Multiagent Coordination by Auctioning POMDP Tasks

We present a procedure for the estimation of bids in auction protocols. This class of protocols is of interest to multiagent systems because they can be used to coordinate the assignment of tasks to agents. The main idea is to take advantage of methods for the synthesis of task execution controllers that rely on the availability of value functions. These provide a natural way to obtain the bid values for a given task. The approach is demonstrated on an active surveillance system, where mobile robots must approach and identify humans, and conduct patrols. The Partially Observable Markov Decision Process (POMDP) framework is used to compute policies for the execution of tasks by each agent, the task bid values are obtained directly from the respective value functions. Several simulation examples are presented for an urban surveillance environment, illustrating the applicability of our ideas.

[1]  Maja J. Mataric,et al.  Multi-robot task allocation: analyzing the complexity and optimality of key architectures , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[2]  Milind Tambe,et al.  The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models , 2011, J. Artif. Intell. Res..

[3]  Nikos A. Vlassis,et al.  Optimal and Approximate Q-value Functions for Decentralized POMDPs , 2008, J. Artif. Intell. Res..

[4]  Neil Immerman,et al.  The Complexity of Decentralized Control of Markov Decision Processes , 2000, UAI.

[5]  Sven Koenig,et al.  Sequential Bundle-Bid Single-Sale Auction Algorithms for Decentralized Control , 2007, IJCAI.

[6]  Michael Brydon.  Economic metaphors for solving intrafirm allocation problems: What does a market buy us? , 2006, Decis. Support Syst..

[7]  Nidhi Kalra,et al.  Market-Based Multirobot Coordination: A Survey and Analysis , 2006, Proceedings of the IEEE.

[8]  Luis Montano,et al.  Comparative experiments on optimization criteria and algorithms for auction based multi-robot task allocation , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[9]  P. Poupart.  Exploiting structure to efficiently solve large scale partially observable Markov decision processes , 2005 .

[10]  Nikos A. Vlassis,et al.  Perseus: Randomized Point-based Value Iteration for POMDPs , 2005, J. Artif. Intell. Res..

[11]  Nawwaf N. Kharma,et al.  A high performance algorithm for static task scheduling in heterogeneous distributed computing systems , 2008, J. Parallel Distributed Comput..

[12]  Milos Hauskrecht,et al.  Value-Function Approximations for Partially Observable Markov Decision Processes , 2000, J. Artif. Intell. Res..

[13]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[14]  Shlomo Zilberstein,et al.  Formal models and algorithms for decentralized decision making under uncertainty , 2008, Autonomous Agents and Multi-Agent Systems.

[15]  Lynne E. Parker,et al.  ALLIANCE: an architecture for fault tolerant multirobot cooperation , 1998, IEEE Trans. Robotics Autom..

[16]  Rainer E. Burkard,et al.  Selected topics on assignment problems , 2002, Discret. Appl. Math..

[17]  Maja J. Mataric,et al.  Sold!: auction methods for multirobot coordination , 2002, IEEE Trans. Robotics Autom..

[18]  Tim Roughgarden,et al.  Algorithmic Game Theory , 2007 .

[19]  Reid G. Smith,et al.  The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver , 1980, IEEE Transactions on Computers.

[20]  J. Andrade-Cetto,et al.  Ubiquitous networking robotics in urban settings , 2006 .

[21]  Frank Werner,et al.  A comparison of scheduling algorithms for flexible flow shop problems with unrelated parallel machines, setup times, and dual criteria , 2009, Comput. Oper. Res..