WO2024085285A1 - Robot-based optimal indoor delivery path planning method using context map - Google Patents

Robot-based optimal indoor delivery path planning method using context map Download PDF

Info

Publication number
WO2024085285A1
WO2024085285A1 PCT/KR2022/016137 KR2022016137W WO2024085285A1 WO 2024085285 A1 WO2024085285 A1 WO 2024085285A1 KR 2022016137 W KR2022016137 W KR 2022016137W WO 2024085285 A1 WO2024085285 A1 WO 2024085285A1
Authority
WO
WIPO (PCT)
Prior art keywords
delivery route
edges
context map
graph
information
Prior art date
Application number
PCT/KR2022/016137
Other languages
French (fr)
Korean (ko)
Inventor
이석준
최충재
성낙명
Original Assignee
한국전자기술연구원
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한국전자기술연구원 filed Critical 한국전자기술연구원
Publication of WO2024085285A1 publication Critical patent/WO2024085285A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping

Definitions

  • the present invention relates to route search technology, and more specifically, to a method of searching for an optimal indoor delivery route using a context map in which specific contexts are fused.
  • a map is essential information for route navigation of a moving object, and is constructed using data acquired through various sensors.
  • SLAM Simultaneous Localization and Mapping
  • SLAM Simultaneous Localization and Mapping
  • a map constructed in this way has no information other than geographical information, such as context (situational awareness information). Although there is a map with approximate environmental information added through semantic technology, it is very insufficient to be used to find the optimal route for faster delivery.
  • the present invention was developed to solve the above problems, and the purpose of the present invention is to provide a method of searching for an optimal indoor delivery route using a context map in which specific contexts are fused.
  • a delivery route search method to achieve the above object includes the steps of obtaining a context map in which contexts are respectively mapped to corresponding zones; Creating a graph connecting movable areas in the context map with edges; With reference to the context map, predicting travel times for each of the edges; Entering the expected travel times into the respective edges; and determining the optimal delivery route using a graph.
  • Contexts may include information about the path of the area, information about objects in the area, and information about the state of the area.
  • Information about the route in the area may include the width and height of the route and maximum speed.
  • Information about the status may include information about the level of congestion and risk factors in the area.
  • travel times for each edge can be predicted by referring to information on the maximum speed, congestion, and risk factors of the route for the corresponding area.
  • the movement time can be predicted to be infinite for edges where movement is impossible due to risk factors.
  • the optimal delivery route can be determined from the graph using the Dijkstra Algorithm.
  • the context map can be created by generating a 2D map of the indoor environment, acquiring contexts in corresponding areas of the indoor environment, and matching the obtained situational awareness information to corresponding areas of the 2D map.
  • Contexts can be obtained from multiple delivery robots.
  • the delivery route search system generates a graph connecting movable areas with edges in a context map in which contexts are mapped to each of the corresponding areas, and each of the edges with reference to the context map.
  • a processor that predicts travel times for, writes the estimated travel times to the corresponding edges, and determines the optimal delivery route using a graph; and a storage unit that provides storage space necessary for the processor.
  • a delivery route search method includes the steps of generating a graph in which movable areas are connected by edges in a context map in which contexts are respectively mapped to the corresponding areas; With reference to the context map, predicting travel times for each of the edges; Entering the expected travel times into the respective edges; Determining an optimal delivery route using a graph; and providing the determined optimal delivery route to the delivery robot.
  • a delivery route search system includes a communication unit for communicating with a delivery robot; And in the context map where the contexts are mapped to the corresponding areas, a graph is created connecting the moveable areas with edges, and the travel times for each of the edges are predicted with reference to the context map, and the expected travel times are calculated. It includes a processor that writes in each of the corresponding edges, determines the optimal delivery route using the graph, and provides the determined optimal delivery route to the delivery robot through the communication unit.
  • FIG. 1 is a flow chart provided to explain a method of building a context map applicable to an embodiment of the present invention
  • 2 is a diagram illustrating a 2D grid map
  • Figure 3 is a diagram illustrating the update result of the context map
  • Figure 4 is a flow chart provided to explain the optimal indoor delivery route search method according to an embodiment of the present invention.
  • Figure 5 is a diagram illustrating a graph
  • Figure 6 is a diagram illustrating the results of writing the predicted travel times into the edges
  • Figure 7 is a block diagram of a delivery route search system according to another embodiment of the present invention.
  • An embodiment of the present invention presents an optimal indoor delivery route search method. This is a technology that explores the optimal indoor delivery route for delivery robots by utilizing a context map in which specific contexts are fused.
  • the embodiment of the present invention focuses on route search based on delivery time rather than route search based on delivery distance, thereby minimizing delivery time, which is the most important factor in delivery.
  • the context that is integrated into the context map used when exploring an indoor delivery route is specific situational awareness information rather than rough environmental information, and this information is matched and stored in each area where the context map is divided into a grid format.
  • FIG. 1 is a flowchart provided to explain a method of building a context map applicable to an embodiment of the present invention.
  • step S110 To build a context map, first create a 3D map of the indoor environment (S110). 3D map generation in step S110 can be performed using the SLAM (Simultaneous Localization and Mapping) technique.
  • SLAM Simultaneous Localization and Mapping
  • step S110 the 3D map generated in step S110 is projected onto a 2D plane and converted into a 2D map (S120). Because 2D maps are more useful than 3D maps for delivery route navigation, step S120 is necessary.
  • the 2D map generated in step S120 is divided into a 2D grid format to divide the indoor environment into multiple zones (S130).
  • Figure 2 shows the results of dividing the 2D map into multiple zones according to the 2D grid shape.
  • Context can be provided from delivery robots performing deliveries in an indoor environment. It is also possible to receive context from multiple delivery robots rather than one. Even if there are multiple delivery robots, only one context map is built.
  • Delivery robots can create context by recognizing various situations based on the sensors they possess (image sensors, lidar, radar, environmental sensors, etc.).
  • the context includes 1) size information, 2) maximum speed information, 3) object information, and 4) state information for the area.
  • Size information is the width and height of the path in the area.
  • Maximum speed information is the maximum speed allowed in the area, which may be determined by the indoor environment manager or the delivery robot manager. For complex and dangerous areas, the maximum speed is set lower than for other areas.
  • Object information is information that describes objects (people, delivery robots, other moving objects, etc.) in the area, and includes information about the type and number of objects.
  • Status information is information that explains the status of the area, and includes information on congestion (cohesion of objects, possible movement speed, etc.) and risk factors (obstacles, obstructions, fire, flooding, accidents, etc.).
  • step S140 situation awareness information is provided along with location information of the delivery robot, that is, area information of the location where the delivery robot acquired the context. This is because location information is needed to match the context to the corresponding area in the context map.
  • the context map is updated by matching the acquired contexts to corresponding areas of the 2D grid map (S150).
  • step S150 matching between the context and the 2D grid map area is performed with reference to the location information transmitted along with the context.
  • Figure 3 shows the results of updating the context map by mapping the context to the corresponding area of the 2D grid map.
  • Figure 4 is a flow chart provided to explain the optimal indoor delivery route search method according to an embodiment of the present invention.
  • a graph is created in which each area is connected by edges, referring to the context map (S210).
  • a graph is a collection of paths that connect edges from one area of the context map to other movable areas.
  • Figure 5 illustrates a graph that can be generated in step S210.
  • the example graph assumes the case where there are 4 regions in the context map. According to the presented graph, it is possible to move from Zone-1 to Zone-2 and Zone-3, but it is impossible to move to Zone-4. Similarly, in Zone-2, you can move to Zone-1 and Zone-3, but you cannot move to Zone-4. In Zone-3, you can move to Zone-1, Zone-2, and Zone-3, and in Zone-3, you can move to Zone-1 and Zone-3. In 4, you can only move to area-3.
  • the travel time for each of the edges connecting the zones is predicted (S220), and the predicted travel times are entered into each of the corresponding edges (S230).
  • the travel time prediction in step S220 is made with reference to the contexts matched to each zone in the context map.
  • the contexts that affect travel time are maximum speed, congestion (cohesion of objects, possible movement speed, etc.), and risk factors (obstacles, obstructions, fire, flooding, accidents, etc.).
  • the moving speed of the moving object should not exceed the maximum speed and is reduced depending on congestion or risk factors. Meanwhile, in the case of edges where movement is impossible due to risk factors, the movement time can be predicted to be infinite ( ⁇ ).
  • the optimal indoor delivery route is determined using the graph (S240).
  • the optimal delivery route determined in step S240 is the route with the shortest overall travel time.
  • the Dijkstra Algorithm can be used as a path search technique for step S240.
  • the use of other route search algorithms is not excluded.
  • FIG. 7 is a block diagram of a delivery route search system according to another embodiment of the present invention.
  • the delivery route search system according to an embodiment of the present invention is constructed including a communication unit 310, a processor 320, and a storage unit 330.
  • the delivery route search system can be performed by a mobile entity, but if the mobile entity does not have sufficient resources, it can also be implemented as being performed by a context map construction system. Below, the latter is assumed.
  • the communication unit 310 is a means for mutual communication with a delivery robot moving in an indoor environment.
  • the processor 320 generates a 2D grid map for the indoor environment, matches the contexts obtained from delivery robots through the communication unit 310 to the 2D grid map, creates and updates the context map, and generates and updates the context map.
  • a context map is provided to the delivery robot through the communication unit 310.
  • the processor 320 searches for an optimal indoor delivery route according to the method shown in FIG. 4 and provides the discovered indoor delivery route to the delivery robot through the communication unit 310.
  • the storage unit 330 provides the storage space necessary for the processor 320 to build/update the context map and search for the optimal indoor delivery route.
  • a context map containing specific context is built/updated to provide more specific context than existing maps, enabling the search for the optimal indoor delivery route and predicting the expected delivery time relatively accurately. It was allowed to happen.
  • the context map uses a grid format to distinguish each area of the indoor environment, improving the convenience of context matching and location accuracy.
  • delivery robots acquire the contexts reflected in the context map.
  • other mobile objects moving in an indoor environment it is also possible for other mobile objects moving in an indoor environment to acquire context, and it is also possible to acquire context for fixed facilities other than mobile objects, such as CCTV cameras or environmental sensors installed on the ceiling or walls. possible.
  • the context acquired by the mobile chain delivery robot is trusted, and the object information in the area matches the information acquired by the delivery robot.
  • the congestion level among the status information (cohesion of objects, possible movement speed, etc.)
  • the context obtained by the CCTV camera is trusted, and the congestion information of the area matches the information obtained by the CCTV camera.
  • the context acquired by the delivery robot is trusted, and the risk factor information in the area is information acquired by the delivery robot. matching
  • a computer-readable recording medium can be any data storage device that can be read by a computer and store data.
  • computer-readable recording media can be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc.
  • computer-readable codes or programs stored on a computer-readable recording medium may be transmitted through a network connected between computers.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

