Multi-robot clustering method considering service and moving path

Abstract

A multi-robot clustering method considering a service and a moving path is provided. A multi-moving object clustering method according to an embodiment of the present invention comprises: collecting pieces of mission performance information from moving objects; calculating similarity between the moving objects on the basis of the collected pieces of mission performance information; clustering the moving objects on the basis of the calculated similarity; and returning a result of the clustering to the moving objects. Accordingly, it is possible to limit information to be shared among multiple robots to prevent a network overload due to information sharing in a service environment in which multiple robots cooperate, thereby contributing to providing a high-speed service.

Description

A multi-robot clustering method considering services and movement paths

[0001] The present invention relates to an Internet of Things service, and more particularly, to a method for controlling mobile robots in an environment where a plurality of mobile robots collaborate to provide a service.

[0002] As the Internet of Things expands from smart devices to robots, robots are performing many physically demanding and repetitive tasks on behalf of humans, and the scope of services is expected to expand further in the future.

[0003] Robots collect sensing data, monitor events, navigate optimal routes, and perform missions. Representative service areas include unmanned logistics / delivery and security / surveillance.

[0004] When multiple robots are deployed, they can further improve service quality by sharing sensing data. However, when the sensing data is in the form of LiDAR or high-resolution images, network load hinders smooth information sharing.

[0005] The present invention has been devised to solve the above problems, and the purpose of the present invention is to provide a multi-robot clustering method that takes into account services, sensing data, and movement paths in a service environment through information sharing of multi-robots.

[0006] A multi-mobile clustering method according to one embodiment of the present invention for achieving the above object includes the steps of: collecting task performance information from mobiles; calculating similarity between mobiles based on the collected task performance information; clustering mobiles based on the calculated similarity; and returning clustering results to the mobiles.

[0007] The mission performance information includes the types of collectable sensing data and the types of sensing data required for mission performance, and the calculation step may be to calculate the similarity between the moving objects based on the overlapping ratio between the types of collectable sensing data and the types of sensing data required for mission performance.

[0008] The mission execution information may include a movement path, and the calculation step may be to calculate a similarity between the moving objects based on the rate of overlap of the movement paths.

[0009] The movement path can be a movement path from a specific point in the past.

[0010] The movement path may be a projected movement path up to a specific point in the future.

[0011] The clustering step may be to cluster the moving objects according to a density-based clustering (Density-Based Spatial Clustering of Applications with Noise) technique.

[0012] Mobile objects classified in the same cluster can share sensing data.

[0013] According to another aspect of the present invention, a multi-mobile clustering server is provided, characterized by including: a communication unit that collects mission performance information from mobiles; a processor that calculates similarity between mobiles based on the collected mission performance information, clusters the mobiles based on the calculated similarity, and returns the clustering results to the mobiles through the communication unit.

[0014] As described above, according to embodiments of the present invention, through multi-robot clustering that takes into account services, sensing data, and movement paths, network overload caused by information sharing can be prevented in a service environment where multi-robots share information and collaborate, thereby contributing to the provision of high-speed services.

[0015] Figure 1 is a multi-robot service system to which an embodiment of the present invention can be applied.

[0016] Figure 2 is a multi-robot clustering method according to one embodiment of the present invention;

[0017] Figure 3 is a multi-robot clustering server according to another embodiment of the present invention.

[0018] Hereinafter, the present invention will be described in more detail with reference to the drawings.

[0019] In an embodiment of the present invention, a multi-robot clustering method considering collaborative services, sensing data, and movement paths is proposed.

[0020] This is a technology that clusters robots that are deemed to need information sharing to share information in order to increase the accuracy of sensing data and compensate for blind spots in an environment where multiple robots collaborate to provide services, and ensures that information sharing only occurs within the cluster.

[0021] FIG. 1 is a diagram illustrating a multi-robot service system to which an embodiment of the present invention can be applied. As illustrated, the multi-robot service system to which an embodiment of the present invention can be applied is configured to include mobile robots (10-1, 10-2, ..., 10-n) and a multi-robot clustering server (100).

[0022] Mobile robots (10-1, 10-2, ..., 10-n) autonomously move around the service area and perform missions to provide services. During this process, the mobile robots (10-1, 10-2, ..., 10-n) collect and utilize sensor data, while sharing the sensing data with other mobile robots (10-1, 10-2, ..., 10-n).

[0023] The multi-robot clustering server (100) clusters mobile robots (10-1, 10-2, ..., 10-n) and controls the sharing of sensing data so that it is only performed within the cluster, thereby limiting the range of sensing data sharing.

[0024] The clustering process of mobile robots (10-1, 10-2, ..., 10-n) by the multi-robot clustering server (100) is illustrated in Fig. 2. Fig. 2 is a flowchart provided to explain a multi-robot clustering method according to one embodiment of the present invention.

[0025] In order to cluster mobile robots (10-1, 10-2, ..., 10-n), first, the multi-robot clustering server (100) collects service performance information from mobile robots (10-1, 10-2, ..., 10-n) (S210).

[0026] The service performance information collected in step S210 includes: 1) the types of sensing data that can be collected, 2) the types of sensing data required for service performance, and 3) the expected movement path from a specific point in the past to a specific point in the future.

[0027] Sensing data can include LiDAR data, camera footage, and other types of sensing data. Services can also include unmanned logistics / delivery, unmanned security / surveillance, and other types of services.

