not satisfying For another example, even when the number of joints is fixed to two, since joints are arbitrarily selected according to the AWD, the partial route of FIG. may not be able to Therefore, if a fixed number of joints are selected probabilistically using AWD like the APSC method, the probability of successful partial path improvement may be lowered and the path improvement time may be increased.

FIG. 2 is an exemplary block diagram of a manipulator device for implementing a parallel processing algorithm for generating a real-time path of a high degree of freedom robot manipulator according to various embodiments of the present disclosure; Referring to FIG. 2 , in an exemplary block diagram 200 , the manipulator device 210 may include a processor 211 , a sensor unit 213 , and a memory 215 . In the present disclosure, a method of performing a path improvement operation of the manipulator device 210 through a processor in the manipulator device 210 is described. However, the operation is performed by an external or internal device of the manipulator device 210 or ) and other devices connected to it.

The processor 211 may be configured to be connected to a component in the manipulator device 210 to perform a parallel processing operation for real-time path improvement post-processing of the manipulator device 210 . For example, the processor 211 selects partial paths from the existing motion path of the manipulator, generates improved partial paths by performing path improvement on joint combinations of the partial paths, and satisfies the condition of the collision detection step. It may be configured to update the partial paths having the greatest path improvement effect among the improved partial paths with the corresponding partial paths.

Table 3 may show an exemplary description of a parallel processing path improvement algorithm for real-time path improvement post-processing of the manipulator device 210 device of the processor 211 .

number process One loop 2 Split the existing path into n partial paths
(Partition Π into n path segment, {Π _s,1 , Π _s,2 ,..., Π _s,n }) 3 Data initialization in a set of selected partial paths corresponding to each of the divided partial paths
(∑ _i =Φ, ∀i∈{1, 2,..., n}) 4 Generate all joint combinations corresponding to each of the divided partial paths
(Run in Parallel: ∀i∈{1, 2,..., n}, ∀j∈{1, 2,..., m} 5 Generates improved sub-paths in parallel using linear interpolation for all joint combinations corresponding to each of the divided sub-paths
(Perform smoothing on Π _s,i via linear interpolation on joints in Y _j ) 6 It is determined whether or not the improved partial paths are included in the collision-free construction space, and the improved partial paths included in the collision-free construction space are added to the set of selected partial paths corresponding to each of the divided partial paths.
(If Π' _s,i ∈ C _free , then ∑ _i =∑ _i ∪Π' _s,i ) 7 Checking whether a set of selected partial paths corresponding to each of the divided partial paths is an empty set
(For each ∑ _i st ∑ _i ≠Φ) 8 Selecting a partial path having the greatest path improvement effect from a set of selected partial paths corresponding to each of the divided partial paths
(Choose one Π' _s,i from ∑ _i wrt smoothing quality) 9 Each of the divided partial paths is changed to a partial path with the greatest improvement effect corresponding to each of the divided partial paths
(Replace Π _s,i with Π' _s,i )

In this case, Π is an existing path, which is a path generated from a sampling-based path planning algorithm and may be composed of a series of nodes and trunks connecting adjacent nodes in the path. C _free can be a conflict-free configuration space. Π _s,i is partial paths, and may be a plurality of partial paths bordering on any two nodes among nodes in Π. Π' _s,i are improved partial paths, and may be paths generated by performing path improvement on _{Π s,i.} Y is a combination of joints for a partial path, and all combinations Y of possible joints for one partial path among a plurality of partial paths are the set {Y ₁ , Y ₂ , ... , Y _m }. ∑ _i is a set of selected partial paths, and may be a set of improved partial paths on which path improvement has been performed and collision-checked among a plurality of partial paths.

