CMANTIC Lab Projects 2001-2009
COMSTAR (Phase I: 2004-2005, Phase II: 2006-2008)
Funding: U.S. DoD NavAir (STTR Phase I and Phase II grants awarded with 21st Century Systems Inc.)
The objective of the COMSTAR–UAV (COllaborative Multi-agent Swarmed system for automatic TArget Recognition using UAVs) project was to build a system comprising of swarms of low-cost but computationally limited autonomous robots to collaboratively perform complex tasks in an unknown environment. The limited capabilities on a robot/UAV makes it difficult for it to complete a 'complex' task on its own using only its on-board resources. Therefore, to complete a task, multiple robots must coordinate their actions with each other, so that they can perform the task collaboratively. Tasks can appear dynamically and must be discovered by the robots online by exploring the environment. Finally, the coordination between the robots must be done in a completely distributed manner, with little or no interaction with a centralized base station. We have developed novel algorithms for distributed multi-robot task allocation, dynamic path planning and distributed exploration/coverage by the robot teams. Our algorithms use swarming-based coordination between robots to perform primitive operations, while more complex operations are handled by higher cognitive capabilities such a game-theoretic coordination. We have tested these algorithms within a comercially available robot simulator called Webots and on a multi-agent simulation platform for defense-related applications called AEDGE (developed by 21st Century Systems). For our harware experiments we used mini-robots called the e-puck that are not very expensive and closely resemble the capabilities of mini-UAVs. We have tested all our techniques and shown them to operate successfully on teams of 3-7 e-puck robots.
Related Publications
1. P. Dasgupta, "A Multi-agent Swarming System for Distributed Automatic Target Recognition," IEEE Transactions on Systems, Man, Cybernetics, Part A, vol. 38, no. 3, 2008, pp. 549-563.
2. L. Fan and P. Dasgupta, "A Stigmergy-based model for Solving Cooperative Pursuit-Evasion Games in Unknown Environments," 2nd IEEE Intl. Conf. on Self Adaptation and Self Organization (SASO), 2008, pp. 467-468.
3. K. Cheng and P. Dasgupta, "Coalition game based distributed coverage of unknown environments using robot swarms," International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'08), Estoril, Portugal, 2008, pp. 1191-1194.
4. K, Cheng and P. Dasgupta, "Dynamic Area Coverage using Faulty Multi-agent Swarms" Proc. IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2007), Fremont, CA, 2007, pp. 17-24.
5. P. Dasgupta, and M. Hoeing, "Task Selection in Multi-Agent Swarms using Adaptive Bid Auctions," Proc. of 1st IEEE Intl. Conf. on Self Adaptation and Self Organization (SASO), 2007, Boston, MA, 307-310.
6. M. Hoeing, P. Dasgupta , et al., "Auction-based Multi-Robot Task Allocation in COMSTAR," Proc. International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'07), Honolulu, HI, 2007, pp. 1435-1442.
7. P. Dasgupta, M. Hoeing, K. Cheng, et al., "Dynamic Pricing Algorithms for Task Allocation in Multi-agent Swarms," Proc. First International Workshop on Coordination and Control in Massively Multi-agent Systems (CCMMS'07), Honolulu, HI, May 2007, pp. 1-15.
8. M. Hoeing and P. Dasgupta, "Market based Distributed Task Selection in Multi-agent Swarms," IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'06), Hong Kong, Dec 2006, pp. 113-116.
9. D. Miller, P. Dasgupta, T. Judkins, "Distributed Task Selection in Multi-agent based Swarms using Heuristic Strategies," LNCS vol. 4433 (Proc. 2nd Swarm Robotics Workshop, Rome, Italy), 2006, pp. 158-172.
10. P. Dasgupta, "Distributed Automatic Target Recognition Using Multi-Agent UAV Swarms," Proc. of the 5th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'06), Hakodate, Japan, 2006, pp. 479-481.
11. P. Dasgupta, S. O'Hara, P. Petrov, "A Multi-agent UAV Swarm for Automatic Target Recognition," Proc. of the 1st International Workshop on Defense Applications of Multi-agent Systems (co-located with AAMAS'05), Utrecht, The Netherlands, 2005, pp. 4-15.
12. P. Dasgupta and P. Petrov, "COMSTAR: Co-Operative Multi-agent Swarm for Automated Target Recognition," 2nd Annual Swarming Conference, Washington D. C., 2004.
CrowdSimu
The Crowd-Simu project was collaboration between faculty from UNO and INAOE, Mexico. The objective of the CrowdSimu project was to investigate novel methodologies from multi-agent coordination using game theory and robotic path planning for simulation of pedestrian crowds.
