We propose a distributed algorithm enabling a large team of robots to detect all intruders within a large planar environment. Each robot can only detect intruders and communicate with other robots within a limited range. No map of the... more
We propose a distributed algorithm enabling a large team of robots to detect all intruders within a large planar environment. Each robot can only detect intruders and communicate with other robots within a limited range. No map of the environment is given, and none is built during the process. Robots are only capable of following walls and other robots that are nearby. The algorithm puts together elementary behaviors giving robots the means to coordinate their movement in order to cover lines between opposite walls with their sensors and discover nearby new walls. A line has leading robots at its endpoints that follow walls and hence move the line of robots forward. Multiple such lines move through the entire assigned area in order to detect all intruders. The movement of multiple lines is coordinated by using a graph representation of the environment that describes possible line movements and their associated costs in terms of robots. This coordination requires only local communication between the leaders of different robot lines when they meet. Finally, we demonstrate how the algorithm can be implemented using elementary wall following and obstacle discovery behaviors.
In this study, motion planning and control scheme for a cooperative transportation system, which consists of a single object and multiple autonomous non-holonomic mobile robots, is proposed. Virtual leader-follower formation control... more
In this study, motion planning and control scheme for a cooperative transportation system, which consists of a single object and multiple autonomous non-holonomic mobile robots, is proposed. Virtual leader-follower formation control strategy is used for the cooperative transportation system. The object is assumed as the virtual leader of the system and the robots carrying the object are considered as follower robots. A smooth path is generated by considering the constraints of the virtual robot. The origin of the coordinate system attached to the center of gravity of the object tracks the generated path. A path for each follower robot is generated to keep the formation structure. The follower robots track their paths. A communication framework is used for the messaging between robots, and asymptotically stable tracking control is used for trajectory tracking. The proposed method is verified with real applications and simulations using Pioneer P3-DX mobile robots and a single object.
La robótica de enjambre trata de desarrollar sistemas multirrobot con algunas características de los enjambres de insectos. La principal ventaja de este enfoque es que permite la autoorganización de los robots a pesar de que cada uno de... more
La robótica de enjambre trata de desarrollar sistemas multirrobot con algunas características de los enjambres de insectos. La principal ventaja de este enfoque es que permite la autoorganización de los robots a pesar de que cada uno de ellos sólo conoce una parte limitada del entorno. Uno de los problemas que se deben afrontar en su construcción es el desarrollo de los comportamientos, para lo cual pueden seguirse distintas estrategias. Una de ellas consiste en dotar a los robots de controladores neuronales, de forma que sus acciones (salidas) estén determinadas por la información sensorial (entradas). Así se puede usar computación evolutiva para ajustar los pesos de la red, lo que se conoce como neuroevolución. En el presente trabajo se revisarán algunas de las investigaciones realizadas al respecto y se desarrollarán diversos comportamientos de enjambre sobre un entorno de simulación de alto nivel. En concreto, se usarán algoritmos genéticos para obtener comportamientos de agregación, dispersión–exploración, seguimiento de feromonas y lucha. Finalmente se analizarán los resultados obtenidos y se comentarán posibles líneas futuras de investigación.
This paper introduces a probabilistic model for multirobot surveillance applications with limited range and possibly faulty sensors. Sensors are described with a footprint and a false negative probability, i.e. the probability of failing... more
This paper introduces a probabilistic model for multirobot surveillance applications with limited range and possibly faulty sensors. Sensors are described with a footprint and a false negative probability, i.e. the probability of failing to report a target within their sensing range. The model implements a probabilistic extension to our formerly developed deterministic approach for modeling surveillance tasks in large environments with large robot teams known as Graph-Clear. This extension leads to a new algorithm that allows to answer new design and performance questions, namely 1) how many robots are needed to obtain a certain confidence that the environment is free from intruders, and 2) given a certain number of robots, how should they coordinate their actions to minimize their failure rate.
This paper presents a novel approach for the generation of residual in order to diagnose (detect and identify) sensor faults in a particular class of network based on multi-agent system (MAS). Specifically, the network under consideration... more
This paper presents a novel approach for the generation of residual in order to diagnose (detect and identify) sensor faults in a particular class of network based on multi-agent system (MAS). Specifically, the network under consideration is composed of local subsystems with nonlinear dynamics which are interconnected through a second-order consensus control law over one of their local states. The proposed methodology takes advantage of a model of the interconnection dynamics rather than nonlinear local models of each subsystem. Simulation results are provided to illustrate the use of the proposed scheme on a network of planar takeoff and landing vehicles (PVTOL) with consensus over the horizontal coordinate.