The parallel processing path improvement algorithm for the real-time path improvement post-processing of the manipulator device 210 device may be an iterative process as shown in Table 3. First, referring to process 2, n partial paths can be determined by dividing the _{existing path Π into n partial paths Π s,i} by randomly selecting n-1 nodes among nodes in the existing path. In this case, by avoiding the selection of consecutive nodes of the existing path, the selected partial paths may not overlap each other. Referring to processes 3 to 6, the set ∑ _i of the selected partial paths is initialized, and the path improvement operation is performed on all possible joint combinations for _{each partial path Π s,i, and the improved} Select only partial paths. For example, initialize a set of selected partial paths ∑ _i , generate all possible joint combinations for each partial path Π _s,i , and perform linear interpolation for all joint combinations corresponding to each of the divided partial paths. can be used to generate improved partial paths in parallel. Thereafter, referring to steps 7 to 9, the existing partial path Π _s,i may be updated _{by selecting the partial path Π' s,i} having the greatest path improvement effect among the improved partial paths obtained through the parallelization process. For example, it is checked whether a set of selected partial paths corresponding to each of the divided partial paths is an empty set, and the part having the greatest path improvement effect in the set of selected partial paths corresponding to each of the divided partial paths is an empty set. A path may be selected, and each of the divided partial paths may be changed to a partial path having the greatest improvement effect corresponding to each of the divided partial paths. After this process is simultaneously processed through a parallel process for all n partial paths, the existing path Π can be updated by combining all the updated partial paths.

The processor 211 may, for example, execute software (eg, a program) to control at least one other component (eg, a hardware or software component) of the manipulator device 210 connected to the processor 211 . and can perform various data processing or operations. According to an embodiment, as at least part of data processing or operation, the processor 211 loads a command or data received from another component (eg, the sensor unit 213 or the memory 215) into the volatile memory, The command or data stored in the volatile memory may be processed, and the resulting data may be stored in the non-volatile memory. According to an embodiment, the processor 211 includes a main processor (eg, a central processing unit or an application processor), and a secondary processor (eg, a graphics processing unit, an image signal processor, a sensor hub processor, or a secondary processor capable of operating independently or together) communication processor). Additionally or alternatively, the auxiliary processor may be configured to use less power than the main processor or to specialize in a designated function. The coprocessor may be implemented separately from or as part of the main processor.

The sensor unit 213 may acquire information necessary for the manipulator device 210 to perform path improvement. For example, obtaining state information of the manipulator device 210, detecting (recognizing) the surrounding environment and an object, receiving object information obtained from an external device, generating map data, determining an operation path, It may determine a response to a user interaction, or may determine an action. In an embodiment, the manipulator device 210 may determine whether an operation path of the manipulator device 210 is free from collision with an external obstacle in the configuration space using sensor information obtained from the sensor. For example, the manipulator device 210 may determine whether there is an obstacle in the improved partial path by using the obstacle existence information of the motion path acquired by the sensor unit 213 , and check collision of the improved partial path. can be performed. The manipulator device 210 determines an operation path by using at least one of map data, object information detected from sensor information, or object information obtained from an external device, and the processor 211 controls the determined improved motion path. The sensing range can be determined accordingly.

The sensor unit 213 detects an operating state (eg, power or temperature) of the manipulator device 210 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the sensed state. can do. According to an embodiment, the sensor unit 213 may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, a humidity sensor, or an illuminance sensor.

The memory 215 may store partial paths and information on joint combinations corresponding to each of the partial paths when the manipulator device 210 operates through a parallel processing algorithm for real-time path generation. For example, the memory 215 may store information including a set of partial paths determined by dividing an existing path. For another example, information including a set of all combinations of possible joints corresponding to each of the partial paths may be stored. As another example, information including the improved partial paths or a set of the improved partial paths included in the configuration space without collision among the partial paths may be stored.

The memory 215 may store various data used by at least one component (eg, the processor 211 or the sensor unit 213 ) of the manipulator device 210 . Data may include, for example, input data or output data for software (eg, a program) and instructions related thereto. The memory 215 may include a volatile memory or a non-volatile memory. The program may be stored as software in the memory 215 and may include, for example, an operating system, middleware, or an application.

According to various embodiments of the present disclosure, in a manipulator device for improving an operation path, the device includes at least one or more processors for path improvement, the at least one processor determines partial paths from an existing path, Determining joint combinations corresponding to each of the partial paths, and performing path improvement on the joint combinations in parallel, thereby generating improved partial paths corresponding to each of the partial paths, the improved partial path It may be configured to determine partial paths having the greatest path improvement effect corresponding to each of the partial paths among the partial paths, and change the partial paths to partial paths having the greatest path improvement effect.

According to various embodiments of the present disclosure, the at least one processor may be further configured to select improved partial paths that do not collide with an obstacle from among the improved partial paths.