A robot-based optimal indoor delivery path planning method using a context map is provided. The delivery path planning method according to an embodiment of the present invention comprises: acquiring a context map in which respective pieces of context are mapped to corresponding zones; creating a graph in which respective movable zones in the context map are connected using edges; estimating respective moving times of the edges with reference to the context map; writing the estimated respective moving times on the edges; and determining an optimal delivery path by using the graph. Therefore, an optimal delivery path can be planned using a context map merged with specific context, and an estimated delivery time can be predicted with relative accuracy.

Description

컨텍스트 맵을 활용한 로봇 기반 최적 실내 배송경로 탐색 방법Robot-based optimal indoor delivery route search method using context map
본 발명은 경로 탐색 기술에 관한 것으로, 더욱 상세하게는 구체적인 컨텍스트가 융합되어 있는 컨텍스트 맵을 활용하여 최적의 실내 배송경로를 탐색하는 방법에 관한 것이다.The present invention relates to route search technology, and more specifically, to a method of searching for an optimal indoor delivery route using a context map in which specific contexts are fused.
맵(Map)은 이동체의 경로 탐색을 위한 필수 정보로, 다양한 센서들을 통해 획득한 데이터들을 활용하여 구축한다. SLAM(Simultaneous Localization and Mapping)은 대표적인 맵 구축 기술이다.A map is essential information for route navigation of a moving object, and is constructed using data acquired through various sensors. SLAM (Simultaneous Localization and Mapping) is a representative map construction technology.
이와 같은 방식에 의해 구축된 맵은 지리적인 정보 이외에 다른 정보, 이를 테면 컨텍스트(context : 상황인지 정보)가 없다. 시맨틱 기술을 통해 대략적인 환경 정보가 부가되어 있는 맵이 있기는 하지만, 보다 빠른 배송을 위한 최적의 경로 탐색을 위해 활용하기에는 매우 미흡하다.A map constructed in this way has no information other than geographical information, such as context (situational awareness information). Although there is a map with approximate environmental information added through semantic technology, it is very insufficient to be used to find the optimal route for faster delivery.
본 발명은 상기와 같은 문제점을 해결하기 위하여 안출된 것으로서, 본 발명의 목적은, 구체적인 컨텍스트가 융합되어 있는 컨텍스트 맵을 활용하여 최적의 실내 배송경로를 탐색하는 방법을 제공함에 있다.The present invention was developed to solve the above problems, and the purpose of the present invention is to provide a method of searching for an optimal indoor delivery route using a context map in which specific contexts are fused.
상기 목적을 달성하기 위한 본 발명의 일 실시예에 따른 배송경로 탐색 방법은, 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵을 획득하는 단계; 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하는 단계; 컨텍스트 맵을 참고로, 엣지들 각각에 대한 이동 시간들을 예상하는 단계; 예상된 이동 시간들을 해당 엣지들에 각각 기입하는 단계; 및 그래프를 이용하여, 최적 배송경로를 결정하는 단계;를 포함한다.A delivery route search method according to an embodiment of the present invention to achieve the above object includes the steps of obtaining a context map in which contexts are respectively mapped to corresponding zones; Creating a graph connecting movable areas in the context map with edges; With reference to the context map, predicting travel times for each of the edges; Entering the expected travel times into the respective edges; and determining the optimal delivery route using a graph.
컨텍스트들은, 해당 구역의 경로에 대한 정보, 해당 구역에 있는 객체들에 대한 정보, 해당 구역의 상태에 대한 정보를 포함할 수 있다.Contexts may include information about the path of the area, information about objects in the area, and information about the state of the area.
해당 구역의 경로에 대한 정보는, 경로의 너비와 높이 및 최대 속도를 포함할 수 있다.Information about the route in the area may include the width and height of the route and maximum speed.
상태에 대한 정보는, 해당 구역의 혼잡도, 위험 요소에 대한 정보를 포함할 수 있다.Information about the status may include information about the level of congestion and risk factors in the area.
예상 단계는, 해당 구역에 대한 경로의 최대 속도, 혼잡도, 위험 요소에 대한 정보를 참고로, 엣지들 각각에 대한 이동 시간들을 예상할 수 있다.In the prediction step, travel times for each edge can be predicted by referring to information on the maximum speed, congestion, and risk factors of the route for the corresponding area.
예상 단계는, 위험 요소로 인해 이동이 불가능한 엣지에 대해서는 이동 시간을 무한대로 예측할 수 있다.In the prediction phase, the movement time can be predicted to be infinite for edges where movement is impossible due to risk factors.
결정 단계는, 다익스트라 알고리즘(Dijkstra Algorithm)을 이용하여, 그래프로부터 최적 배송경로를 결정할 수 있다.In the decision step, the optimal delivery route can be determined from the graph using the Dijkstra Algorithm.
컨텍스트 맵은, 실내 환경의 2D 맵을 생성하고, 실내 환경의 해당 구역들에서 컨텍스트들을 획득하며, 획득된 상황인지 정보들을 2D 맵의 해당 구역들에 각각 매칭하여 생성할 수 있다.The context map can be created by generating a 2D map of the indoor environment, acquiring contexts in corresponding areas of the indoor environment, and matching the obtained situational awareness information to corresponding areas of the 2D map.
컨텍스트들은, 다수의 배송로봇들로부터 획득될 수 있다.Contexts can be obtained from multiple delivery robots.