In this work, we approach the problem of a box transport by the robots that are requested to bring a box from an arbitrary initial to some preassigned target position. The robots are modeled as rational collaborative autonomous agents... more
In this work, we approach the problem of a box transport by the robots that are requested to bring a box from an arbitrary initial to some preassigned target position. The robots are modeled as rational collaborative autonomous agents working on their movement coordination in a discrete state space. The proposed method for coordinating the multirobot system is a two-level control model in which on the upper level, a Virtual Structure (VS) agent calculates offline the box trajectory from the initial to the goal position with incomplete obstacles data and informs the robots of the nominal route. The robots on the lower level, on the basis of the preassigned positions and the data about the unforeseen obstacles sensed by limited range sensors and exchanged among all the robots, individually optimize their local movement objective functions to mutually push the box following a preassigned trajectory in a safe manner. When the robots, due to the unforeseen obstacles, move from the trajectory defined by the VS agent too far away, more than a predefined distance, they contact the VS agent for the recalculation of the same. The results of the proposed coordination model's simulation in 2D environment are described.
Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there... more
Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there exists a number of techniques that can perform multi-robot task allocation quite efficiently, they hardly consider deadline for task completion while assigning tasks to the robots. A careful allocation is of paramount importance when there is an associated penalty with each of the tasks if it is not completed within a stipulated time. In this work, we develop an algorithm, called Minimum Penalty Scheduling (MPS) that allocates tasks among a group of robots with the goal that the overall penalty of executing all the tasks can be minimized. Our algorithm provides a robust, scalable, and near-optimal real-time task schedule. By comparing with the state-of-the-art algorithm, we show that MPS attracts up to 62.5% less penalty when a significant number o...
In this study, motion planning and control scheme for a cooperative transportation system, which consists of a single object and multiple autonomous non-holonomic mobile robots included forklifts, is proposed. Virtual leader-follower... more
In this study, motion planning and control scheme for a cooperative transportation system, which consists of a single object and multiple autonomous non-holonomic mobile robots included forklifts, is proposed. Virtual leader-follower formation control strategy is used for the cooperative transportation system. The object is assumed as the virtual leader of the system and the robots carrying the object on their forklifts are considered as follower robots. A smooth path is generated by considering the constraints of the virtual robot. The origin of the coordinate system attached to the center of gravity of the object tracks the generated path. A path for each follower robot is generated to keep the formation structure. The follower robots track their paths. A communication framework is used for the messaging between robots, and asymptotically stable tracking control is used for trajectory tracking. The proposed method is verified with real applications and simulations using Pioneer P3-DX mobile robots and a single object.
Abstract in English: In this study, a system providing indoor localization for the mobile robots is presented. The developed system is composed of two sub-systems. The first system is used to determine location of mobile robots. The... more
Abstract in English:
In this study, a system providing indoor localization for the mobile robots is presented. The developed system is composed of two sub-systems. The first system is used to determine location of mobile robots. The localization is performed by processing images captured from the overhead cameras. The cameras are mounted on the ceiling of the building as to cover whole working region of mobile robots. Functions are defined in these methods to compensate the distortions on the image; which are caused by the positions of the cameras, using wide angle lenses, and changing light amplitude. The local poses computed by using these functions are then converted into global values. The second system is used to provide the communication between the first system and the mobile robots. This study is presented with the applications realized with a mobile robot in real-time.