Funding: UNO Faculty Research International
DynaPAC
In the DynaPAC (Dynamic Pricing for Agent Coordination) project, we developed techniques for multi-attribute dynamic pricing by sellers in an information market economy. Previous work in this area restricts itself to pricing goods, only along a single attribute, and, assumes that sellers know a priori different buyer parameters, such as buyer demand, number of buyers, buyer strategies, etc. We address the harder problem of developing appropriate pricing strategies for sellers along multiple attributes of an item, without providing any a prioriinformation about buyers to sellers. Our techniques have resulted in improved/accurate pricing resulting in higher profits (utilities) to sellers.
Related Publications
1. J. Jumadinova and P. Dasgupta, "Firefly-Inspired Synchronization for Improved Dynamic Pricing in Online Markets," 2nd IEEE Intl. Conf. on Self Adaptation and Self Organization (SASO), 2008, pp. 403-412.
2. J. Jumadinova and P. Dasgupta "Multi-attributed Regret-based Dynamic Pricing," Agent Mediated Electronic Commerce Workshop (AMEC-X), co-located with AAMAS 2008, Estoril, Portugal, 2008.
3. P. Dasgupta, P. M. Melliar-Smith, L. E. Moser, "Dynamic Pricing Algorithms for Online Sellers using Intelligent Agents," (Book Chapter) Encyclopedia of E-commerce, e-government and mobile commerce, (Ed. M. Khosrow-pour), 2006.
4. P. Dasgupta, P. M. Melliar-Smith, "Dynamic Pricing for Time Limited Goods in a Supplier-Driven Electronic Marketplace", Journal of Electronic Commerce Research, Springer, vol. 5, no. 2, pp. 267-292, 2005.
5. P. Dasgupta and Y. Hashimoto, "Multi-attribute Dynamic Pricing for Online Markets Using Intelligent Agents," Proceedings of the Third International Conference on Autonomous Agents and Multi-agent Systems (AAMAS '04), New York, NY, 2004, pp. 277-284.
6. P. Dasgupta and Y. Hashimoto, "Eliciting Buyer Preferences Using Intelligent Agents for Multi-attribute Dynamic Pricing," Proceedings of the 8th International Conference on Artificial Intelligence, Las Vegas, NV, 2004, pp. 790-797.
7. P. Dasgupta, P. M. Melliar-Smith, "Dynamic Consumer Profiling and Tiered Pricing Using Software Agents", Journal of Electronic Commerce Research, Kluwer Academic Publishers, The Netherlands, vol.3, no 3-4, July-October 2003, pp. 277-296.
8. P. Dasgupta, “Incentive Driven Node Discovery in a Peer-to-Peer Network Using Mobile Intelligent Agents,” Proceedings of the 7th International Conference on Artificial Intelligence, Las Vegas, 2003, pp. 750-756.
9. P. Dasgupta, “A Peer-to-Peer System Architecture for Multi-agent Collaboration,” Advances in Soft Computing, Springer-Verlag, (Proceedings of the 3rd International Conference on Intelligent Systems and Design Automation, Tulsa, OK), 2003, pp. 483-492.
10. P. Dasgupta, "Agent based Peer-to-Peer Systems," Proceedings of the 45th IEEE Midwest Symposium on Circuits and Systems, Vol. 1, August 4-7, 2002, pp. 663-666.
11. P. Dasgupta, V. Kalogeraki, "Auctioning Strategies in Agent Enabled Peer-to-Peer Marketplace," Proceedings of the Sixth International Conference on Artificial Intelligence, Las Vegas, NV, June 24-27, 2002, pp. 64-70.
12. P. Dasgupta, "Fault tolerance in MAgNET: A Mobile Agent E-commerce System," Proceedings of the Sixth International Conference on Internet Computing, Las Vegas, NV, June 24-27, 2002, pp. 733-739.
13. P. Dasgupta, "Multi-attribute Tiered Pricing to Maximize Sellers' Profits in a Multi-agent economy," First International Conference on Intelligent Agents, Web Technology and Internet Commerce, Las Vegas, NV, July 9-11, 2001, pp. 360-369.
14. P. Dasgupta, L. E. Moser, P. M. Melliar-Smith, "Dynamic Tiered Pricing in a Multi-agent economy," International Conference on Artificial Intelligence, Las Vegas, NV, June 25-28, 2001, pp. 1142-1148.
15. P. Dasgupta, R. Das, "Dynamic Pricing with Limited Competitor Information in a Multi-Agent Economy", Cooperative Information Systems, Lecture Notes in Computer Science 1901, Proceedings of the Fifth International Conference on Cooperative Information Systems(CoopIS), Eilat, Israel, September 6-8, 2000, pp. 299-310.