본 발명의 다른 실시예에 따른 배송경로 탐색 시스템은, 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하고, 컨텍스트 맵을 참고로 엣지들 각각에 대한 이동 시간들을 예상하며, 예상된 이동 시간들을 해당 엣지들에 각각 기입하고, 그래프를 이용하여 최적 배송경로를 결정하는 프로세서; 및 프로세서에 필요한 저장공간을 제공하는 저장부;를 포함한다.The delivery route search system according to another embodiment of the present invention generates a graph connecting movable areas with edges in a context map in which contexts are mapped to each of the corresponding areas, and each of the edges with reference to the context map. A processor that predicts travel times for, writes the estimated travel times to the corresponding edges, and determines the optimal delivery route using a graph; and a storage unit that provides storage space necessary for the processor.
본 발명의 또 다른 실시예에 따른 배송경로 탐색 방법은, 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하는 단계; 컨텍스트 맵을 참고로, 엣지들 각각에 대한 이동 시간들을 예상하는 단계; 예상된 이동 시간들을 해당 엣지들에 각각 기입하는 단계; 그래프를 이용하여, 최적 배송경로를 결정하는 단계; 및 결정된 최적 배송경로를 배송로봇에 제공하는 단계;를 포함한다.A delivery route search method according to another embodiment of the present invention includes the steps of generating a graph in which movable areas are connected by edges in a context map in which contexts are respectively mapped to the corresponding areas; With reference to the context map, predicting travel times for each of the edges; Entering the expected travel times into the respective edges; Determining an optimal delivery route using a graph; and providing the determined optimal delivery route to the delivery robot.
본 발명의 또 다른 실시예에 따른 배송경로 탐색 시스템은, 배송로봇과 통신 연결하는 통신부; 및 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하고, 컨텍스트 맵을 참고로 엣지들 각각에 대한 이동 시간들을 예상하며, 예상된 이동 시간들을 해당 엣지들에 각각 기입하고, 그래프를 이용하여 최적 배송경로를 결정하며, 결정된 최적 배송경로를 통신부를 통해 배송로봇에 제공하는 프로세서;를 포함한다.A delivery route search system according to another embodiment of the present invention includes a communication unit for communicating with a delivery robot; And in the context map where the contexts are mapped to the corresponding areas, a graph is created connecting the moveable areas with edges, and the travel times for each of the edges are predicted with reference to the context map, and the expected travel times are calculated. It includes a processor that writes in each of the corresponding edges, determines the optimal delivery route using the graph, and provides the determined optimal delivery route to the delivery robot through the communication unit.
이상 설명한 바와 같이, 본 발명의 실시예들에 따르면, 구체적인 컨텍스트가 융합되어 있는 컨텍스트 맵을 활용하여 최적의 실내 배송경로를 탐색할 수 있게 되고, 예상 배송 시간을 비교적 정확하게 예측할 수 있게 된다.As described above, according to embodiments of the present invention, it is possible to search for an optimal indoor delivery route by utilizing a context map in which specific contexts are fused, and to predict the expected delivery time relatively accurately.
도 1은 본 발명의 일 실시예에 적용가능한 컨텍스트 맵을 구축하는 방법의 설명에 제공되는 흐름도,1 is a flow chart provided to explain a method of building a context map applicable to an embodiment of the present invention;
도 2는 2D 그리드 맵을 예시한 도면,2 is a diagram illustrating a 2D grid map;
도 3은 컨텍스트 맵의 업데이트 결과를 예시한 도면,Figure 3 is a diagram illustrating the update result of the context map;
도 4는 본 발명의 일 실시예에 따른 최적 실내 배송경로 탐색 방법의 설명에 제공되는 흐름도,Figure 4 is a flow chart provided to explain the optimal indoor delivery route search method according to an embodiment of the present invention;
도 5는 그래프를 예시한 도면,Figure 5 is a diagram illustrating a graph;
도 6은 예측된 이동 시간들을 엣지들에 각각 기입된 결과를 예시한 도면, 그리고,Figure 6 is a diagram illustrating the results of writing the predicted travel times into the edges, and
도 7은 본 발명의 다른 실시예에 따른 배송경로 탐색 시스템의 블럭도이다.Figure 7 is a block diagram of a delivery route search system according to another embodiment of the present invention.
이하에서는 도면을 참조하여 본 발명을 보다 상세하게 설명한다.Hereinafter, the present invention will be described in more detail with reference to the drawings.
본 발명의 실시예에서는 최적 실내 배송경로 탐색 방법을 제시한다. 구체적인 컨텍스트가 융합되어 있는 컨텍스트 맵을 활용하여 배송로봇의 최적 실내 배송경로를 탐색하는 기술이다.An embodiment of the present invention presents an optimal indoor delivery route search method. This is a technology that explores the optimal indoor delivery route for delivery robots by utilizing a context map in which specific contexts are fused.
본 발명의 실시예에서는 배송 거리를 기초로 한 경로 탐색이 아닌 배송 시간을 기초로 경로 탐색을 지향하여, 배송에서 가장 중요한 요소인 배송 시간을 최소화할 수 있도록 한다.The embodiment of the present invention focuses on route search based on delivery time rather than route search based on delivery distance, thereby minimizing delivery time, which is the most important factor in delivery.
실내 배송경로를 탐색함에 있어 이용되는 컨텍스트 맵에 융합되는 컨텍스트는 대략적인 환경 정보가 아닌 구체적인 상황인지 정보이며, 이 정보는 컨텍스트 맵을 그리드 형태로 구획한 각 구역들에 매칭되어 저장된다.The context that is integrated into the context map used when exploring an indoor delivery route is specific situational awareness information rather than rough environmental information, and this information is matched and stored in each area where the context map is divided into a grid format.
도 1은 본 발명의 일 실시예에 적용가능한 컨텍스트 맵을 구축하는 방법의 설명에 제공되는 흐름도이다.1 is a flowchart provided to explain a method of building a context map applicable to an embodiment of the present invention.
컨텍스트 맵 구축을 위해 먼저 실내 환경에 대한 3D 맵을 생성한다(S110). S110단계에서의 3D 맵 생성은 SLAM(Simultaneous Localization and Mapping) 기법을 이용하여 수행될 수 있다.To build a context map, first create a 3D map of the indoor environment (S110). 3D map generation in step S110 can be performed using the SLAM (Simultaneous Localization and Mapping) technique.