Abstract in Turkish:
Bu çalışmada, iç ortamlarda gezgin robotların seyrüseferleri esnasında ihtiyaç duydukları konum bilgilerini sağlamak için görüntü tabanlı bir sistem sunulmaktadır. Sunulan sistem, gezgin robotların çalışma alanını kapsayacak şekilde tavana yerleştirilmiş kameralardan alınan görüntülerden robotların konumlarının hesaplanması ve bu konum bilgilerinin robotlara ulaştırılması olarak iki kısımdan oluşmaktadır. Çalışmada kameralardan sağlanan görüntülerin kameranın pozisyonu, geniş açılı mercek kullanılması ve ortamdaki ışık şiddetinin değişmesi gibi nedenlerle bozulmasından dolayı, bu bozulmaları tanımlayan bir fonksiyon kullanılarak robotların konum bilgileri hesaplanmakta ve. her bir kameranın yerel koordinat sistemine göre hesaplanan konum bilgileri, küresel koordinat sistemine dönüştürülerek robotlara mesaj tabanlı bir haberleşme yapısı ile aktarılmaktadır. Geliştirilen bu konumlandırma sistemi, gerçek ortamda gezgin robot kullanılarak yapılan uygulamalar ile birlikte sunulmaktadır.
There is an increasing amount of research into the area of pervasive computing, smart homes and intelligent spaces, one example being that of the DTI-funded Pervasive Home Environment Networking (PHEN) project. Much of the current... more
There is an increasing amount of research into the area of pervasive computing, smart homes and intelligent spaces, one example being that of the DTI-funded Pervasive Home Environment Networking (PHEN) project. Much of the current research focuses on environments populated by numerous computing devices, sensors, actuators, various wired and wireless networking systems and poses the question of how such computing environments might become ‘intelligent’? Often, the proposed solution is to explicitly preprogram in the intelligence. In this paper we discuss a solution based on embeddedagents which enables emergent intelligent behaviour by predominantly implicit processes. We describe an experimental testbed for pervasive computing, the iDorm, and report on experiments that scope the agent-learning characteristics in such environments. We also introduce a more human-directed approach to programming in pervasive environments which we refer to as task-oriented programming (TOP).
Agent-Based Computing is a diverse research domain concerned with the building of intelligent software based on the concept of "agents". In this paper, we use Scientometric analysis to analyze all sub-domains of agent-based computing.... more
Agent-Based Computing is a diverse research domain concerned with the building of intelligent software based on the concept of "agents". In this paper, we use Scientometric analysis to analyze all sub-domains of agent-based computing. Our data consists of 1,064 journal articles indexed in the ISI web of knowledge published during a twenty year period: 1990-2010. These were retrieved using a topic search with various keywords commonly used in sub-domains of agent-based computing. In our proposed approach, we have employed a combination of two applications for analysis, namely Network Workbench and CiteSpace - wherein Network Workbench allowed for the analysis of complex network aspects of the domain, detailed visualization-based analysis of the bibliographic data was performed using CiteSpace. Our results include the identification of the largest cluster based on keywords, the timeline of publication of index terms, the core journals and key subject categories. We also identify the core authors, top countries of origin of the manuscripts along with core research institutes. Finally, our results have interestingly revealed the strong presence of agent-based computing in a number of non-computing related scientific domains including Life Sciences, Ecological Sciences and Social Sciences.
2 Intelligent Computing Research Group(GPCI) University Center of Bahia (FIB) Rua Xingu, nº. 179, Jardim Atalaia/STIEP. Salvador BA Brazil marcosimoes@fib.br, {helderfib, okvictorok, simonpiata}@yahoo.com.br, {hugodaluz,... more
2 Intelligent Computing Research Group(GPCI) University Center of Bahia (FIB) Rua Xingu, nº. 179, Jardim Atalaia/STIEP. Salvador BA Brazil marcosimoes@fib.br, {helderfib, okvictorok, simonpiata}@yahoo.com.br, {hugodaluz, jessy.meyer}@gmail.com
This paper presents an overview of the numerous results we recently published for the problem of multi-robot pursuit evasion. We review the Graph-Clear formalism we introduced, we summarize the variants we studied, and the main results we... more
This paper presents an overview of the numerous results we recently published for the problem of multi-robot pursuit evasion. We review the Graph-Clear formalism we introduced, we summarize the variants we studied, and the main results we derived. Finally, we outline directions for future research both in Graph-Clear and for pursuit-evasion and search problems in general.
