MASS: Multi-Agent Scheduling System for Intelligent Surveillance

Noh, DongKi; Choi, Junho; Choi, Jeongsik; Byun, Dasol; Kim, Young-Jae; Kim, Hyoung-Rock; Baek, Seung-Min; Lee, SeungHwan; Myung, Hyun

doi:10.1109/ur55393.2022.9826281

Cited by 6 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cyclic coverage method [28] can be applied to various maps as shown in Figure 10. (SLAM data set published on Ref.…”

Section: Simulation Results Of Cyclic Coveragementioning

confidence: 99%

Coverage Technology of Autonomous Mobile Mapping Robots

Lee¹

2023

Autonomous Mobile Mapping Robots

Self Cite

View full text Add to dashboard Cite

The coverage technique is one of the essential applications of autonomous mobile mapping robots. There are various approaches for coverage depending on the model (model/non-model), robot systems (single/multi), and its purpose (patrol/cleaning). Coverage components include viewpoint generation and path planning approaches, which are described as CPP research work. Particularly, in surveillance systems, coverage techniques, such as spanning tree, cyclic coverage, and area-based coverage, are reviewed specifically, which can be expanded for multi-robot systems. In addition, required coverage techniques according to conditions for intelligent surveillance systems are summarized. Lastly, several issues on coverage, specifically cyclic coverage, are described and considered.

show abstract

“…The cyclic coverage method [28] can be applied to various maps as shown in Figure 10. (SLAM data set published on Ref.…”

Section: Simulation Results Of Cyclic Coveragementioning

confidence: 99%

Coverage Technology of Autonomous Mobile Mapping Robots

Lee¹

2023

Autonomous Mobile Mapping Robots

Self Cite

View full text Add to dashboard Cite

show abstract

“…Research on CPP is being conducted in various fields, including sanitation robots [15], harvesting robots [16], vacuum cleaning robots [17], and surveillance robots [3]. These studies primarily focus on coverage completeness and minimizing the overlap of coverage paths [18][19][20].…”

Section: Related Workmentioning

confidence: 99%

“…The tour was distributed to the robots. In [3], these studies were enhanced and expanded for MCPP. The nodes to be visited were generated based on the normal vector direction of the given map by considering the sensing range (SR).…”

Section: Related Workmentioning

confidence: 99%

“…Additionally, processes such as path partitioning and recombination were added to achieve balanced paths. In this study, the graph construction method using the normal vectors of the map [3] is also employed. Unlike previous works, area-based structures as well as path-based structures are considered in our general MCPP framework for surveillance systems.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, research on multirobot coverage path planning (MCPP) has been actively conducted for various purposes such as unmanned large space surveillance, cleaning, lawn mowing, and crevasse exploration [1][2][3][4][5]. Among them, cleaning and lawn mowing are tasks that are only allowed to directly visit all areas, regardless of the sensing range (SR) of the robot.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical Area-Based and Path-Based Heuristic Approaches for Multirobot Coverage Path Planning with Performance Analysis in Surveillance Systems

