This project is a collaborative effort by
computer scientists and engineers from Texas A&M and UC Berkeley
consulting with natural scientists and documentary filmmakers. The goal
is to advance the fundamental understanding of automated and
collaborative systems that combine sensors, actuators, and human input
to observe and record detailed natural behavior in remote settings.
Currently, scientific study of animals in situ requires vigilant
observation of detailed animal behavior over weeks or months. When
animals live in remote and/or inhospitable locations, observation can be
an arduous, expensive, dangerous, and lonely experience for scientists.
The project proposes a new class of hybrid teleoperated/autonomous
robotic "observatories" that allow groups of scientists, via the
internet, to remotely observe, record, and index detailed animal
activity. Such observatories are made possible by emerging advances in
robotic cameras, long-range wireless networking, and distributed
sensors.
This project will investigate the algorithmic foundations for such
observatories: new metrics, models, data structures, and algorithms,
that will comprise a robust, mathematical framework for collaborative
observation. The project will build on past work to extend and formally
characterize hybrid models of collaborative and automated observation
that draw on computational geometry, stochastic modeling and
optimization. The project will advance fundamental understanding of
networked robotics and develop efficient algorithms for collaborative
observation that combines human and sensor input. This effort is
intended to benefit biological scientists and facilitate collaboration
among researchers. It will produce working prototypes that will be
accessible via the internet to scientists, students, and the public
worldwide.
Updates,
hardware designs, CAD models, schematics, source code, experimental
data, and documentation will be posted on this website as they emerge.