다음 S110단계에서 생성된 3D 맵을 2D 평면으로 프로젝션 하여, 2D 맵으로 변환한다(S120). 배송경로 탐색에는 3D 맵 보다는 2D 맵이 유용하기 때문에, S120단계가 필요하다.Next, the 3D map generated in step S110 is projected onto a 2D plane and converted into a 2D map (S120). Because 2D maps are more useful than 3D maps for delivery route navigation, step S120 is necessary.
이후 S120단계에서 생성된 2D 맵을 2D 그리드 형태로 구획하여 실내 환경을 다수의 구역들로 구분한다(S130). 도 2에는 2D 맵을 2D 그리드 형태에 따라 다수의 구역들로 구분한 결과를 나타내었다.Afterwards, the 2D map generated in step S120 is divided into a 2D grid format to divide the indoor environment into multiple zones (S130). Figure 2 shows the results of dividing the 2D map into multiple zones according to the 2D grid shape.
S110단계 내지 S130단계를 통해 컨텍스트 맵 구축에 필요한 2D 그리드 맵이 확보되었다. 이하에서는 컨텍스트를 획득하여 2D 그리드 맵과 융합시키는 과정에 대해 설명한다.Through steps S110 to S130, the 2D grid map necessary for constructing the context map was secured. Below, we describe the process of acquiring context and fusing it with a 2D grid map.
이를 위해, 먼저 실내 환경의 해당 구역들에서 컨텍스트들을 획득/수집한다(S140). 컨텍스트는 실내 환경에서 배송을 수행하고 있는 배송로봇들로부터 제공받을 수 있다. 한 대가 아닌 여러 대의 배송로봇들로부터 컨텍스트들을 제공받는 것도 가능하다. 배송로봇들이 다수라 할지라도 컨텍스트 맵은 하나만 구축된다.To this end, contexts are first obtained/collected from corresponding areas of the indoor environment (S140). Context can be provided from delivery robots performing deliveries in an indoor environment. It is also possible to receive context from multiple delivery robots rather than one. Even if there are multiple delivery robots, only one context map is built.
배송로봇은 보유하고 있는 센서들(이미지 센서, 라이다, 레이더, 환경 센서 등)을 기반으로 다양한 상황들을 인지하여 컨텍스트를 생성할 수 있다.Delivery robots can create context by recognizing various situations based on the sensors they possess (image sensors, lidar, radar, environmental sensors, etc.).
컨텍스트는 해당 구역에 대한 1) 크기 정보, 2) 최대 속도 정보, 3) 객체 정보, 4) 상태 정보를 포함한다.The context includes 1) size information, 2) maximum speed information, 3) object information, and 4) state information for the area.
1) 크기 정보는 해당 구역의 경로에 대한 너비와 높이이다. 2) 최대 속도 정보는 해당 구역에서 허용되는 최대 속도로, 이는 실내 환경 관리자에 의해 정해질 수도 있고 배송로봇 관리자에 의해 정해질 수도 있다. 복잡하고 위험한 구역에 대해서는 그렇지 않은 구역 보다 최대 속도를 낮게 정한다.1) Size information is the width and height of the path in the area. 2) Maximum speed information is the maximum speed allowed in the area, which may be determined by the indoor environment manager or the delivery robot manager. For complex and dangerous areas, the maximum speed is set lower than for other areas.
3) 객체 정보는 해당 구역에 있는 객체들(사람, 배송로봇, 기타 다른 이동체 등)을 설명하여 주는 정보로, 객체의 종류와 수에 대한 정보를 포함한다. 4) 상태 정보는 해당 구역의 상태를 설명하여 주는 정보로, 혼잡도(객체들의 응집도, 이동 가능 속도 등)와 위험 요소(장애물, 방해물, 화재, 침수, 사고 발생 등)에 대한 정보를 포함한다.3) Object information is information that describes objects (people, delivery robots, other moving objects, etc.) in the area, and includes information about the type and number of objects. 4) Status information is information that explains the status of the area, and includes information on congestion (cohesion of objects, possible movement speed, etc.) and risk factors (obstacles, obstructions, fire, flooding, accidents, etc.).
한편 S140단계에서 상황인지 정보는 배송로봇의 위치정보, 즉, 배송로봇이 컨텍스트를 획득한 위치의 구역 정보와 함께 제공된다. 위치정보는 컨텍스트를 컨텍스트 맵에서 해당 구역에 매칭시키는데 필요하기 때문이다.Meanwhile, in step S140, situation awareness information is provided along with location information of the delivery robot, that is, area information of the location where the delivery robot acquired the context. This is because location information is needed to match the context to the corresponding area in the context map.
컨텍스트들이 획득되면, 획득된 컨텍스트들을 2D 그리드 맵의 해당 구역들에 각각 매칭하여 컨텍스트 맵을 업데이트 한다(S150). S150단계에서 컨텍스트와 2D 그리드 맵 구역의 매칭은 컨텍스트와 함께 전송되는 위치정보를 참고로 이루어진다.When the contexts are acquired, the context map is updated by matching the acquired contexts to corresponding areas of the 2D grid map (S150). In step S150, matching between the context and the 2D grid map area is performed with reference to the location information transmitted along with the context.
도 3에는 컨텍스트를 2D 그리드 맵의 해당 구역에 매핑하여 컨텍스트 맵을 업데이트 한 결과를 나타내었다.Figure 3 shows the results of updating the context map by mapping the context to the corresponding area of the 2D grid map.
이하에서는 도 2에 제시된 방법에 의해 구축/업데이트 되는 컨텍스트 맵을 활용하여 배송로봇의 최적 배송경로를 탐색하는 방법에 대해 도 4를 참조하여 설명한다.Hereinafter, a method of searching for the optimal delivery route of a delivery robot using a context map built/updated by the method shown in FIG. 2 will be described with reference to FIG. 4.
도 4는 본 발명의 일 실시예에 따른 최적 실내 배송경로 탐색 방법의 설명에 제공되는 흐름도이다.Figure 4 is a flow chart provided to explain the optimal indoor delivery route search method according to an embodiment of the present invention.
실내 배송경로 탐색을 위해, 컨텍스트 맵을 참고로 구역들을 엣지들로 각각 연결한 그래프를 생성한다(S210). 그래프는 컨텍스트 맵의 한 구역에서 이동 가능한 다른 구역들을 엣지들로 연결한 경로들의 집합니다.To explore an indoor delivery route, a graph is created in which each area is connected by edges, referring to the context map (S210). A graph is a collection of paths that connect edges from one area of the context map to other movable areas.