According to various embodiments of the present disclosure, the at least one processor determines partial paths by selecting at least one node from among a plurality of nodes included in the existing path, and selects non-consecutive nodes so that there is no overlap. It may be further configured to determine partial paths that are not.

According to various embodiments of the present disclosure, the at least one processor may be further configured to select an improved partial path in which the corresponding improved partial path is the shortest compared to the straight path of the first node and the last node of each partial path. have.

According to various embodiments of the present disclosure, the at least one processor may be further configured to select a partial path having the shortest length of an operation path in the configuration space from among the improved partial paths.

According to various embodiments of the present disclosure, the at least one processor may be further configured to update the existing path by combining the changed partial paths with the partial paths having the greatest path improvement effect.

According to various embodiments of the present disclosure, the at least one processor determines partial paths in the existing path, determines joint combinations corresponding to each of the partial paths, and improves a path for the joint combinations generating improved partial paths corresponding to each of the partial paths by performing The process of changing to the corresponding partial paths having the greatest path improvement effect is repeated for (1) a preset time, (2) repeats for a preset number of times, or (3) the partial path with the greatest path improvement effect By combining the partial paths changed with the , the updated existing path may be configured to repeat until the same as the existing path before the update.

According to various embodiments of the present disclosure, there is provided a computer-readable storage medium storing data representing software executable by a computer for improving an operation path of a manipulator device, the computer-readable storage medium comprising: instructions for determining, instructions for determining joint combinations corresponding to each of the partial paths, and performing path improvement on the joint combinations, thereby generating improved partial paths corresponding to each of the partial paths. instructions for generating, instructions for determining, among the improved partial paths, the partial paths having the greatest path improvement effect corresponding to each of the partial paths, and the path improving effect corresponding to the partial paths being the most It may be a computer-readable storage medium containing instructions for changing to large partial paths.

3 is a flowchart illustrating parallel processing for real-time path improvement post-processing of a manipulator device, according to various embodiments of the present disclosure; Referring to FIG. 3 , a flowchart 300 illustrating parallel processing may represent the overall structure of a parallelization-based path improvement technique for real-time path improvement post-processing of the manipulator device. The parallel processing technique for real-time path improvement post-processing of the manipulator device performs path improvement through an iterative process like the existing sampling-based path planning algorithm (e.g. APSC), but utilizes parallelism to achieve the same level with a much smaller number of iterations. path improvement effect can be achieved.

In an embodiment, first, when the manipulator device 210 operates, existing path information may be input as an input value in a parallel processing process. The manipulator device 210 may generate a plurality of partial paths by selecting any two paths within an existing path. For example, the manipulator device 210 may determine and generate n partial paths by randomly selecting n-1 nodes from among nodes in an existing path. For example, in determining the partial paths, the manipulator device 210 may generate partial paths that do not overlap each other by not selecting consecutive nodes.

The manipulator device 210 may determine all possible joint combinations for each of the plurality of generated partial paths, and perform path improvement in parallel based on linear interpolation. For example, the manipulator device 210 may generate improved partial paths by determining all possible joint combinations m for _{one partial path Π s,j , and performing path improvement for each joint combination.} In an embodiment, the manipulator device 210 additionally performs a process of selecting only valid partial paths that do not collide with an obstacle for the improved partial path, so that only the improved partial paths that do not collide with an obstacle in the path can be selected. have.

The manipulator device 210 may update the partial paths in parallel by selecting the partial path having the greatest path improvement effect from among the improved partial paths generated for all joint combinations corresponding to each of the plurality of partial paths. . For example, by changing the plurality of partial paths determined in the existing path to the partial path having the greatest path improvement effect among the improved partial paths generated for all joint combinations corresponding to each of the plurality of partial paths, the path update can be performed. For example, one partial path Π _{s,j is changed to Π' s,j} with the greatest improvement effect among the partial paths for which path improvement is performed for all possible joint combinations and collision check is performed, so that the path is updated. This can be done.

In an embodiment, the manipulator device 210 may determine a partial path having the shortest motion path among the improved partial paths based on the length of the path in the configuration space as the partial path having the greatest improvement effect. In another embodiment, the manipulator device 210 may determine that the corresponding improved partial path is the shortest partial path with the greatest path improvement effect compared to the straight paths of the first and last nodes of each partial path divided from the existing path. have.

