RoboCup Rescue as multiagent task allocation among teams: experiments with task interdependencies

Ferreira, Paulo R.; Santos, Fernando dos; Bazzan, Ana L. C.; Epstein, Daniel A.; Waskow, Samuel J.

doi:10.1007/s10458-009-9087-8

Cited by 40 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rescue robots are allocated to tasks, and re-assigned new tasks as the old tasks are completed. There are a variety of methods to assign tasks to robots, such as using a biologically-inspired approach [12], using coalition formation with spatial and temporal constraints [35], modeling the problem as a generalized allocation problem with task interdependencies [13], and developing predictive models [21]. We use the RoboCup Rescue simulator and existing algorithms designed for it as a test-bed for our weighted synergy graph model.…”

Section: Multi-robot Task Allocationmentioning

confidence: 99%

See 1 more Smart Citation

Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents

Liemhetcharat

Veloso

2014

Artificial Intelligence

View full text Add to dashboard Cite

Previous approaches to select agents to form a team rely on single-agent capabilities, and team performance is treated as a sum of such known capabilities. Motivated by complex team formation situations, we address the problem where both single-agent capabilities may not be known upfront, e.g., as in ad hoc teams, and where team performance goes beyond single-agent capabilities and depends on the specific synergy among agents. We formally introduce a novel weighted synergy graph model to capture new interactions among agents. Agents are represented as vertices in the graph, and their capabilities are represented as Normally-distributed variables. The edges of the weighted graph represent how well the agents work together, i.e., their synergy in a team. We contribute a learning algorithm that learns the weighted synergy graph using observations of performance of teams of only two and three agents. Further, we contribute two team formation algorithms, one that finds the optimal team in exponential time, and one that approximates the optimal team in polynomial time. We extensively evaluate our learning algorithm, and demonstrate the expressiveness of the weighted synergy graph in a variety of problems. We show our approach in a rich ad hoc team formation problem capturing a rescue domain, namely the RoboCup Rescue domain, where simulated robots rescue civilians and put out fires in a simulated urban disaster. We show that the weighted synergy graph outperforms a competing algorithm, thus illustrating the efficacy of our model and algorithms.

show abstract

Section: Multi-robot Task Allocationmentioning

confidence: 99%

“…Different approaches have been used to solve this problem, such as treating it as a generalized allocation problem [13], using a biologically-inspired approach [12], and extending coalition formation to handle spatial and temporal constraints [35].…”

Section: The Robocup Rescue Simulatormentioning

confidence: 99%

Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents

Liemhetcharat

Veloso

2014

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Ferreira et al [2] describe the problem of task allocation among teams as finding the assignment that maximizes the overall utility.…”

Section: Related Workmentioning

confidence: 99%

Shape control of cyclic networks in multi-robot formations

Eren¹

2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper addresses coalition formation, based on agent capabilities, centered on task allocation in emergency-response environments (EREs). EREs are environments that need fast task completion as their main requirement. We propose a team-based organization model, based on an existing organization model for adaptive complex systems. The model has some key characteristics that are beneficial for EREs: agents act in dynamic, open domains; agents collaborate in completing group tasks; agents may have similar types of capabilities, but at different levels; tasks need different agent capabilities, at collective different levels; and agents are supervised in a partially decentralized manner. We formulate task allocation as a capability-based coalition-formation problem, propose a greedy myopic algorithm to form coalitions, and compare it with F-Max-Sum, another efficient myopic algorithm. Experiments in which utility is measured show that the capability-based approach outperforms the role-based one. The numerical experiments suggest that the proposed task allocation method is possibly scalable with growing numbers of agents.

show abstract

“…For multi-robot system, paper [5] researched the task assignment of agent teams in RoboCupRescue project. In paper [6], the reinforcement learning algorithm for multi-robot is divided into two types: non-cooperation and cooperation.…”

Section: Introductionmentioning

confidence: 99%

A Mutli-Agent Task Allocation Model in Open-Space Emergency Evacuation Management

Du¹,

Zheng²,

Kan³

et al. 2013

IJHIT

View full text Add to dashboard Cite

Open-space emergency evacuation is the movement of people away the threat in the short time. Task allocation is a fundamental research challenge in emergency evacuation domain of multi-agent systems (MAS). This paper proposes the multi-agent task allocation model which is called EV-GAP. Accordingly, the capability of agent was redefined to satisfy the requirement of open-space emergency evacuation. Corresponding the task allocation algorithm based on EV-GAP has is also given. Finally, the experiment of the task allocation of open-space emergency evacuation for a chlorine leakage accident is completed to validate this model.

show abstract

RoboCup Rescue as multiagent task allocation among teams: experiments with task interdependencies

Cited by 40 publications

References 17 publications

Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents

Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents

Shape control of cyclic networks in multi-robot formations

A Mutli-Agent Task Allocation Model in Open-Space Emergency Evacuation Management

Contact Info

Product

Resources

About