In this paper we present a novel graph theoretic problem, called GRAPH-CLEAR, useful to model surveillance tasks where multiple robots are used to detect all possible intruders in a given indoor environment. We provide a formal definition... more
In this paper we present a novel graph theoretic problem, called GRAPH-CLEAR, useful to model surveillance tasks where multiple robots are used to detect all possible intruders in a given indoor environment. We provide a formal definition of the problem and we investigate its basic theoretical properties, showing that the problem is NP-complete. We then present an algorithm to compute a strategy for the restriction of the problem to trees and present a method how to use this solution in applications. The method is then tested in simple simulations. GRAPH-CLEAR is useful to describe multirobot pursuit evasion games when robots have limited sensing capabilities, i.e. multiple agents are needed to perform basic patrolling operations.
We address the problem of searching for moving targets in large outdoor environments represented by height maps. To solve the problem we present a complete system that computes from an annotated height map a graph representation and... more
We address the problem of searching for moving targets in large outdoor environments represented by height maps. To solve the problem we present a complete system that computes from an annotated height map a graph representation and search strategies based on worst-case assumptions about all targets. These strategies are then used to compute a schedule and task assignment for all agents. We improve the graph construction from previous work and for the first time present a method that computes a schedule to minimize the execution time. For this we consider travel times of agents determined by a path planner on the height map. We demonstrate the entire system in a real environment with an area of 700,000m2 in which eight human agents search for two intruders using mobile computing devices (iPads). To the best of our knowledge this is the first demonstration of a search system applied to such a large environment.
This paper presents the initial research results of Bahia Robotics Team. This is a new research group created to investigate the application of artificial intelligence methods in the standard problem of robotics soccer. In this work,... more
This paper presents the initial research results of Bahia Robotics Team. This is a new research group created to investigate the application of artificial intelligence methods in the standard problem of robotics soccer. In this work, fuzzy controllers are used to improve some abilities of the players. In the case of the attackers, the kick and the positioning ability were improved. The midfielders had their positioning and passing ability improved. The goalkeeper and the defenders had their positioning ability improved. The generated Bahia2D soccer team was tested in matches against some victorious teams from Robocup Brazil Open 2006 and from previous editions of the Robocup World Competition. The positive results achieved and the ongoing works to improve the current limitations are also presented.
Abstract. This paper presents the initial research results of Bahia Robotics Team. This is a new research group created to investigate the application of artificial intelligence methods in the standard problem of robotics soccer. In this... more
Abstract. This paper presents the initial research results of Bahia Robotics Team. This is a new research group created to investigate the application of artificial intelligence methods in the standard problem of robotics soccer. In this work, fuzzy controllers are used to improve some abilities of the players. In the case of the attackers, the kick and the positioning ability were improved. The midfielders had their positioning and passing ability improved. The goalkeeper and the defenders had their positioning ability improved. The generated Bahia2D soccer team was tested in matches against some victorious teams from Robocup Brazil Open 2006 and from previous editions of the Robocup World Competition. The positive results achieved and the ongoing works to improve the current limitations are also presented. Key Words: fuzzy logic, simulation, robotics soccer 1.
Distributed algorithms are presented that describe various degrees of cooperation between autonomous agents. The algorithms generate styles of cooperation that cover a whole spectrum, from total cooperation, to complete self-interest, to... more
Distributed algorithms are presented that describe various degrees of cooperation between autonomous agents. The algorithms generate styles of cooperation that cover a whole spectrum, from total cooperation, to complete self-interest, to absolute antagonism, to complete self-destruction and every mixture of these. A classification of cooperation styles is described. The algorithms act on the intentional states of the agents. To resolve goal conflicts, three compromise methods are considered: rank-based compromise using a simple ranking of goals, value-optimal compromise using costs and values with the branch-and-bound procedure, and a more efficient value-optimal compromise using a zero-one integer programming method that exploits goal dependencies.
Citation: Alpaslan Yufka, Metin Ozkan, Formation-Based Control Scheme for Cooperative Transportation by Multiple Mobile Robots, International Journal of Advanced Robotic Systems, 2015, 12:120. ISSN 1729-8806. DOI: 10.5772/60972.... more
Citation: Alpaslan Yufka, Metin Ozkan, Formation-Based Control Scheme for Cooperative Transportation by Multiple Mobile Robots, International Journal of Advanced Robotic Systems, 2015, 12:120. ISSN 1729-8806. DOI: 10.5772/60972.
