Results 1  10
of
108
Coverage Control for Mobile Sensing Networks
, 2002
"... This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functio ..."
Abstract

Cited by 582 (49 self)
 Add to MetaCart
This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closedloop behavior is adaptive, distributed, asynchronous, and verifiably correct.
Cooperative MultiAgent Learning: The State of the Art
 Autonomous Agents and MultiAgent Systems
, 2005
"... Cooperative multiagent systems are ones in which several agents attempt, through their interaction, to jointly solve tasks or to maximize utility. Due to the interactions among the agents, multiagent problem complexity can rise rapidly with the number of agents or their behavioral sophistication. ..."
Abstract

Cited by 182 (8 self)
 Add to MetaCart
(Show Context)
Cooperative multiagent systems are ones in which several agents attempt, through their interaction, to jointly solve tasks or to maximize utility. Due to the interactions among the agents, multiagent problem complexity can rise rapidly with the number of agents or their behavioral sophistication. The challenge this presents to the task of programming solutions to multiagent systems problems has spawned increasing interest in machine learning techniques to automate the search and optimization process. We provide a broad survey of the cooperative multiagent learning literature. Previous surveys of this area have largely focused on issues common to specific subareas (for example, reinforcement learning or robotics). In this survey we attempt to draw from multiagent learning work in a spectrum of areas, including reinforcement learning, evolutionary computation, game theory, complex systems, agent modeling, and robotics. We find that this broad view leads to a division of the work into two categories, each with its own special issues: applying a single learner to discover joint solutions to multiagent problems (team learning), or using multiple simultaneous learners, often one per agent (concurrent learning). Additionally, we discuss direct and indirect communication in connection with learning, plus open issues in task decomposition, scalability, and adaptive dynamics. We conclude with a presentation of multiagent learning problem domains, and a list of multiagent learning resources. 1
Collaborative Multiagent Reinforcement Learning by Payoff Propagation
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2006
"... In this article we describe a set of scalable techniques for learning the behavior of a group of agents in a collaborative multiagent setting. As a basis we use the framework of coordination graphs of Guestrin, Koller, and Parr (2002a) which exploits the dependencies between agents to decompose t ..."
Abstract

Cited by 65 (2 self)
 Add to MetaCart
In this article we describe a set of scalable techniques for learning the behavior of a group of agents in a collaborative multiagent setting. As a basis we use the framework of coordination graphs of Guestrin, Koller, and Parr (2002a) which exploits the dependencies between agents to decompose the global payoff function into a sum of local terms. First, we deal with the singlestate case and describe a payoff propagation algorithm that computes the individual actions that approximately maximize the global payoff function. The method can be viewed as the decisionmaking analogue of belief propagation in Bayesian networks. Second, we focus on learning the behavior of the agents in sequential decisionmaking tasks. We introduce different modelfree reinforcementlearning techniques, unitedly called Sparse Cooperative Qlearning, which approximate the global actionvalue function based on the topology of a coordination graph, and perform updates using the contribution of the individual agents to the maximal global action value. The combined use of an edgebased decomposition of the actionvalue function and the payoff propagation algorithm for efficient action selection, result in an approach that scales only linearly in the problem size. We provide experimental evidence that our method outperforms related multiagent reinforcementlearning methods based on temporal differences.
A multirobot system for continuous area sweeping tasks,
 in Proceedings of the IEEE Conference on Robotics and Automation
, 2006
"... ..."
(Show Context)
PursuitEvasion on Trees by Robot Teams
, 2010
"... We present GraphClear, a novel pursuitevasion problem on graphs which models the detection of intruders in complex indoor environments by robot teams. The environment is represented by a graph, and a robot team can execute sweep and block actions on vertices and edges respectively. A sweep action ..."
Abstract

Cited by 25 (4 self)
 Add to MetaCart
We present GraphClear, a novel pursuitevasion problem on graphs which models the detection of intruders in complex indoor environments by robot teams. The environment is represented by a graph, and a robot team can execute sweep and block actions on vertices and edges respectively. A sweep action detects intruders in a vertex and represents the capability of the robot team to detect intruders in the region associated to the vertex. Similarly, a block action prevents intruders from crossing an edge and represents the capability to detect intruders as they move between regions. Both actions may require multiple robots to be executed. A strategy is a sequence of block and sweep actions detecting all intruders. When solving instances of GraphClear the goal is to determine optimal strategies, i.e. strategies using the least number of robots. We prove that for the general case of graphs the problem of computing optimal strategies is NPhard. Next, for the special case of trees we provide a polynomial time algorithm. The algorithm ensures that throughout the execution of the strategy all cleared vertices form a connected subtree, and we show it produces optimal strategies.
Task Allocation via SelfOrganizing Swarm Coalitions in Distributed Mobile Sensor Network
 In: Proceedings of the American Association of Artificial Intelligence
, 2004
"... This paper presents a task allocation scheme via selforganizing swarm coalitions for distributed mobile sensor network coverage. Our approach uses the concepts of ant behavior to selfregulate the regional distributions of sensors in proportion to that of the moving targets to be tracked in a nons ..."
Abstract

