Abstract:
In the development of sensor network technology, one of the long-standing research challenges has been the development of methods that efficiently monitor large (and possibly uncertain) environments. Often these environments also exhibit complex dynamics across both space and time that can only be partially observed. With limited sensing resources available, mobile sensing platforms are used to achieve sufficient spatial and temporal coverage by attaching these sensors with the mobile agents. However, planning the motion of these mobile agents - coordinating their paths in order to maximize the amount of information collected while placing bounds on their resources (e.g., path length, energy capacity or sensing time) - is a NP-hard problem.

In this talk I will first present a couple of tethered mobile platforms developed by us for environmental monitoring applications. We then present novel approximation algorithms for solving this NP-hard problem of path planning in such complex environments. We exploit several machine learning concepts to maximize the “informativeness” of the locations visited by the mobile agents. We provide strong theoretical guarantees for the proposed algorithms, exploiting different intuitive properties of sensing applications - diminishing returns, locality and monotonicity. We collaborated with biologists and environmental scientists to use these systems and algorithms for several critical applications of water quality monitoring in lake and river environments. Several such field experiments were performed, in addition to using multiple real world sensing datasets, to validate the effectiveness of the proposed algorithms for real world sensing applications. Expanding the applicability of the proposed work from environmental applications to socially responsive applications, we also present the recent work in the system development and deployments in sustainability related applications pertaining to energy and water metering and traffic monitoring.

Bio:
Amarjeet Singh completed his undergraduate education in Electrical Engineering from Indian Institute of Technology, Delhi in 2002. He was awarded Rajendra Kumari Malhotra Award for Responsible Student Leadership in 2001. From 2002 – 2004, he worked as Senior Research and Development Engineer at Tejas Networks, Bangalore, India. In 2005, he joined Center for Embedded Networked Sensing (CENS), UCLA and completed his MS in Electrical Engineering in 2007. He was awarded the Edward K. Rice outstanding MS student award in 2007. In 2008-09, he was a recipient of Dissertation year fellowship, awarded to less than 1% of graduate students at UCLA. He completed his Phd in Electrical Engineering from UCLA in 2009. Part of the thesis work was completed during the research collaborations at Carnegie Mellon University and Sydney University. He was also awarded with a certification of “Leaders in Sustainability” for multidisciplinary work amongst top caliber UCLA students interested in sustainability.