Gong,

Lee

2023

Sensors

Self Cite

View full text Add to dashboard Cite

In this study, we present a systematic exploration of hierarchical designs for multirobot coverage path planning (MCPP) with a special focus on surveillance applications. Unlike conventional studies centered on cleaning tasks, our investigation delves into the realm of surveillance problems, specifically incorporating the sensing range (SR) factor equipped on the robots. Conventional path-based MCPP strategies considering SR, primarily rely on naive approaches, generating nodes (viewpoints) to be visited and a global path based on these nodes. Therefore, our study proposes a general MCPP framework for surveillance by dealing with path-based and area-based structures comprehensively. As the traveling salesman problem (TSP) solvers, our approach incorporates not the naive approach but renowned and powerful algorithms such as genetic algorithms (GAs), and ant colony optimization (ACO) to enhance the planning process. We devise six distinct methods within the proposed MCPP framework. Two methods adopt area-based approaches which segments areas via a hierarchical max-flow routing algorithm based on SR and the number of robots. TSP challenges within each area are tackled using a GA or ACO, and the result paths are allocated to individual robots. The remaining four methods are categorized by the path-based approaches with global–local structures such as GA-GA, GA-ACO, ACO-GA, and ACO-ACO. Unlike conventional methods which requires a global path, we further incorporate ACO- or GA-based local planning. This supplementary step at the local level enhances the quality of the path-planning results, particularly when dealing with a large number of nodes, by preventing any degradation in global path-planning outcomes. An extensive comparative analysis is conducted to evaluate the proposed framework based on execution time, total path length, and idle time. The area-based approaches tend to show a better execution time and overall path length performance compared to the path-based approaches. However, the path-based MCPP methods have the advantage of having a smaller idle time than the area-based MCPP methods. Our study finds that the proposed area-based MCPP method excels in path planning, while the proposed path-based MCPP method demonstrates superior coverage balance performance. By selecting an appropriate MCPP structure based on the specific application requirements, leveraging the strengths of both methodologies, efficient MCPP execution becomes attainable. Looking forward, our future work will focus on tailoring these MCPP structures to diverse real-world conditions, aiming to propose the most suitable approach for specific applications.

show abstract

An Efficient Coverage Area Re-Assignment Strategy for Multi-Robot Long-Term Surveillance

Lee

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

This study deals with a new strategy of the re-assignment for multi-robot seamless coverage tasks using the concept of propagation in a multi-robot surveillance system (MRSS). In the context of MRSSs, multi-robot coverage tasks play a critical role. These tasks require generating paths for two or more robots to cover an entire area, with the objective of minimizing the time needed to complete the task. However, over time, robots may need to be excluded from coverage missions due to issues such as battery charging or malfunctions. It is important to handle these situations efficiently in order to maintain the completeness and balance of the coverage mission. Typically, it can be resolved by either recomputing the coverage algorithm for the remaining robots or redistributing the coverage task of the excluded robot to its neighbors. However, in the proposed method, the amount of coverage area of the excluded robot is equally and efficiently assigned to the remaining robots. First off, a relational graph between robots and a tree based on the excluded robot are sequentially constructed to necessarily know how the robots are geometrically arranged in the given area centered on the excluded robot. The excluded robot becomes the root of the tree, and the depth of the tree indicates the proximity of the coverage areas. Subsequently, the amount of the original coverage area of the excluded robot can be differently assigned to its nearest neighbor robots according to the size of the subtree. Then, the coverage area of the robots corresponding to the second level of the tree are added from the partial coverage area of their parent robot to keep their coverage area balanced, respectively. The similar process is continuously performed, such as 'propagation', until the re-assignment of the coverage area over the leaf nodes is complete. Finally, balanced coverage area is re-assigned to the remaining robots, which is time-efficiently computed. Simulations were performed on two occupancy grid maps that were acquired from a simultaneous localization and mapping method. The proposed method was evaluated against conventional methods on three factors such as the balanced re-assignment of the coverage area (Balancing), the variation of the individual coverage area before and after the re-assignment process (Seamless Coverage), and the total computational efficiency over time (Time-efficiency). The coverage area was uniformly re-allocated after the proposed method was applied. In addition, the proposed method had a short calculation time and enables seamless coverage even after re-allocation. In the future, probabilistic maps related to the importance rate, accident rate, and crowds in the coverage area will also be taken into consideration.

show abstract

MASS: Multi-Agent Scheduling System for Intelligent Surveillance

Cited by 6 publications

References 14 publications

Coverage Technology of Autonomous Mobile Mapping Robots

Coverage Technology of Autonomous Mobile Mapping Robots

Hierarchical Area-Based and Path-Based Heuristic Approaches for Multirobot Coverage Path Planning with Performance Analysis in Surveillance Systems

An Efficient Coverage Area Re-Assignment Strategy for Multi-Robot Long-Term Surveillance

Contact Info

Product

Resources

About