16. P. Dasgupta, R. Das, "Dynamic Service Pricing for Brokers in a Multi-Agent Economy", Proceedings of the Third International Conference for Multi-Agent Systems(ICMAS), Boston, MA, July 4-9, 2000, pp. 375-376. (poster paper)
17. P. Dasgupta, L. E. Moser, P. M. Melliar-Smith, "The Security Architecture for MAgNET: A Mobile Agent E-commerce System", Proceedings of the Third International Conference on Telecommunications and E-commerce, Dallas,TX, November 16-19, 2000, pp. 289-298.
18. P. Dasgupta, N. Narasimhan, L. Moser, P.M. Melliar Smith, "MAgNET: Mobile Agents for Networked Electronic Trading", IEEE transactions on Knowledge and Data Engineering, Special Issue on Web Technologies, vol. 24, no. 6, July/August 1999, pp 509-525.
19. P. Dasgupta, N. Narasimhan, L. Moser, P.M. Melliar Smith, "A Supplier-Driven Electronic Marketplace Using Mobile Agents", Proceedings of the First International Conference on Telecom and E-commerce, Nashville,TN, November 19-22, 1998, pp 42-50.
PeerNets
In this project, we have developed techniques to enable rapid search in unstructured peer-to-peer networks. We have mainly developed algorithms based on emergent properties of artificial insect societies to enable rapid and dynamic network (re)-construction and fast searching.
Related Publications
1. P. Dasgupta, "Building Small Worlds in Unstructured P2P Networks using a Multi-agent Bayesian Inference Mechanism," International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'07), Honolulu, HI, May 2007, pp. 936-938.
2. P. Dasgupta, `` A Multi-agent Mechanism for Topology Balancing in Unstructured P2P Networks,'' IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'06), Hong Kong, 2006, pp. 389-392.
3. S. Airiau, S. Sen and P. Dasgupta, "Effect of Joining Decisions on Peer Clusters," Proc. of the 5th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'06), Hakodate, Japan, 2006, pp. 609-615.
4. P. Dasgupta, "Efficient Searching in Peer-to-Peer Networks Using Agent Enabled Ant Algorithms," (Book Chapter) Handbook of Research on Nature-Inspired Computing for Economics and Management, vol. II, (Ed. J. Rennard), Idea Group Publishing, 2006, pp. 721-737.
5. P. Dasgupta,"Adaptive Sharing of Large Resources in P2P Networks," Proc. of the 4th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'05), Utrecht, The Netherlands, 2005, pp. 839-845.
6. D. Banerjee, S. Saha, S. Sen, P. Dasgupta, "Reciprocal Resource Sharing in P2P Environments", Proc. of the 4th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'05), Utrecht, The Netherlands, 2005, pp. 853-869.
7. P. Dasgupta, "Intelligent Agent Enabled Genetic Ant Algorithm for P2P Resource Discovery," Lecture Notes in Computer Science, vol. 3601 (Proc. 3rd Workshop on Agent Enabled P2P Computing, New York, NY, 2004), Springer, 2005, pp. 213-220.
8. P. Dasgupta, “Improving Peer-to-Peer Resource Discovery Using Mobile Agent Based Referrals,” Lecture Notes in Computer Science, vol. 2872, Springer, 2004, pp. 186-197. (Preliminary version: Proceedings of the 2nd Workshop on Agent Enabled P2P Computing (co-located with AAMAS'03) , Melbourne, Australia, July 2003, pp 41-54. )
9. P. Dasgupta, "Intelligent Agent Enabled P2P Search Using Ant Algorithms," Proceedings of the 8th International Conference on Artificial Intelligence, Las Vegas, NV, 2004, pp. 751-757.
10. P. Dasgupta, “Incentive Driven Node Discovery in a Peer-to-Peer Network Using Mobile Intelligent Agents,” Proceedings of the 7th International Conference on Artificial Intelligence, Las Vegas, 2003, pp. 750-756.
11. P. Dasgupta, “A Peer-to-Peer System Architecture for Multi-agent Collaboration,” Advances in Soft Computing, Springer-Verlag, (Proceedings of the 3rd International Conference on Intelligent Systems and Design Automation, Tulsa, OK), 2003, pp. 483-492.
12. P. Dasgupta, "Agent based Peer-to-Peer Systems," Proceedings of the 45th IEEE Midwest Symposium on Circuits and Systems, Vol. 1, August 4-7, 2002, pp. 663-666.
13. P. Dasgupta, V. Kalogeraki, "Auctioning Strategies in Agent Enabled Peer-to-Peer Marketplace," Proceedings of the Sixth International Conference on Artificial Intelligence, Las Vegas, NV, June 24-27, 2002, pp. 64-70.