도 5에는 S210단계에서 생성가능한 그래프를 예시하였다. 예시된 그래프는 컨텍스트 맵에 구역이 4개인 경우를 상정하였다. 제시된 그래프에 따르면 구역-1에서는 구역-2와 구역-3으로 이동 가능하지만, 구역-4로 이동하는 것은 불가능하다. 마찬가지로, 구역-2에서는 구역-1과 구역-3으로 이동 가능하지만 구역-4로 이동하는 것은 불가능하고, 구역-3에서는 구역-1, 구역-2, 구역-3 모두로 이동가능하며, 구역-4에서는 구역-3으로만 이동 가능하다.Figure 5 illustrates a graph that can be generated in step S210. The example graph assumes the case where there are 4 regions in the context map. According to the presented graph, it is possible to move from Zone-1 to Zone-2 and Zone-3, but it is impossible to move to Zone-4. Similarly, in Zone-2, you can move to Zone-1 and Zone-3, but you cannot move to Zone-4. In Zone-3, you can move to Zone-1, Zone-2, and Zone-3, and in Zone-3, you can move to Zone-1 and Zone-3. In 4, you can only move to area-3.
다음 그래프에서 구역들을 연결하는 엣지들 각각에 대한 이동 시간을 예측하고(S220), 예측된 이동 시간들을 해당 엣지들에 각각 기입한다(S230).In the next graph, the travel time for each of the edges connecting the zones is predicted (S220), and the predicted travel times are entered into each of the corresponding edges (S230).
S220단계에서의 이동 시간 예측은 컨텍스트 맵에서 각 구역들에 매칭되어 있는 컨텍스트들을 참조로 이루어진다. 구역들에 매칭된 컨텍스트들 중 이동 시간에 영향을 미치는 컨텍스트들은 최대 속도, 혼잡도(객체들의 응집도, 이동 가능 속도 등), 위험 요소(장애물, 방해물, 화재, 침수, 사고 발생 등)이다.The travel time prediction in step S220 is made with reference to the contexts matched to each zone in the context map. Among the contexts matched to zones, the contexts that affect travel time are maximum speed, congestion (cohesion of objects, possible movement speed, etc.), and risk factors (obstacles, obstructions, fire, flooding, accidents, etc.).
이동 시간 예측시, 이동체의 이동 속도는 최대 속도를 넘지 않도록 하여야 하고, 혼잡도나 위험 요소에 따라 감소된다. 한편 위험 요소로 인해 이동이 불가능한 엣지의 경우 이동 시간은 무한대(∞)로 예측할 수 있다.When predicting travel time, the moving speed of the moving object should not exceed the maximum speed and is reduced depending on congestion or risk factors. Meanwhile, in the case of edges where movement is impossible due to risk factors, the movement time can be predicted to be infinite (∞).
예측된 이동 시간들이 S230단계에 의해 엣지들에 각각 기입된 결과를 도 6에 예시하였다.The results of the predicted travel times written to the edges in step S230 are shown in Figure 6.
다시 도 4를 참조하여 설명한다.This will be described again with reference to FIG. 4 .
S210단계 내지 S230단계를 통해 그래프가 완성되면, 그래프를 이용하여 최적 실내 배송경로를 결정한다(S240). S240단계에서 결정되는 최적 배송경로는 전체 이동시간이 가장 짧은 경로이다.When the graph is completed through steps S210 to S230, the optimal indoor delivery route is determined using the graph (S240). The optimal delivery route determined in step S240 is the route with the shortest overall travel time.
S240단계를 위한 경로 탐색 기법으로 다익스트라 알고리즘(Dijkstra Algorithm)을 이용할 수 있다. 물론 그 밖의 다른 경로 탐색 알고리즘을 이용하는 것을 배제하지 않는다.The Dijkstra Algorithm can be used as a path search technique for step S240. Of course, the use of other route search algorithms is not excluded.
도 7은 본 발명의 다른 실시예에 따른 배송경로 탐색 시스템의 블럭도이다. 본 발명의 실시예에 따른 배송경로 탐색 시스템은 도시된 바와 같이, 통신부(310), 프로세서(320) 및 저장부(330)를 포함하여 구축된다.Figure 7 is a block diagram of a delivery route search system according to another embodiment of the present invention. As shown, the delivery route search system according to an embodiment of the present invention is constructed including a communication unit 310, a processor 320, and a storage unit 330.
배송경로 탐색 시스템은 이동체에 의해 수행될 수 있지만, 이동체의 리소스가 충분하지 않은 경우에는 컨텍스트 맵 구축 시스템에 의해 수행되는 것으로 구현할 수도 있다. 이하에서는 후자를 상정한다.The delivery route search system can be performed by a mobile entity, but if the mobile entity does not have sufficient resources, it can also be implemented as being performed by a context map construction system. Below, the latter is assumed.
통신부(310)는 실내 환경에서 이동하는 배송로봇과 상호 통신을 위한 수단이다.The communication unit 310 is a means for mutual communication with a delivery robot moving in an indoor environment.
프로세서(320)는 실내 환경에 대한 2D 그리드 맵을 생성하고, 통신부(310)를 통해 배송로봇들로부터 획득되는 컨텍스트들을 2D 그리드 맵에 매칭하여 컨텍스트 맵을 생성하고 업데이트하며, 컨텍스트 맵을 필요로 하는 배송로봇에 대해서는 통신부(310)를 통해 컨텍스트 맵을 제공한다.The processor 320 generates a 2D grid map for the indoor environment, matches the contexts obtained from delivery robots through the communication unit 310 to the 2D grid map, creates and updates the context map, and generates and updates the context map. A context map is provided to the delivery robot through the communication unit 310.
또한 프로세서(320)는 도 4에 제시된 방법에 따라 최적 실내 배송경로를 탑색하고, 탐색된 실내배송 경로를 통신부(310)를 통해 배송로봇에 제공한다.Additionally, the processor 320 searches for an optimal indoor delivery route according to the method shown in FIG. 4 and provides the discovered indoor delivery route to the delivery robot through the communication unit 310.
저장부(330)는 프로세서(320)가 컨텍스트 맵을 구축/업데이트하고 최적 실내 배송경로를 탐색함에 있어 필요로 하는 저장 공간을 제공한다.The storage unit 330 provides the storage space necessary for the processor 320 to build/update the context map and search for the optimal indoor delivery route.
지금까지 자율주행 및 관제를 위한 컨텍스트 맵 구축 방법에 대해 바람직한 실시예를 들어 상세히 설명하였다.So far, the context map construction method for autonomous driving and traffic control has been described in detail with preferred embodiments.