The manipulator device 210 selects any two paths in the existing path, performs path improvement on a plurality of partial paths in parallel at the same time, and then combines the updated partial paths to create an existing path. Can be updated. For example, by performing path improvement in parallel on n partial paths Π _s,j divided in the existing path, n improved partial paths Π' _s,j are generated, and each partial path is improved. After updating the partial paths by changing the partial path, the existing path Π can be updated by combining the _{improved partial path Π' s,j.}

The manipulator device 210 may determine whether to repeat the path improvement process after performing path improvement on an existing path. In an embodiment, the manipulator device 210 may determine whether to repeat the path improvement process by determining whether an iteration release condition is satisfied. For example, the manipulator device 210 may determine that the repeat release condition is satisfied and output the final motion path when a preset time elapses based on the time when the path improvement is started after the existing path is input. For another example, when the path improvement process is repeated for a predetermined number of times based on the number of times that the existing path is input and the path improvement is started, the manipulator device 210 determines that the repeat release condition is satisfied, and the final motion path can be printed out. As another example, the manipulator device 210 determines that the iteration release condition is satisfied when the updated existing path is the same as the existing path before the update by combining the changed partial paths with the partial paths having the greatest path improvement effect. and output the final motion path.

4 is an exemplary diagram of a graph showing performance of a parallel processing algorithm according to various embodiments of the present disclosure; Referring to FIG. 4 , a result of comparing the performance of the existing sampling-based path planning technique (eg, APSC) and the parallel processing algorithm proposed in the present disclosure based on the path length is shown. The X-axis is the number of times the path improvement is repeated, and the Y-axis is the length of the improved path (Len(Π ^* ) compared to the length of the original existing path (Len(Π°)), which means the performance of the path improvement process. Referring to , it can be confirmed that the method proposed in the present disclosure converges to the performance threshold faster, and thus has better performance than the existing sampling-based path planning method (eg, APSC).

5 is an example of a flowchart for explaining implementation of a parallel processing algorithm for generating a real-time path of a manipulator according to various embodiments of the present disclosure; The process included in the flowchart 500 of FIG. 5 may be performed by the manipulator device 210 (eg, the processor 211 ).

In operation 501 , the manipulator device 210 may determine partial paths from the existing path. For example, the manipulator device 210 may determine the plurality of partial paths by dividing the existing path into a plurality of partial paths by selecting two arbitrary nodes among nodes in the existing path. In this case, by avoiding the selection of consecutive nodes of the existing path, the selected partial paths may not overlap each other.

In step 503 , the manipulator device 210 may determine joint combinations corresponding to each of the partial paths. For example, the manipulator device 210 may determine all joint combinations for which path improvement is possible in each of the determined partial paths.

In operation 505 , the manipulator device 210 may generate improved partial paths corresponding to each of the partial paths by performing path improvement on joint combinations. For example, the manipulator device 210 may perform a path improvement operation using linear interpolation for all possible joint combinations for each partial path and generate the improved partial path in parallel. In an embodiment, only the improved partial routes that do not collide with an obstacle among the partial routes on which the route improvement work has been performed may be selected.

In operation 507 , the manipulator device 210 may determine, among the improved partial paths, the partial paths having the greatest path improvement effect corresponding to each of the partial paths. For example, the manipulator device 210 may determine a partial path having the shortest motion path as the partial path having the greatest improvement effect based on the length of the path in the configuration space among the improved partial paths. As another example, the manipulator device 210 may determine that the corresponding improved partial path is the shortest partial path with the greatest improvement effect compared to the straight paths of the first and last nodes of each partial path divided from the existing path. have.

In operation 509 , the manipulator device 210 may change the partial paths to corresponding partial paths having the greatest path improvement effect. For example, the manipulator device 210 changes each of the divided partial paths into improved partial paths having the greatest improvement effect corresponding to each of the divided partial paths, and changes all of the updated partial paths. You can update existing routes by combining them.

6 is another example of a flowchart for explaining implementation of a parallel processing algorithm for generating a real-time path of a manipulator according to various embodiments of the present disclosure; The process included in the flowchart 600 of FIG. 6 may be performed by the manipulator device 210 or a configuration (eg, the processor 211 ) included in the manipulator device 210 .

In operation 601 , the manipulator device 210 may determine partial paths from the existing path. The manipulator device 210 may determine partial paths from the existing path. For example, the manipulator device 210 may determine the plurality of partial paths by dividing the existing path into a plurality of partial paths by selecting two arbitrary nodes among nodes in the existing path.

