Evolved multi-agent systems and thorough evaluation are necessary for scalable logistics (position paper)

We consider logistics problems that are both dynamic and potentially large scale. A common way to create a scalable solution for logistics problems is to use multi-agent systems. In this paper we take two positions of a different nature: (1) evolutionary designed multi-agent systems are a promising approach to create scalable and performant solutions for logistics problems, (2) the multi-agent systems field does not prioritize evaluation enough, which hinders thorough scientific comparisons and prevents adoption in industry. We present arguments and refute common counterarguments for our position. Further, we discuss our present and upcoming efforts to realize our position.

[1]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[2]  Dario Floreano,et al.  Evolved swarming without positioning information: an application in aerial communication relay , 2009, Auton. Robots.

[3]  El-Ghazali Talbi,et al.  Flexible Variable Neighborhood Search in Dynamic Vehicle Routing , 2011, EvoApplications.

[4]  A. Fabri,et al.  On dynamic pickup and delivery vehicle routing with several time windows and waiting times , 2006 .

[5]  Monique Calisti,et al.  An adaptive solution to dynamic transport optimization , 2005, AAMAS '05.

[6]  David B. Knoester,et al.  Digitally Evolving Models for Dynamically Adaptive Systems , 2007, International Workshop on Software Engineering for Adaptive and Self-Managing Systems (SEAMS '07).

[7]  Michel Gendreau,et al.  Neighborhood Search Heuristics for a Dynamic Vehicle Dispatching Problem with Pick-ups and Deliveries , 2006 .

[8]  Gilbert Laporte,et al.  Parallel Tabu search heuristics for the dynamic multi-vehicle dial-a-ride problem , 2004, Parallel Comput..

[9]  Michel Gendreau,et al.  Diversion Issues in Real-Time Vehicle Dispatching , 2000, Transp. Sci..

[10]  Tom Holvoet,et al.  Evolutionary synthesis of multi-agent systems for dynamic dial-a-ride problems , 2012, GECCO '12.

[11]  George Rzevski,et al.  Multi-Agent Real Time Scheduling System for Taxi Companies , 2009 .

[12]  Gilbert Laporte,et al.  Dynamic pickup and delivery problems , 2010, Eur. J. Oper. Res..

[13]  Klaus Fischer,et al.  Cooperative Transportation Scheduling: An Application Domain for DAI , 1996, Appl. Artif. Intell..

[14]  Darrel C. Ince,et al.  The case for open computer programs , 2012, Nature.

[15]  Ke Tang,et al.  A developmental solution to (dynamic) capacitated arc routing problems using genetic programming , 2012, GECCO '12.

[16]  Richard F. Hartl,et al.  A survey on pickup and delivery problems , 2008 .

[17]  John R. Koza,et al.  Human-competitive results produced by genetic programming , 2010, Genetic Programming and Evolvable Machines.

[18]  Adil Qureshi,et al.  Evolving agents , 1996 .

[19]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[20]  Martijn Mes,et al.  Comparison of agent-based scheduling to look-ahead heuristics for real-time transportation problems , 2007, Eur. J. Oper. Res..

[21]  Gilbert Laporte,et al.  Waiting strategies for the dynamic pickup and delivery problem with time windows , 2004 .

[22]  Russell Bent,et al.  Waiting and Relocation Strategies in Online Stochastic Vehicle Routing , 2007, IJCAI.

[23]  Peter A. Whigham,et al.  Grammar-based Genetic Programming: a survey , 2010, Genetic Programming and Evolvable Machines.

[24]  Marius M. Solomon,et al.  Recent Developments in Dynamic Vehicle Routing Systems , 2008 .

[25]  Barbara Messing,et al.  An Introduction to MultiAgent Systems , 2002, Künstliche Intell..

[26]  L. Darrell Whitley,et al.  Evolving cooperative strategies for UAV teams , 2005, GECCO '05.

[27]  Sophie N. Parragh,et al.  A survey on pickup and delivery models Part II : Transportation between pickup and delivery locations , 2007 .

[28]  Jürgen Branke *,et al.  Anticipation and flexibility in dynamic scheduling , 2005 .

[29]  Dario Floreano,et al.  Genetic Team Composition and Level of Selection in the Evolution of Cooperation , 2009, IEEE Transactions on Evolutionary Computation.

[30]  Sean Luke,et al.  Genetic Programming Produced Competitive Soccer Softbot Teams for RoboCup97 , 1998 .

[31]  Rob A. Zuidwijk,et al.  Can agents measure up? A comparative study of an agent-based and on-line optimization approach for a drayage problem with uncertainty , 2010 .

[32]  Michael Affenzeller,et al.  Agent-Based Simulation of Dispatching Rules in Dynamic Pickup and Delivery Problems , 2009, 2009 2nd International Symposium on Logistics and Industrial Informatics.

[33]  Bernd Scholz-Reiter,et al.  Generating dispatching rules for semiconductor manufacturing to minimize weighted tardiness , 2010, Proceedings of the 2010 Winter Simulation Conference.

[34]  Richard F. Hartl,et al.  A survey on pickup and delivery problems , 2008 .

[35]  Giselher Pankratz,et al.  Dynamic vehicle routing by means of a genetic algorithm , 2005 .

[36]  Jörg P. Müller,et al.  COOPERATIVE TRANSPORTATION SCHEDULING : AN APPLICATION DOMAIN FOR DAI , 1996 .

[37]  Tom De Wolf,et al.  Towards a Methodology for Engineering Self-Organising Emergent Systems , 2005, SOAS.

[38]  Kagan Tumer,et al.  Evolving large scale UAV communication system , 2012, GECCO '12.

[39]  Michel Gendreau,et al.  Exploiting Knowledge About Future Demands for Real-Time Vehicle Dispatching , 2006, Transp. Sci..

[40]  Tom Holvoet,et al.  RinSim: A Simulator for Collective Adaptive Systems in Transportation and Logistics , 2012, 2012 IEEE Sixth International Conference on Self-Adaptive and Self-Organizing Systems.

[41]  Lee Spector,et al.  Evolving teamwork and coordination with genetic programming , 1996 .

[42]  Sean Luke,et al.  Cooperative Multi-Agent Learning: The State of the Art , 2005, Autonomous Agents and Multi-Agent Systems.

[43]  Peter A. N. Bosman,et al.  Computationally Intelligent Online Dynamic Vehicle Routing by Explicit Load Prediction in an Evolutionary Algorithm , 2006, PPSN.

[44]  Sophie N. Parragh,et al.  A survey on pickup and delivery problems Part I : Transportation between customers and depot , 2007 .

[45]  Jörg P. Müller,et al.  A Model for Cooperative Transportation Scheduling , 1995, ICMAS.

[46]  David B. Knoester,et al.  Constructing Communication Networks with Evolved Digital Organisms , 2012, 2012 IEEE Sixth International Conference on Self-Adaptive and Self-Organizing Systems.