Cited by 22 (5 self)
 Add to MetaCart
(Show Context)
This paper presents a task allocation scheme via selforganizing swarm coalitions for distributed mobile sensor network coverage. Our approach uses the concepts of ant behavior to selfregulate the regional distributions of sensors in proportion to that of the moving targets to be tracked in a nonstationary environment. As a result, the adverse effects of task interference between robots are minimized and sensor network coverage is improved. Quantitative comparisons with other tracking strategies such as static sensor placement, potential fields, and auctionbased negotiation show that our approach can provide better coverage and greater flexibility to respond to environmental changes.
Multirobot surveillance: an improved algorithm for the graphclear problem
 In Proc. IEEE Intl. Conf. on Robotics and Automation
, 2008
"... Abstract—The main contribution of this paper is an improved algorithm for the GRAPHCLEAR problem, a novel NPcomplete graph theoretic problem we recently introduced as a tool to model multirobot surveillance tasks. The proposed algorithm combines two previously developed solving techniques and p ..."
Abstract

Cited by 20 (6 self)
 Add to MetaCart
(Show Context)
Abstract—The main contribution of this paper is an improved algorithm for the GRAPHCLEAR problem, a novel NPcomplete graph theoretic problem we recently introduced as a tool to model multirobot surveillance tasks. The proposed algorithm 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. I.
Extracting surveillance graphs from robot maps
 In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
, 2008
"... Abstract — GRAPHCLEAR is a recently introduced theoretical framework to model surveillance tasks accomplished by multiple robots patrolling complex indoor environments. In this paper we provide a first step to close the loop between its graphbased theoretical formulation and practical scenarios. ..."
Abstract

Cited by 18 (7 self)
 Add to MetaCart
(Show Context)
Abstract — GRAPHCLEAR is a recently introduced theoretical framework to model surveillance tasks accomplished by multiple robots patrolling complex indoor environments. In this paper we provide a first step to close the loop between its graphbased theoretical formulation and practical scenarios. We show how it is possible to algorithmically extract suitable socalled surveillance graphs from occupancy grid maps. We also identify local graph modification operators, called contractions, that alter the graph being extracted so that the original surveillance problem can be solved using less robots. The algorithm we present is based on the Generalized Voronoi Diagram, a structure that can be simply computed using watershed like algorithms. Our algorithm is evaluated by processing maps produced by mobile robots exploring indoor environments. It turns out that the proposed algorithm is fast, robust to noise, and opportunistically modifies the graph so that less expensive strategies can be computed. I.
Toward the Automated Synthesis of Cooperative Mobile Robot Teams
 In Proceedings of SPIE Mobile Robots XIII
, 1998
"... A current limitation in the realworld use of cooperating mobile robots is the difficulty in determining the proper team composition for a given robotic application. Present technology restricts the design and implementation of cooperative robot teams to the expertise of a robotics researcher, who h ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
A current limitation in the realworld use of cooperating mobile robots is the difficulty in determining the proper team composition for a given robotic application. Present technology restricts the design and implementation of cooperative robot teams to the expertise of a robotics researcher, who has to develop robot teams on an applicationspecific basis. The objective of our research is to reduce the complexity of cooperative robotic systems through the development of a methodology that enables the automated synthesis of cooperative robot teams. We propose an approach to this problem that uses a combination of the theories of sensoricomputational systems and information invariants, building on the earlier work of Donald, Rus, et al. We describe the notion of defining equivalence classes that serve as fundamental building blocks of more complex cooperative mobile robot behaviors. We postulate a methodology for framing mission requirements in terms of the goals and constraints of the ...
A SamplingBased Motion Planning Approach to Maintain Visibility of Unpredictable Targets
 Auton. Robots
, 2005
"... This paper deals with the surveillance problem of computing the motions of one or more robot observers in order to maintain visibility of one or several moving targets. The targets are assumed to move unpredictably, and the distribution of obstacles in the workspace is assumed to be known in advan ..."
Abstract

Cited by 17 (2 self)
 Add to MetaCart
(Show Context)
This paper deals with the surveillance problem of computing the motions of one or more robot observers in order to maintain visibility of one or several moving targets. The targets are assumed to move unpredictably, and the distribution of obstacles in the workspace is assumed to be known in advance.