In step 603 , the manipulator device 210 may determine joint combinations corresponding to each of the partial paths. For example, the manipulator device 210 may determine all joint combinations for which path improvement is possible in each of the determined partial paths.

In operation 605 , the manipulator device 210 may generate improved partial paths corresponding to each of the partial paths by performing path improvement on joint combinations. For example, the manipulator device 210 may perform a path improvement operation using linear interpolation for all possible joint combinations for each partial path and generate the improved partial path in parallel.

In operation 607 , the manipulator device 210 may select improved partial paths that do not collide with obstacles from among the improved partial paths. For example, the manipulator device 210 uses the information obtained from the sensor unit 213 to determine whether the improved partial path of the manipulator device 210 is free from collision with an external obstacle in the configuration space. , the validity judgment can be performed, and only improved partial routes without collision with obstacles can be selected.

In operation 609 , the manipulator device 210 may determine partial paths having the greatest path improvement effect corresponding to each of the partial paths among the selected partial paths. For example, the manipulator device 210 may determine a partial path having the shortest motion path as the partial path having the greatest improvement effect based on the length of the path in the configuration space among the improved partial paths. As another example, the manipulator device 210 may determine that the corresponding improved partial path is the shortest partial path with the greatest improvement effect compared to the straight paths of the first and last nodes of each partial path divided from the existing path. have.

In operation 611 , the manipulator device 210 may change the partial paths to the corresponding partial paths having the greatest path improvement effect. For example, the manipulator device 210 may change each of the divided partial paths into improved partial paths having the greatest improvement effect corresponding to each of the divided partial paths.

In operation 613 , the manipulator device 210 may update the existing path by combining the updated partial paths. For example, the manipulator device 210 changes each of the divided partial paths into improved partial paths that have the greatest improvement effect corresponding to each of the divided partial paths, and combines all of the updated partial paths. The path can be updated. Accordingly, the manipulator device 210 may update the existing path by combining all of the updated partial paths by simultaneously and parallelly improving the paths for all partial paths in steps 601 to 611 .

In operation 615 , the manipulator device 210 may determine whether the iteration release condition is satisfied. For example, the manipulator device 210 may determine that the repeat release condition is satisfied when a preset time has elapsed from the time when the path improvement is started after the existing path is input. As another example, the manipulator device 210 may determine that the repetition cancellation condition is satisfied when the path improvement process is repeated for a predetermined number of times based on the number of times that an existing path is input and path improvement is started. For another example, the manipulator device 210 determines that the iteration release condition is satisfied when the updated existing path is the same as the existing path before the update by combining the changed partial paths with the partial paths having the greatest path improvement effect. can If it is determined that the iterative release condition is satisfied, the manipulator device 210 may determine the path on which the path improvement has been performed as the final path. can be done

According to various embodiments of the present disclosure, a method of operating a manipulator device for improving a motion path includes a process of determining partial paths in an existing path, a process of determining joint combinations corresponding to each of the partial paths, and the joint The process of generating improved partial paths corresponding to each of the partial paths by performing path improvement on the combinations in parallel, and a path improvement effect corresponding to each of the partial paths among the improved partial paths It may include a process of determining the largest partial paths, and a process of changing the partial paths to the corresponding partial paths having the greatest path improvement effect.

According to various embodiments of the present disclosure, in the method of operating a manipulator device for improving an operation path, the process of generating the improved partial paths includes selecting improved partial paths that do not collide with an obstacle from among the improved partial paths. process may be included.

According to various embodiments of the present disclosure, in the method of operating a manipulator device for improving an operation path, the process of determining partial paths in the existing path includes selecting at least one node from among a plurality of nodes included in the existing path. and determining partial paths by doing so, and the selecting of the at least one node may include determining non-overlapping partial paths by selecting non-consecutive nodes.

According to various embodiments of the present disclosure, in the method of operating a manipulator device for improving an operation path, the process of determining the partial path having the greatest path improvement effect comprises: a comparison of the straight path between the first node and the last node of each partial path; The corresponding improved partial path may include selecting the shortest improved partial path.

According to various embodiments of the present disclosure, in the method of operating a manipulator device for improving the motion path, the process of determining the partial path having the greatest path improvement effect includes the length of the motion path in the configuration space among the improved partial paths. It may include the process of selecting the shortest partial path.