Abstract: This paper presents a motion planning and control scheme for a cooperative transportation system comprising a single rigid object and multiple autonomous non-holonomic mobile robots. A leader-follower formation control strategy is used for the transportation system in which the object is assumed to be the virtual leader; the robots carrying the object are considered followers. A smooth trajectory between the current and desired locations of the object is generated by considering the constraints of the virtual leader. In the leader-follower approach, the origin of the coordinate system attached to the center of gravity of the object, which is known as the virtual leader, moves along the generated trajectory while the real robots, which are known as followers, maintain a desired distance and orientation to the leader. An asymptotically stable tracking controller is used for trajectory tracking. The proposed approach is verified by simulations and real applications using Pioneer P3-DX mobile robots.
Solvable Graphs (also known as Reachable Graphs) are types of graphs that any arrangement of a specified number of agents located on the graph’s vertices can be reached from any initial arrangement through agents’ moves along the graph’s... more
Solvable Graphs (also known as Reachable Graphs) are types of graphs that any arrangement of a specified number of agents located on the graph’s vertices can be reached from any initial arrangement through agents’ moves along the graph’s edges, while avoiding deadlocks (interceptions). In this paper, the properties of Solvable Graphs are investigated, and a new concept in multi agent motion planning, called Minimal Solvable Graphs is introduced. Minimal Solvable Graphs are the smallest graphs among Solvable Graphs in terms of the number of vertices. Also, for the first time, the problem of deciding whether a graph is Solvable for m agents is answered, and a new algorithm is presented for making an existing graph solvable and lean for a given number of agents. Finally, through an industrial example, it is demonstrated that how the findings of this paper can be used in designing and reshaping transportation networks (e.g. railways, traffic roads, AGV routs, robotic workspaces, etc.) for multiple moving agents such as trains, vehicles, and robots.
This paper presents a behavior-based solution to the problem of observing multiple mobile targets by multiple mobile robots. Robots sense targets using sensors and in addition exchange information about them with other robots. Workload is... more
This paper presents a behavior-based solution to the problem of observing multiple mobile targets by multiple mobile robots. Robots sense targets using sensors and in addition exchange information about them with other robots. Workload is shared between different robots by requesting help when targets are escaping and supporting robots requesting such help. We provide a detailed description of the proposed solution, as well as significant simulation tests to outline its performance. The described approach outperforms formerly proposed solutions.
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists... more
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists that can act as a common frame of reference for these varied works. As a result, much duplication of research is evidenced in the
Underwater exploration is an important task in many aspects like surveying shipwrecks, observing the seabed and depth. Since, it is fatal for humans to venture into such depth, robots are deployed to accomplish them. Exploration is done... more
Underwater exploration is an important task in many aspects like surveying shipwrecks, observing the seabed and depth. Since, it is fatal for humans to venture into such depth, robots are deployed to accomplish them. Exploration is done by solving the Simultaneous Localization and Mapping (SLAM), one of the most fundamental concept in robotics. Due to the large expanse of sea and limitations of underwater communication, it is tedious to accomplish the task using a single AUV. Multi-robot systems are known to be more efficient and versatile compared to single robot. Hence, a system of multiple Autonomous Underwater Vehicles(AUVs) is a better option for mapping the ocean. However, underwater communication is a big challenge in underwater activities since traditional methods like Ground Positioning System (GPS) or radio signals prove to be futile under water. In limitation of these constraints, acoustic signals or image data is used for underwater operations. SLAM using multiple AUVs can result in a faster process since the robots can share their respective maps with one another. A decentralized SLAM approach is taken in this project where all the AUVs communicate on one-to-one basis instead of a single central server. To ensure a complete map coverage, Ant Colony Optimization (ACO), a route optimization algorithm is employed on each robot. The robot are assigned specific areas to explore by dividing the map based on their initial positions. Hence, an algorithm is devised through this project for building a multi-AUV system to be used in mapping the ocean floor. All the simulations have been done using Python language.
