Coordinating very large groups of wide area search munitions

Coordinating hundreds or thousands of unmanned aerial vehicles (UAVs), presents a variety of new exciting challenges, over and above the challenges of building single UAVs and small teams of UAVs. We are specifically interested in coordinating large groups of Wide Area Search Munitions (WASMs), which are part UAV and part munition. We are developing a “flat”, distributed organization to provide the robustness and flexibility required by a group where team members will frequently leave. Building on established teamwork theory and infrastructure we are able to build large teams that can achieve complex goals using completely distributed intelligence. However, as the size of the team is increased, new issues arise that require novel algorithms. Specifically, key algorithms that work well for relatively small teams, fail to scale up to very large teams. We have developed novel algorithms meeting the requirements of large teams for the tasks of instantiating plans, sharing information and allocating roles. We have implemented these algorithms in reusable software proxies using the novel design abstraction of a coordination agent that encapsulates a piece of coordination protocol. We illustrate the effectiveness of the approach with 200 WASMs coordinating to find and destroy ground based targets in support of a manned

[1]  Maria L. Gini,et al.  A team of robotic agents for surveillance , 2000, AGENTS '00.

[2]  Keith S. Decker,et al.  Coordinated hospital patient scheduling , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[3]  Hiroaki Kitano,et al.  RoboCup Rescue: search and rescue in large-scale disasters as a domain for autonomous agents research , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[4]  Katia Sycara,et al.  Team-Oriented Agent Coordination in the RETSINA Multi-Agent System , 2002 .

[5]  Alexander G. Gray,et al.  An Integrated System for Multi-Rover Scientific Exploration , 1999, AAAI/IAAI.

[6]  Gil Tidhar,et al.  On team knowledge and common knowledge , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[7]  Victor R. Lesser,et al.  The UMASS intelligent home project , 1999, AGENTS '99.

[8]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[9]  Katia P. Sycara,et al.  Designing behaviors for information agents , 1997, AGENTS '97.

[10]  G. Tidhar,et al.  Guided Team Selection * , 1996 .

[11]  Candace L. Sidner,et al.  COLLAGEN: when agents collaborate with people , 1997, AGENTS '97.

[12]  Tony White,et al.  Towards multi-swarm problem solving in networks , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[13]  Nicholas R. Jennings,et al.  The archon systems and its applications , 1995 .

[14]  D. P. Schrage,et al.  Software-enabled control for intelligent UAVs , 1999, Proceedings of the 1999 IEEE International Symposium on Computer Aided Control System Design (Cat. No.99TH8404).

[15]  Milind Tambe,et al.  Building large-scale robot systems: Distributed role assignment in dynamic, uncertain domains , 2003 .

[16]  Milind Tambe,et al.  Agent Architectures for Flexible, Practical Teamwork , 1997, AAAI/IAAI.

[17]  Claudia V. Goldman,et al.  Optimizing information exchange in cooperative multi-agent systems , 2003, AAMAS '03.

[18]  Milind Tambe,et al.  Multiagent teamwork: analyzing the optimality and complexity of key theories and models , 2002, AAMAS '02.

[19]  Hiroaki Kitano,et al.  RoboCup: A Challenge Problem for AI , 1997, AI Mag..

[20]  Nicholas R. Jennings,et al.  Specification and Implementation of a Belief Desire-Joint_intention Architecture for Cooperative Problem Solving , 1993, Int. J. Cooperative Inf. Syst..

[21]  Victor R. Lesser,et al.  Communication decisions in multi-agent cooperation: model and experiments , 2001, AGENTS '01.

[22]  Mark H. Burstein,et al.  A Framework for Dynamic Information Flow in Mixed-Initiative Human/Agent Organizations , 2004, Applied Intelligence.

[23]  Milind Tambe,et al.  A prototype infrastructure for distributed robot-agent-person teams , 2003, AAMAS '03.

[24]  Wei-Min Shen,et al.  Teamwork in Cyberspace: Using TEAMCORE to Make Agents Team-Ready , 1999 .

[25]  Joanna J. Bryson,et al.  Hierarchy and Sequence vs. Full Parallelism in Action Selection , 2000 .

[26]  Milind Tambe,et al.  An Automated Teamwork Infrastructure for Heterogeneous Software Agents and Humans , 2003, Autonomous Agents and Multi-Agent Systems.

[27]  John Yen,et al.  CAST: Collaborative Agents for Simulating Teamwork , 2001, IJCAI.

[28]  Jean Oh,et al.  Electric Elves: Agent Technology for Supporting Human Organizations , 2002, AI Mag..

[29]  D. Mcdonald,et al.  ARCHON : A DISTRIBUTED ARTIFICIAL INTELLIGENCE SYSTEM FOR INDUSTRIAL APPLICATIONS , 1995 .

[30]  Milind Tambe,et al.  Toward Team-Oriented Programming , 1999, ATAL.

[31]  Jacques Ferber,et al.  Action selection in an autonomous agent with a hierarchical distributed reactive planning architecture , 1998, AGENTS '98.

[32]  Michael Van Wie A probabilistic method for team plan formation without communication , 2000, AGENTS '00.

[33]  Nicholas R. Jennings,et al.  Foundations of distributed artificial intelligence , 1996, Sixth-generation computer technology series.

[34]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[35]  C. Lee Giles,et al.  How communication can improve the performance of multi-agent systems , 2001, AGENTS '01.

[36]  Claudia V. Goldman,et al.  Mechanism Design for Communication in Cooperative Systems , 2003 .

[37]  John E. Laird,et al.  Coordinated Behavior of Computer Generated Forces in TacAir-Soar , 1994 .