Max Versace, Director of the Neuromorphics Lab, was invited to give a talk at the NASA Langley Research Center in Virginia, guest of Mark Motter, Ph.D., PE NASA Langley Research Center Electronics System Branch.
The talked, titled "Neuromorphic solutions for autonomous land and aerial vehicles", focused on the work done between the lab, NASA, and Neurala in land and areal robots.
(In the picture, Max Versace with Mark Motter)
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.
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).