Inspired by the new achievements in mobile robotics having as a result mobile robots able to execute different production tasks, we consider a factory producing a set of distinct products via or with the additional help of mobile robots.... more
Inspired by the new achievements in mobile robotics having as a result mobile robots able to execute different production tasks, we consider a factory producing a set of distinct products via or with the additional help of mobile robots. This particularly flexible layout requires the definition and the solution of a complex planning and scheduling problem. In order to minimize production costs, dynamic determination of the number of robots for each production task and the individual robot allocation are needed. We propose a solution in terms of a two-level decentralized Multi-Agent System (MAS) framework: at the first, production planning level, agents are tasks which compete for robots (resources at this level); at the second, scheduling level, agents are robots which reallocate themselves among different tasks to satisfy the requests coming from the first level. An iterative auction based negotiation protocol is used at the first level while the second level solves a Multi-Robot Task Allocation (MRTA) problem through a distributed version of the Hungarian Method. A comparison of the results with a centralized approach is presented.
Highlights
► Factories producing different goods with additional mobile resources (robots). ► A two-level multi-agent system framework for production planning and scheduling. ► First: allocate robots to fulfill demands with minimum production cost. ► An iterative auction method inspired by Lagrangean relaxation is adopted. ► Second: robots (re)schedule themselves with a distributed version of Hungarian method.
In this paper, we study a distributed intelligent multi-robot system (MRS) in assembly setting where robots have partially overlapping capabilities. We treat the problem of the system's self-(re)configurability and self-optimization. In... more
In this paper, we study a distributed intelligent multi-robot system (MRS) in assembly setting where robots have partially overlapping capabilities. We treat the problem of the system's self-(re)configurability and self-optimization. In this light, we propose a distributed and optimized robots configuration and scheduling system ORCAS which integrates the MRS configuration based on semantic descriptions with process scheduling.
In this paper, we consider a decentralized approach to the multi-agent target allocation problem where agents are partitioned in two groups and every member of each group is a possible target for the members of the opposite group. Each... more
In this paper, we consider a decentralized approach to the multi-agent target allocation problem where agents are partitioned in two groups and every member of each group is a possible target for the members of the opposite group. Each agent has a limited communication range (radius) and individual preferences for the target allocation based on its individual local utility function. Furthermore, all agents are mobile and the allocation is achieved through a proposed dynamic iterative auction algorithm. Every agent in each step finds its best target based on the auction algorithm and the exchange of information with connected agents and moves towards it without any insight in the decision-making processes of other agents in the system. In the case of connected communication graph among all agents, the algorithm results in an optimal allocation solution. We explore the deterioration of the allocation solution in respect to the decrease of the quantity of the information exchanged amon...
In this study, a path smoothing strategy is proposed for sensor-based coverage problems. Smooth paths are generated for the coverage problems considering mobile robot kinematics constraints. An open agent architecture-based control... more
In this study, a path smoothing strategy is proposed for sensor-based coverage problems. Smooth paths are generated for the coverage problems considering mobile robot kinematics constraints. An open agent architecture-based control structure is used to implement the proposed approach on real robots. The algorithm is coded with C++ and implemented on P3-DX mobile robots in MobileSim simulation environments. It is
In this study, a path smoothing strategy is proposed for sensor-based coverage problems. Smooth paths are generated for the coverage problems considering mobile robot kinematics constraints. An open agent architecture-based control... more
In this study, a path smoothing strategy is proposed for sensor-based coverage problems. Smooth paths are generated for the coverage problems considering mobile robot kinematics constraints. An open agent architecture-based control structure is used to implement the proposed approach on real robots. The algorithm is coded with C++ and implemented on P3-DX mobile robots in MobileSim simulation environments. It is shown that the proposed approach smoothes the curves and robot easily turns the corners. As a result of this, the completion time of the coverage decreases.
The main contribution of this paper is an im- proved algorithm for the GRAPH-CLEAR problem, a novel NP-complete graph theoretic problem we recently introduced as a tool to model multi-robot surveillance tasks. The proposed al- gorithm... more
The main contribution of this paper is an im- proved algorithm for the GRAPH-CLEAR problem, a novel NP-complete graph theoretic problem we recently introduced as a tool to model multi-robot surveillance tasks. The proposed al- gorithm combines two previously developed solving techniques and produces strategies that require less robots to be executed. We provide a theoretical framework useful to identify the conditions for the existence of an optimal solution under special circumstances, and a set of mathematical tools characterizing the problem being studied. Finally we also identify a set of open questions deserving more investigations.