According to various embodiments of the present disclosure, the method of operating a manipulator device for improving an operation path may further include updating the existing path by combining the changed partial paths with the partial paths having the greatest path improvement effect. can

According to various embodiments of the present disclosure, in a method of operating a manipulator device for motion path improvement, a process of determining partial paths in an existing path, a process of determining joint combinations corresponding to each of the partial paths, and the joint A process of generating improved partial paths corresponding to each of the partial paths by performing path improvement on the combinations, and a portion of the improved partial paths having the greatest path improvement effect corresponding to each of the partial paths The process of determining the routes and the process of changing the partial routes to the corresponding partial routes having the greatest route improvement effect are (1) repeated for a preset time, (2) repeated for a preset number of times, (3) ) By combining the changed partial paths with the partial paths having the greatest path improvement effect, the updated existing path may be repeated until the same as the existing path before the update.

Electronic devices according to various embodiments of the present disclosure may be devices of various types. The electronic device may include, for example, a portable communication device (eg, a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance device. The electronic device according to the embodiment of this document is not limited to the above-described devices.

Various embodiments of the present disclosure and terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of the embodiments. In connection with the description of the drawings, like reference numerals may be used for similar or related components. The singular form of the noun corresponding to the item may include one or more of the item, unless the relevant context clearly dictates otherwise. As used herein, “A or B”, “at least one of A and B”, “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “A , B, or C" each may include any one of the items listed together in the corresponding one of the phrases, or all possible combinations thereof. Terms such as “first”, “second”, or “first” or “second” may simply be used to distinguish the component from other such components, and refer to those components in other aspects (e.g., importance or order) is not limited. that one (e.g. first) component is "coupled" or "connected" to another (e.g. second) component with or without the terms "functionally" or "communicatively" When referenced, it means that one component can be connected to the other component directly (eg by wire), wirelessly, or through a third component.

As used herein, the term “module” or “-unit” may include a unit implemented in hardware, software, or firmware, and is, for example, interchangeable with terms such as logic, logic block, component, or circuit. can be used as A module may be an integrally formed part or a minimum unit or a part of the part that performs one or more functions. For example, according to an embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Methods according to the embodiments described in the claims or specifications of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors in an electronic device (device). One or more programs include instructions for causing an electronic device to execute methods according to embodiments described in a claim or specification of the present disclosure.

Such programs (software modules, software) include random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable ROM (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other It may be stored in an optical storage device or a magnetic cassette. Alternatively, it may be stored in a memory composed of a combination of some or all thereof. In addition, each configuration memory may be included in plurality.

In addition, the program is transmitted through a communication network consisting of a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that can be accessed. Such a storage device may be connected to a device implementing an embodiment of the present disclosure through an external port. In addition, a separate storage device on the communication network may be connected to the device implementing the embodiment of the present disclosure.

In the specific embodiments of the present disclosure described above, elements included in the disclosure are expressed in the singular or plural according to the specific embodiments presented. However, the singular or plural expression is appropriately selected for the context presented for convenience of description, and the present disclosure is not limited to the singular or plural element, and even if the element is expressed in plural, it is composed of the singular or singular. Even an expressed component may be composed of a plurality of components.

So far, the present invention has been focused on preferred embodiments. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention can be implemented in modified forms without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive point of view. The scope of the present invention is indicated in the claims rather than the above description, and it should be construed that the invention claimed by the claims and inventions equivalent to the claimed invention are included in the present invention.

Claims (15)