본 발명의 실시예에서는 구체적인 컨텍스트를 포함하는 컨텍스트 맵을 구축/업데이트하여, 기존의 맵들 보다 더 구체적인 컨텍스트를 제공함으로써, 최적의 실내 배송경로를 탐색할 수 있도록 하고, 예상 배송 시간을 비교적 정확하게 예측할 수 있도록 하였다.In an embodiment of the present invention, a context map containing specific context is built/updated to provide more specific context than existing maps, enabling the search for the optimal indoor delivery route and predicting the expected delivery time relatively accurately. It was allowed to happen.
그리고 컨텍스트 맵은 그리드 형태로써 실내 환경의 각 구역들을 구분함으로써, 컨텍스트에 대한 매칭의 편의와 위치 정확도를 향상시켰다.And the context map uses a grid format to distinguish each area of the indoor environment, improving the convenience of context matching and location accuracy.
위 실시예에서는 컨텍스트 맵에 반영되는 컨텍스트들을 배송로봇들이 획득하는 것을 상정하였다. 하지만 배송로봇 이외에도 실내 환경을 이동하고 있는 다른 이동체들이 컨텍스트를 획득하는 것도 가능하며, 이동체가 아닌 고정 설비, 이를 테면, 천정이나 벽에 설치되어 있는 CCTV 카메라나 환경 센서들도 컨텍스트를 획득하는 것으로 확장 가능하다.In the above example, it was assumed that delivery robots acquire the contexts reflected in the context map. However, in addition to delivery robots, it is also possible for other mobile objects moving in an indoor environment to acquire context, and it is also possible to acquire context for fixed facilities other than mobile objects, such as CCTV cameras or environmental sensors installed on the ceiling or walls. possible.
이 때 동일 구역에 대해 동일 시점에 다수의 컨텍스트들이 획득되는 경우가 있을 수 있다. 이 경우 획득된 컨텍스트들을 해당 구역에 매칭시켜야 하는데, 문제는 컨텍스트의 내용이 다른 경우이다.At this time, there may be cases where multiple contexts are acquired at the same time for the same area. In this case, the obtained contexts must be matched to the corresponding area, but the problem is when the contents of the context are different.
이 경우에는 컨텍스트를 해당 구역에 매칭함에 있어, 컨텍스트 획득 장치의 종류에 따라 우선순위를 두어 운용하는 것이 가능하다. 배송로봇과 CCTV 카메라에 의해 컨텍스트들이 획득된 경우를 상정하면, 우선순위는 다음과 같이 부여할 수 있다.In this case, when matching the context to the corresponding area, it is possible to prioritize operation according to the type of context acquisition device. Assuming that contexts are acquired by delivery robots and CCTV cameras, priority can be assigned as follows.
1) 크기 정보(해당 구역의 경로에 대한 너비와 높이)에 대해서는, 고정설비인 CCTV 카메라에 의해 획득된 컨텍스트를 신뢰하여, 해당 구역의 크기 정보는 CCTV 카메라에 의해 획득된 정보를 매칭1) Regarding size information (width and height of the path of the area), the context acquired by the CCTV camera, which is a fixed equipment, is trusted, and the size information of the area matches the information acquired by the CCTV camera.
2) 객체 정보(사람, 차량 등)에 대해서는, 이동체인 배송로봇에 의해 획득된 컨텍스트를 신뢰하여, 해당 구역의 객체 정보는 배송로봇에 의해 획득된 정보를 매칭2) For object information (people, vehicles, etc.), the context acquired by the mobile chain delivery robot is trusted, and the object information in the area matches the information acquired by the delivery robot.
3) 상태 정보 중 혼잡도(객체들의 응집도, 이동 가능 속도 등)에 대해서는, CCTV 카메라에 의해 획득된 컨텍스트를 신뢰하여, 해당 구역의 혼잡도 정보는 CCTV 카메라에 의해 획득된 정보를 매칭3) Regarding the congestion level among the status information (cohesion of objects, possible movement speed, etc.), the context obtained by the CCTV camera is trusted, and the congestion information of the area matches the information obtained by the CCTV camera.
4) 상태 정보 중 위험 요소(장애물, 방해물, 화재, 침수, 사고발생, 범죄 등)에 대해서는, 배송로봇에 의해 획득된 컨텍스트를 신뢰하여, 해당 구역의 위험 요소 정보는 배송로봇에 의해 획득된 정보를 매칭4) Regarding risk factors (obstacles, obstructions, fire, flooding, accidents, crimes, etc.) among status information, the context acquired by the delivery robot is trusted, and the risk factor information in the area is information acquired by the delivery robot. matching
한편, 본 실시예에 따른 장치와 방법의 기능을 수행하게 하는 컴퓨터 프로그램을 수록한 컴퓨터로 읽을 수 있는 기록매체에도 본 발명의 기술적 사상이 적용될 수 있음은 물론이다. 또한, 본 발명의 다양한 실시예에 따른 기술적 사상은 컴퓨터로 읽을 수 있는 기록매체에 기록된 컴퓨터로 읽을 수 있는 코드 형태로 구현될 수도 있다. 컴퓨터로 읽을 수 있는 기록매체는 컴퓨터에 의해 읽을 수 있고 데이터를 저장할 수 있는 어떤 데이터 저장 장치이더라도 가능하다. 예를 들어, 컴퓨터로 읽을 수 있는 기록매체는 ROM, RAM, CD-ROM, 자기 테이프, 플로피 디스크, 광디스크, 하드 디스크 드라이브, 등이 될 수 있음은 물론이다. 또한, 컴퓨터로 읽을 수 있는 기록매체에 저장된 컴퓨터로 읽을 수 있는 코드 또는 프로그램은 컴퓨터간에 연결된 네트워크를 통해 전송될 수도 있다.Meanwhile, of course, the technical idea of the present invention can be applied to a computer-readable recording medium containing a computer program that performs the functions of the device and method according to this embodiment. Additionally, the technical ideas according to various embodiments of the present invention may be implemented in the form of computer-readable code recorded on a computer-readable recording medium. A computer-readable recording medium can be any data storage device that can be read by a computer and store data. For example, of course, computer-readable recording media can be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc. Additionally, computer-readable codes or programs stored on a computer-readable recording medium may be transmitted through a network connected between computers.
또한, 이상에서는 본 발명의 바람직한 실시예에 대하여 도시하고 설명하였지만, 본 발명은 상술한 특정의 실시예에 한정되지 아니하며, 청구범위에서 청구하는 본 발명의 요지를 벗어남이 없이 당해 발명이 속하는 기술분야에서 통상의 지식을 가진자에 의해 다양한 변형실시가 가능한 것은 물론이고, 이러한 변형실시들은 본 발명의 기술적 사상이나 전망으로부터 개별적으로 이해되어져서는 안될 것이다.In addition, although preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the invention pertains without departing from the gist of the present invention as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