This paper describes a research about fuzzy controllers for the positioning of the goalkeeper without the ball in the 2d simulated robot soccer. The goal of this research was to improve the behavior of the goalkeeper, raising the number... more
This paper describes a research about fuzzy controllers for the positioning of the goalkeeper without the ball in the 2d simulated robot soccer. The goal of this research was to improve the behavior of the goalkeeper, raising the number of catches and decreasing the number of goals, improving its positioning to catch the ball. To validate the research, 30 matches were simulated against some of the best teams of the world that participate of the RoboCup. The achieved results are presented, the conclusions are discussed and future works are suggested.
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists... more
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists that can act as a common frame of reference for these varied works. As a result, much duplication of research is evidenced in the literature. This paper seeks to fill this important gap by outlining “for the first time” a formal field of research that has hitherto gone unacknowledged, namely the field of Mixed Reality Agents (MiRAs), which are defined as agents embodied in a Mixed Reality environment.
Based on this definition, a taxonomy is offered that classifies MiRAs along three axes: agency, based on the weak and strong notions outlined by Wooldridge and Jennings (1995); corporeal presence, which describes the degree of virtual or physical representation (body) of a MiRA; and interactive capacity, which characterises its ability to sense and act on the virtual and physical environment.
Furthermore, this paper offers the first comprehensive survey of the state-of-the-art of MiRA research and places each project within the proposed taxonomy. Finally, common trends and future directions for MiRA research are discussed.
By defining Mixed Reality Agents as a formal field, establishing a common taxonomy, and retrospectively placing existing MiRA projects within it, future researchers can effectively position their research within this landscape, thereby avoiding duplication and fostering reuse and interoperability.
ABSTRACT In this paper, we present a self-deployment strategy for a swarm of robots that is capable of exploring and identifying victims in an unknown structured building environment while preserving a global network interconnectivity for... more
ABSTRACT In this paper, we present a self-deployment strategy for a swarm of robots that is capable of exploring and identifying victims in an unknown structured building environment while preserving a global network interconnectivity for information exchange. The strategy are conducted in two phases: self-displacement shifting the robotic swarm from room to room, and self-dispersion and aggregation for exploration and coverage in each room. A decentralised control is built up by decentralised node control governing the dispersion and aggregation and decentralised connectivity control guaranteeing the global network preservation. The self-deployment strategy reduces significantly number of the robots while increasing its capacity of exploration and coverage. The simulation results illustrate technical aspects of the robotic swarm with the application of exploration, search and rescue services.
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists... more
In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology — both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists that can act as a common frame of reference for these varied works. As a result, much duplication of research is evidenced in the
Multi-UAV applications can be analyzed from the point of view of a complex system. Request-oriented deployment is a category of complex systems, in which the UAVs (the set of resources) are used to meet demands of the task requests (the... more
Multi-UAV applications can be analyzed from the point of view of a complex system. Request-oriented deployment is a category of complex systems, in which the UAVs (the set of resources) are used to meet demands of the task requests (the set of needs). Task requests require aircrafts to attend to an occurrence location, perform a task on it and, finally, return and land on an available location. Literature proposes centralized, decentralized and hybrid strategies to coordinate such systems. This paper proposes a centralized framework, in which a single coordinator handles the task requests and assign UAVs to answer to these requests by means of the ground control station. The strategy aims at cost optimization, relying on mission partitioning and the analysis of multi-variables (such as wind bearing, battery state-of-charge, maneuvers and spatial position). The communication interface of the UAVs with the coordinator is formally defined by automata, which are generated on-the-fly based on configuration parameters provided by the human operator. Simulation results show that the framework is functional, safe and versatile in terms of custom cost optimization.
In this paper, we propose two decentralized approximate algorithms for nested Gaussian processes in multirobot systems. The distributed implementation is achieved with iterative and consensus methods that facilitate local computations at... more
In this paper, we propose two decentralized approximate algorithms for nested Gaussian processes in multirobot systems. The distributed implementation is achieved with iterative and consensus methods that facilitate local computations at the expense of inter-robot communications. Moreover, we propose a covariance-based nearest neighbor robot selection strategy that enables a subset of agents to perform predictions. In addition, both algorithms are proved to be consistent. Empirical evaluations with real data illustrate the efficiency of the proposed algorithms.