[0028] The next multi-robot clustering server (100) calculates the similarity between mobile robots (10-1, 10-2, ..., 10-n) based on the service performance information collected in step S210 (S220).

[0029] Specifically, in step S220, the similarity between mobile robots (10-1, 10-2, ..., 10-n) with a high overlapping ratio of 'types of collectable sensing data' and 'types of sensing data required for service performance' is calculated to be high, and the similarity between mobile robots (10-1, 10-2, ..., 10-n) with a low overlapping ratio is calculated to be low.

[0030] Additionally, the similarity between mobile robots with a high rate of overlapping movement paths (10-1, 10-2, ..., 10-n) is calculated to be high, and the similarity between mobile robots with a low rate of overlapping movement paths (10-1, 10-2, ..., 10-n) is calculated to be low.

[0031] Thereafter, the multi-robot clustering server (100) clusters the mobile robots (10-1, 10-2, ..., 10-n) based on the similarity between the mobile robots (10-1, 10-2, ..., 10-n) calculated in step S220 (S230).

[0032] In step S230, mobile robots (10-1, 10-2, ..., 10-n) can be clustered using the density-based clustering (DNSC) technique. Of course, it is also possible to cluster mobile robots (10-1, 10-2, ..., 10-n) using other techniques.

[0033] The next multi-robot clustering server (100) returns the clustering results from step S230 to the mobile robots (10-1, 10-2, ..., 10-n) (S240). Accordingly, the mobile robots (10-1, 10-2, ..., 10-n) classified in the same cluster share sensing data.

[0034] The mobile robot clustering by steps S210 to S240 can be repeated periodically so that the clusters are updated periodically. This is done in consideration of the fact that the movement paths and required sensing data of the mobile robots (10-1, 10-2, ..., 10-n) can change at any time.

[0035] The detailed configuration of the multi-robot clustering server (100) illustrated in Fig. 1 is illustrated in Fig. 3. Fig. 3 is a block diagram illustrating the configuration of the multi-robot clustering server (100) according to another embodiment of the present invention.

[0036] The multi-robot clustering server (100) can be implemented as a computing server system including a communication unit (110), a processor (120), and a storage unit (130), as illustrated.

[0037] The communication unit (110) is a communication interface for connection with an external network or external device, and in the embodiment of the present invention, collects service performance information from mobile robots (10-1, 10-2, ..., 10-n).

[0038] The processor (120) calculates the similarity between mobile robots (10-1, 10-2, ..., 10-n) based on the collected task performance information according to the procedure illustrated in the aforementioned FIG. 1, clusters the mobile robots (10-1, 10-2, ..., 10-n) based on the calculated similarity, and returns the clustering results to the mobile robots (10-1, 10-2, ..., 10-n).

[0039] The storage unit (130) provides the storage space necessary for the processor (120) to function and operate.

[0040] So far, a preferred embodiment of a multi-robot clustering method considering services and movement paths has been described in detail.

[0041] In the above embodiment, through multi-robot clustering that takes into account services, sensing data, and movement paths, network overload caused by information sharing can be prevented in a service environment where multi-robots collaborate by sharing information, thereby contributing to the provision of high-speed services.

[0042] Meanwhile, it goes without saying that the technical idea of ​​the present invention can also be applied to a computer-readable recording medium containing a computer program that performs the functions of the device and method according to the present embodiment. In addition, the technical idea according to various embodiments of the present invention can be implemented in the form of computer-readable code recorded on a computer-readable recording medium. The computer-readable recording medium can be any data storage device that can be read by a computer and store data. For example, the computer-readable recording medium can be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical disk, a hard disk drive, etc. In addition, the computer-readable code or program stored on the computer-readable recording medium can be transmitted through a network connected between computers.

[0043] In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications can be made by a person having ordinary skill in the art to which the present invention pertains without departing from the gist of the present invention as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present invention.

Claims

1. A step of collecting mission performance information from moving objects; A step of calculating the similarity between mobile objects based on the collected mission performance information; A step of clustering moving objects based on the calculated similarity; A multi-mobile clustering method, characterized by including a step of returning clustering results to mobile objects.

2. In claim 1, Mission execution information is, Including the types of sensing data that can be collected and the types of sensing data required to perform the mission; The calculation steps are: A multi-mobile object clustering method characterized by calculating the similarity between mobile objects based on the overlapping ratio between the types of collectable sensing data and the types of sensing data required for performing a mission.

3. In claim 1, Mission execution information is, Including the movement path, The calculation steps are: A multi-mobile object clustering method characterized by calculating the similarity between mobile objects based on the rate of overlapping movement paths.

4. In claim 3, The movement path is, A multi-mobile object clustering method characterized by a movement path from a specific point in the past.

5. In claim 4, The movement path is, A multi-mobile clustering method characterized by a predicted movement path until a specific point in the future.

6. In claim 1, The clustering step is, A multi-mobile object clustering method characterized by clustering mobile objects according to the density-based clustering (Density-Based Spatial Clustering of Applications with Noise) technique.

7. In claim 1, The mobile objects classified in the same cluster are, A multi-mobile clustering method characterized by sharing sensing data.

8. A communications unit that collects mission performance information from mobile devices; A multi-mobile clustering server, characterized by including a processor that calculates the similarity between mobiles based on collected mission performance information, clusters the mobiles based on the calculated similarity, and returns the clustering results to the mobiles through a communication unit.

Images