Topic: Autonomy Incubator Seminar Series: Neuromorphic Solutions for Autonomous Land and Aerial Vehicles
Speaker: Massimiliano Versace, Boston University Neuromorphics Lab, Neurala Inc.
Date: Thursday, February 27, 2014
Time: 9:00am – 10:00am
Location: NASA/LaRC – Pear Young Theatre
Hosts: Danette Allen, NASA
Fred Brooks, NIA
Abstract: Convergent advances in brain modeling, neuroinformatics, neuromorphic engineering, and low-power parallel computing are opening the door to the design and fielding of large-scale neural models for application domains ranging from sense-making to mobile robotics. This talk introduces the state-of-the-art in neuromorphic or brain-based computing, in particular its relevance to support advanced autonomous behavior in land and aerial vehicles. The talk will focus on large-scale neuromorphic models that simulate key elements of perceptual, cognitive, and motivational competencies in both virtual environments and land/air robotic platforms. Compared to alternative approaches, the discussed neuromorphic solutions rely on parallel processing as well as learning and adaptation in relatively simple, neural-like computing elements to solve problems ranging from navigation to sense- and decision-making. The most intriguing implication of neuromorphic research for robotics is that, quite often, the mechanisms observed in the brain appear as natural solutions to the problems that robotic navigation are struggling with, namely: the fusion of multiple sensory streams that dynamically correct each other, increasing the overall precision of the system; redundant representations that increase system robustness; and attractor dynamics that work as a low pass filter to reduce the effects of sensory noise. The talk will illustrate two main applications of this principles in the context of the “Adaptive bio-inspired navigation for planetary exploration” NASA STTR Phase II (NASA Langley with Boston University Neuromorphics Laboratory and Neurala LLC). This effort seeks to translate neuroscience research on animal navigation and sensing into usable software that can control land robots and UAVs. The talk will illustrate the working “mini-brain” that can drive a Mars rover in a virtual environment and a robotic platform, and its applications to UAV collision avoidance.
Bio: Massimiliano Versace is the founding Director of the Neuromorphics Lab at Boston University and the CEO of Neurala Inc. He is a pioneer in the design of large scale, multi-system neural models that allow robots to interact and learn real-time in complex environments. He has authored approximately thirty journal articles, book chapters, and conference papers, and has been an invited speaker at dozens of academic meetings, research and national labs, and companies, including iRobot, Qualcomm, HP, Ericsson, BAE Systems, Mitsubishi, and Accenture. His work has been featured in over thirty articles and news programs, including IEEE Spectrum, New Scientist, Geek Magazine, CNN, MSNBC and others. Versace has his PhD in Cognitive and Neural Systems from Boston University and his BS from University of Trieste, Italy.
Acknowledgments: Supported in part by the National Aeronautics and Space Administration (NASA), and CELEST, a National Science Foundation Science of Learning Center (NSF SBE-0354378).