Robots assist rescuers in search and rescue operations. An area of research that can significantly benefit search and rescue operations, if integrated, is cooperative robotics, since a multi-robot team can cover a vast area more... more
Robots assist rescuers in search and rescue operations. An area of research that can significantly benefit search and rescue operations, if integrated, is cooperative robotics, since a multi-robot team can cover a vast area more efficiently than a single robot system. The research discussed in this paper focuses on the need for cooperative search and rescue robots, the related research in literature, and the design of a control architecture that will support the requirements of a cooperation system for search and rescue applications.
In this work we address the Multi-Robot Task Allocation Problem (MRTA). We assume that the decision making environment is decentralized with as many decision makers (agents) as the robots in the system. To solve this problem, we developed... more
In this work we address the Multi-Robot Task Allocation Problem (MRTA). We assume that the decision making environment is decentralized with as many decision makers (agents) as the robots in the system. To solve this problem, we developed a distributed version of the Hungarian Method for the assignment problem. The robots autonomously perform different substeps of the Hungarian algorithm on the base of the individual and the information received through the messages from the other robots in the system. It is assumed that each robot agent has an information regarding its distance from the targets in the environment. The inter-robot communication is performed over a connected dynamic communication network and the solution to the assignment problem is reached without any common coordinator or a shared memory of the system. The algorithm comes up with a global optimum solution in O(n3) cumulative time (O(n2) for each robot), with O(n3) number of messages exchanged among the n robots.
We describe a new application domain for intelligent autonomous systems – intelligent buildings. We show how a building can be regarded as a machine and how behaviour-based principles first proposed by Brooks for mobile-robot control can... more
We describe a new application domain for intelligent autonomous systems – intelligent buildings. We show how a building can be regarded as a machine and how behaviour-based principles first proposed by Brooks for mobile-robot control can be applied to enable autonomous intelligent-building agents to adapt their control to suit the occupants. In other words we will argue that "an intelligent building is a robot that we live inside". We present a novel approach to the implementation of Intelligent Buildings based on a multi embedded-agent architecture comprising a low-level behaviour based reactive layer together with a high- level deliberative layer based on evidential learning (a case-like learning mechanism). We also present a hierarchical agent architecture in which mobile agents (residing on body wearable devices) and fixed agents (residing in buildings) can be integrated, opening new commercial and personal possibilities. We discuss how this architecture is being implemented, using a combination of IP and Lonworks networking technology together with a Java programming environment. We consider future directions of this work, in particular how it might play a key role in intelligent interactive environments enabled by emerging technologies such as mobile phones and embedded-internet devices.
The researchers and oil companies are trying to take some precaution for the problem of oil spill in sea, river or on ground etc. A lot of work concerned by removing the oil from water, there were many advanced tools for this task This... more
The researchers and oil companies are trying to take some precaution for the problem of oil spill in sea, river or on ground etc. A lot of work concerned by removing the oil from water, there were many advanced tools for this task This paper presents a multi-robot system that works on the surface of water to help cleaning up marine oil spills using a skimmer as a collecting tool, the aim of this multi-robot system is to surround the oil spill in certain position for fast and easy cleaning and prevent it from spreading wider.
In this paper we present a method to extract surveillance graphs from occupancy grid maps. Surveillance graphs are part of the Graph-Clear framework and model the problem of detecting targets using multiple robots with limited range... more
In this paper we present a method to extract surveillance graphs from occupancy grid maps. Surveillance graphs are part of the Graph-Clear framework and model the problem of detecting targets using multiple robots with limited range sensors. Robots can only execute basic actions called sweep and block on vertices and edges, respectively. Sweep detects targets in vertices and block prevents them from crossing edges. The extracted graphs accurately model the complexity of the planar environment to be searched, and are constructed as duals of the Voronoi Diagram. We give a geometric embedding for blocking and sweeping actions of the graph into the environment by directly associating them to sweep lines that robots cover with their sensors. This paper solves two open problems, namely the generation of surveillance graphs and the implementation of actions on a robot team. Sweep lines can then be directly translated into control inputs to the robot team. The new method is superior to previous heuristics for the extraction of graphs not only through its direct geometric relationship to the environment, but also due to its increased performance in direct experimental comparisons. Additionally, it provides a basis for possible theoretical results regarding the optimal coordination of multiple robots to detect targets in an arbitrary planar environment.