Claims (12)

  1. 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵을 획득하는 단계;Obtaining a context map in which contexts are respectively mapped to corresponding zones;
    컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하는 단계;Creating a graph connecting movable areas in the context map with edges;
    컨텍스트 맵을 참고로, 엣지들 각각에 대한 이동 시간들을 예상하는 단계;With reference to the context map, predicting travel times for each of the edges;
    예상된 이동 시간들을 해당 엣지들에 각각 기입하는 단계; 및Entering the expected travel times into the respective edges; and
    그래프를 이용하여, 최적 배송경로를 결정하는 단계;를 포함하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method comprising: determining an optimal delivery route using a graph.
  2. 청구항 1에 있어서,In claim 1,
    컨텍스트들은,The contexts are,
    해당 구역의 경로에 대한 정보, 해당 구역에 있는 객체들에 대한 정보, 해당 구역의 상태에 대한 정보를 포함하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method comprising information on the route in the area, information on objects in the area, and information on the status of the area.
  3. 청구항 2에 있어서,In claim 2,
    해당 구역의 경로에 대한 정보는,For information on routes in this area,
    경로의 너비와 높이 및 최대 속도를 포함하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method including the width and height of the route and maximum speed.
  4. 청구항 3에 있어서,In claim 3,
    상태에 대한 정보는,For information about the status,
    해당 구역의 혼잡도, 위험 요소에 대한 정보를 포함하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method that includes information on congestion and risk factors in the area.
  5. 청구항 4에 있어서,In claim 4,
    예상 단계는,The expected steps are:
    해당 구역에 대한 경로의 최대 속도, 혼잡도, 위험 요소에 대한 정보를 참고로, 엣지들 각각에 대한 이동 시간들을 예상하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method characterized by predicting travel times for each edge with reference to information on the maximum speed, congestion, and risk factors of the route for the corresponding area.
  6. 청구항 5에 있어서,In claim 5,
    예상 단계는,The expected steps are:
    위험 요소로 인해 이동이 불가능한 엣지에 대해서는 이동 시간을 무한대로 예측하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method characterized by predicting infinite travel time for edges where movement is impossible due to risk factors.
  7. 청구항 1에 있어서,In claim 1,
    결정 단계는,The decision step is,
    다익스트라 알고리즘(Dijkstra Algorithm)을 이용하여, 그래프로부터 최적 배송경로를 결정하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method characterized by determining the optimal delivery route from a graph using the Dijkstra Algorithm.
  8. 청구항 1에 있어서,In claim 1,
    컨텍스트 맵은,The context map is,
    실내 환경의 2D 맵을 생성하고, 실내 환경의 해당 구역들에서 컨텍스트들을 획득하며, 획득된 상황인지 정보들을 2D 맵의 해당 구역들에 각각 매칭하여 생성하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method characterized by generating a 2D map of the indoor environment, acquiring contexts from corresponding areas of the indoor environment, and matching the obtained situational awareness information to corresponding areas of the 2D map.
  9. 청구항 8에 있어서,In claim 8,
    컨텍스트들은,The contexts are,
    다수의 배송로봇들로부터 획득되는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method characterized by being obtained from a plurality of delivery robots.
  10. 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하고, 컨텍스트 맵을 참고로 엣지들 각각에 대한 이동 시간들을 예상하며, 예상된 이동 시간들을 해당 엣지들에 각각 기입하고, 그래프를 이용하여 최적 배송경로를 결정하는 프로세서; 및In the context map where the contexts are mapped to each of the corresponding areas, a graph is created connecting the moveable areas with edges, the travel times for each of the edges are estimated with reference to the context map, and the expected travel times are calculated accordingly. A processor that writes to each edge and determines the optimal delivery route using a graph; and
    프로세서에 필요한 저장공간을 제공하는 저장부;를 포함하는 것을 특징으로 하는 배송경로 탐색 시스템.A delivery route search system comprising a storage unit that provides storage space necessary for the processor.
  11. 컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하는 단계;Creating a graph connecting movable areas with edges in a context map in which contexts are mapped to the corresponding areas;
    컨텍스트 맵을 참고로, 엣지들 각각에 대한 이동 시간들을 예상하는 단계;With reference to the context map, predicting travel times for each of the edges;
    예상된 이동 시간들을 해당 엣지들에 각각 기입하는 단계;Entering the expected travel times into the respective edges;
    그래프를 이용하여, 최적 배송경로를 결정하는 단계; 및Determining an optimal delivery route using a graph; and
    결정된 최적 배송경로를 배송로봇에 제공하는 단계;를 포함하는 것을 특징으로 하는 배송경로 탐색 방법.A delivery route search method comprising: providing the determined optimal delivery route to a delivery robot.
  12. 배송로봇과 통신 연결하는 통신부; 및A communication department that connects communication with delivery robots; and
    컨텍스트들이 해당 구역들에 각각 매핑되어 있는 컨텍스트 맵에서 이동 가능한 구역들을 엣지들로 각각 연결한 그래프를 생성하고, 컨텍스트 맵을 참고로 엣지들 각각에 대한 이동 시간들을 예상하며, 예상된 이동 시간들을 해당 엣지들에 각각 기입하고, 그래프를 이용하여 최적 배송경로를 결정하며, 결정된 최적 배송경로를 통신부를 통해 배송로봇에 제공하는 프로세서;를 포함하는 것을 특징으로 하는 배송경로 탐색 시스템.In the context map where the contexts are mapped to each of the corresponding areas, a graph is created connecting the moveable areas with edges, the travel times for each of the edges are estimated with reference to the context map, and the expected travel times are calculated accordingly. A delivery route search system comprising a processor that writes to each edge, determines the optimal delivery route using a graph, and provides the determined optimal delivery route to the delivery robot through a communication unit.
PCT/KR2022/016137 2022-10-21 2022-10-21 Robot-based optimal indoor delivery path planning method using context map WO2024085285A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020220136235A KR102529332B1 (en) 2022-10-21 2022-10-21 Robot-based optimal indoor delivery path planning method with context map
KR10-2022-0136235 2022-10-21

