Prateek Tandon
Computer Engineering, Computer Science
Undergraduate Researcher, Senior Year
Main Website: http://scf.usc.edu/~tandonp
Full Resume/CV: http://scf.usc.edu/~tandonp/Prateek_Tandon_Resume_10_17_2009.pdf

I am a researcher with the TeamCore Research Group led by Professor Milind Tambe on the USC Landroids (now the MAAF project) Project which seeks to apply the Distributed Constraint Optimization Problem (DCOP) Framework to a robotic sensor network. DCOP is a general purpose algorithmic framework for multi-agent coordination previously used for agent-based scheduling and other domains. Our mission with this project is see what kind of results this agent coordination framework can give us on a robotic sensor network. We saw some good results in simulation last year and I was excited to see what could happen with real world robots.

Last summer I built a robotic sensor network of 5 iCreates to prototype our group’s system.

Currently I have been able to scale the network up to 8 robots. Soon I hope to have 10 iCreate robots in the network executing our algorithms. DCOP algorithims facilitate coordination amongst the robots as they decide within their local networks which robots should move a couple inches so that the local signal strengths get better. These local optimizations have experimentally been shown to have a beneficial effect on global throughputs and ping rates. The results we’ve gotten indicate that with small scale movements alone the throughput of the robotic network can be improved nearly 50%!

Earlier I worked on decision tree analysis for DCOPs. DCOP algorithms have various tradeoffs and when applying these algorithms to real world problems, these tradeoffs need to be optimized. That’s where machine learning can help us. My work involved utilizing decision trees to mine structure out of the parameter spaces of a robotic configuration. This work was published as part of our group paper at the Distributed Constraint Reasoning (DCR) conference at IJCAI 2009.

I am currently extending this work to develop a new class of Hybrid DCOP algorithms that combine the benefits of prior algorithms but use decision trees to switch between algorithms to get the optimal reward.

My general interests lie within the realms of Artificial Intelligence, Machine Learning, Robotics, Natural Language Processing, Intelligent Distributed Systems, and Computational Neuroscience. In general, I am intrigued by the complex behavior that arises in a system by virtue of its interacting parts - whether its reactive robots in a robotic sensor network or neurons cooperating and competiting to produce the complex computations in the brain. Can DCOPs and other coordination algorithms can help us both better understand and better build such systems?

• Matthew Taylor, Manish Jain, Prateek Tandon, Milind Tambe. Using DCOPs to Balance Exploration and Exploitation in Time-Critical Domains. Distributed Constraint Reasoning Workshop at IJCAI 2009.
• Marcos A. M. Viera, Matthew E. Taylor, Prateek Tandon, Manish Jain, Ramesh Govindran, Gaurav Sukhatme, Milind Tambe. A Distributed Reasoning Approach to Mobile Mesh Network Optimization. [Submitted for review, InfoCom Conference on Computer Communications 2010]

Contact Information:
tandonp@usc.edu
(408)-891-0290