A method of operating a manipulator device for improving an operation path, the method comprising:
The process of determining partial paths from the existing path, and
Initializing a path constituting each of the partial paths,
determining, as joint combinations corresponding to each of the partial paths, the joint combinations that are all combinations of possible joints for each partial path for each partial path of the partial paths;
The process of generating improved partial paths corresponding to each of the partial paths by performing path improvement in parallel for each and every joint combination of the joint combinations;
determining, among the improved partial paths, partial paths having the greatest path improvement effect corresponding to each of the partial paths;
and changing the partial paths to the corresponding partial paths having the greatest path improvement effect.
The method according to claim 1,
The generating of the improved partial routes includes selecting the improved partial routes that do not collide with an obstacle from among the improved partial routes.
The method according to claim 1,
The process of determining partial paths in the existing path includes determining partial paths by selecting at least one or more nodes from among a plurality of nodes included in the existing path,
The selecting of the at least one or more nodes may include determining non-overlapping partial paths by selecting non-consecutive nodes.
The method according to claim 1,
The process of determining the partial path having the greatest path improvement effect includes selecting an improved partial path having the shortest corresponding improved partial path compared to the straight path of the first node and the last node of each partial path;
The method according to claim 1,
The determining of the partial path having the greatest path improvement effect includes selecting a partial path having the shortest length of an operation path in a configuration space from among the improved partial paths.
The method according to claim 1,
and updating the existing path by combining the changed partial paths with the partial paths having the greatest path improvement effect.
The method according to claim 1,
An improved part corresponding to each of the partial paths by determining partial paths in the existing path, determining joint combinations corresponding to each of the partial paths, and performing path improvement on the joint combinations The process of generating routes, the process of determining partial routes having the greatest route improvement effect corresponding to each of the partial routes among the improved partial routes, and the part having the greatest route improvement effect corresponding to the partial routes The process of changing the routes is (1) repeated for a preset time, (2) repeated for a preset number of times, or (3) the existing updated by combining the changed partial routes with the partial routes having the greatest route improvement effect. A method, characterized in that it is repeated until the path is the same as the existing path before the update.
A manipulator device for improving a motion path, comprising:
The device comprises at least one or more processors for path improvement,
The at least one or more processors,
Determining partial paths from an existing path,
Initializing a path constituting each of the partial paths,
determine the joint combinations corresponding to each of the partial paths, for each partial path of the partial paths, the joint combinations being all combinations of possible joints for each partial path,
by performing path improvement in parallel for each and every joint combination of the joint combinations, thereby generating improved partial paths corresponding to each of the partial paths;
determining, among the improved partial paths, partial paths having the greatest path improvement effect corresponding to each of the partial paths;
an apparatus configured to change the partial paths to the corresponding partial paths having the greatest path improvement effect.
9. The method of claim 8,
The at least one or more processors,
The apparatus further configured to select improved partial paths free from obstacles and collisions among the improved partial paths.
9. The method of claim 8,
The at least one or more processors,
determining partial paths by selecting at least one or more nodes among a plurality of nodes included in the existing path;
The apparatus further configured to determine non-overlapping partial paths by selecting non-contiguous nodes.
9. The method of claim 8,
The at least one or more processors,
The apparatus further configured to select an improved partial path having a shortest corresponding improved partial path compared to the straight path of the first node and the last node of each partial path.
9. The method of claim 8,
The at least one or more processors,
The apparatus further configured to select a partial path having the shortest length of the motion path on the construction space from among the improved partial paths.
9. The method of claim 8,
The at least one or more processors,
The apparatus further configured to update the existing route by combining the changed partial routes into the partial routes having the greatest route improvement effect.
9. The method of claim 8,
The at least one or more processors,
An improved partial path corresponding to each of the partial paths by determining partial paths in the existing path, determining joint combinations corresponding to each of the partial paths, and performing path improvement on the joint combinations generating the partial paths, determining the partial paths having the greatest path improvement effect corresponding to each of the partial paths among the improved partial paths, and changing the partial paths to the partial paths having the greatest path improvement effect. By repeating the process (1) for a preset time, (2) repeating for a preset number of times, or (3) combining the changed partial paths with the partial paths having the greatest path improvement effect, the updated existing path is restored to the existing path before the update. A device configured to repeat until it is identical to a path.
A computer-readable storage medium storing data representing software executable by a computer for improving an operation path of a manipulator device, the computer-readable storage medium comprising:
Commands for determining partial paths in an existing path, commands for initializing a path constituting each of the partial paths, and joint combinations corresponding to each of the partial paths, respectively, for each partial path of the partial paths Improved partial paths corresponding to each of the partial paths by instructions for determining the joint combinations that are all combinations of possible joints for the partial path, and performing path improvement on each and every joint combination of the joint combinations. instructions for generating, instructions for determining, among the improved partial paths, the partial paths having the greatest path improvement effect corresponding to each of the partial paths, and the path improving effect corresponding to the partial paths being the most A computer readable storage medium comprising instructions for changing to large partial paths.

Images