Publications (1)

Publication Number Publication Date
WO2024085285A1 true WO2024085285A1 (en) 2024-04-25

Family

ID=86381282

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/016137 WO2024085285A1 (en) 2022-10-21 2022-10-21 Robot-based optimal indoor delivery path planning method using context map

Country Status (2)

Country Link
KR (1) KR102529332B1 (en)
WO (1) WO2024085285A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160210591A1 (en) * 2015-01-19 2016-07-21 9316-2832 Quebec Inc. System and Method for Managing and Optimizing Delivery Networks
JP2021111237A (en) * 2020-01-14 2021-08-02 三東運輸株式会社 Route calculation program, route optimization system, and route calculation method
KR102337531B1 (en) * 2020-07-08 2021-12-09 네이버랩스 주식회사 Method and system for specifying node for robot path plannig
KR20220134928A (en) * 2021-03-29 2022-10-06 네이버랩스 주식회사 Method and system for controling driving of robot
KR20220138438A (en) * 2021-02-26 2022-10-13 현대자동차주식회사 Apparatus for generating multi path of moving robot and method thereof

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160210591A1 (en) * 2015-01-19 2016-07-21 9316-2832 Quebec Inc. System and Method for Managing and Optimizing Delivery Networks
JP2021111237A (en) * 2020-01-14 2021-08-02 三東運輸株式会社 Route calculation program, route optimization system, and route calculation method
KR102337531B1 (en) * 2020-07-08 2021-12-09 네이버랩스 주식회사 Method and system for specifying node for robot path plannig
KR20220138438A (en) * 2021-02-26 2022-10-13 현대자동차주식회사 Apparatus for generating multi path of moving robot and method thereof
KR20220134928A (en) * 2021-03-29 2022-10-06 네이버랩스 주식회사 Method and system for controling driving of robot

Also Published As

Publication number Publication date
KR102529332B1 (en) 2023-05-08

Similar Documents

Publication Publication Date Title
Vincent et al. Distributed multirobot exploration, mapping, and task allocation
EP3351024A1 (en) Landmark location determination
CN113821029A (en) Path planning method, device, equipment and storage medium
EP4141599B1 (en) Multi-robot route planning
CN110515390A (en) Aircraft Autonomous landing method and device, electronic equipment, storage medium
CN112650244A (en) Multi-floor automatic mapping method for mobile robot in building based on feature point matching
EP4180895A1 (en) Autonomous mobile robots for coverage path planning
CN114527753A (en) Man-machine integrated building path planning method, computer device and program product
WO2018012855A1 (en) Hierarchical graph-based path searching method, and path searching method in internet of things environment, using same
Jose et al. Optimization based routing model for the dynamic path planning of emergency vehicles
CN115079701A (en) Unmanned vehicle and unmanned aerial vehicle cooperative path planning method
Hoshino et al. Dynamic partitioning strategies for multi-robot patrolling systems
CN112015187A (en) Semantic map construction method and system for intelligent mobile robot
CN113568400A (en) Robot control method and device, electronic equipment and storage medium
CN113358118B (en) End-to-end autonomous navigation method for indoor mobile robot in unstructured environment
WO2024085285A1 (en) Robot-based optimal indoor delivery path planning method using context map
WO2014107000A1 (en) Guidance system and method for walking route
WO2024085286A1 (en) Method for establishing context map based on collaboration of drone and robot
WO2024085287A1 (en) Method for constructing context map for autonomous driving and control
KR102003640B1 (en) Intellectual signpost system for guiding room
CN116382322A (en) Device and method for searching collaborative area based on swarm unmanned plane
KR20130107062A (en) Apparatus and method of path planning for a plurality of moving bodies
Shell et al. Directional audio beacon deployment: an assistive multi-robot application
CN116774603B (en) Multi-AGV cooperative scheduling simulation platform and simulation method
Wang et al. A Diffusion-Based Reactive Approach to Road Network Cooperative Persistent Surveillance

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22962847

Country of ref document: EP

Kind code of ref document: A1