LCSR Seminar: Student Seminar

November 16, 2022 @ 12:00 pm – 1:00 pm
Hackerman B17
Ashley Moriarty

Link for Live Seminar

Link for Recorded seminars – 2022/2023 school year


Student 1: Maia Stiber “Supporting Effective HRI via Flexible Robot Error Management Using Natural Human Responses”

Abstract: Unexpected robot errors during human-robot interaction are inescapable; they can occur during any task and do not necessarily fit human expectations of possible errors. When left unmanaged, robot errors’ impact on an interaction harms task performance and user trust, resulting in user unwillingness to work with a robot. Prior error management techniques often do not possess the versatility to appropriately address robot errors across tasks and error types as they frequently use task or error specific information for robust management. In this presentation, I describe my work on exploring techniques for creating flexible error management through leveraging natural human responses (social signals) to robot errors as input for error detection and classification across tasks, scenarios, and error types in physical human-robot interaction. I present an error detection method that uses facial reactions for real-time detection and temporal localization of robot error during HRI,  a flexible error-aware framework using traditional and social signal inputs that allow for improved error detection, and an exploration on the effects of robot error severity on natural human responses. I will end my talk by discussing how my current and future work further investigates the use of social signals in the context of HRI for flexible error detection and classification.

Bio: Maia Stiber is a Ph.D. candidate in the Department of Computer Science, co-advised by Dr. Chien-Ming Huang and Dr. Russell Taylor. Her work focuses on leveraging natural human responses to robot errors in an effort to develop flexible error management techniques in support of effective human-robot interaction.



Student 2: Akwasi Akwaboah “Neuromorphic Cognition and Neural Interfaces”

Abstract: I present research at the Ralph Etienne-Cummings-led Computational Sensor-Motor Systems Lab, Johns Hopkins University on two fronts – (1) Neuromorphic Cognition (NC) focused on the emulation neural physiology at algorithmic and hardware levels, and (2) Neural Interfaces with emphasis on electronics for neural MicroElectrode Array (MEA) characterization. The motivation for the NC front is as follows. The human brain expends a mere 20 watts in learning and inference, exponentially lower than state-of-the-art large language models (GPT-3 and LaMDA). There is the need to innovate sustainable AI hardware as the 3.4x compute doubling per month has drastically outpaced Moore’s law, i.e., a 2-year transistor doubling. Efforts here are geared towards realizing biologically plausible learning rules such as the Hebb’s rule-based Spike-Timing-Dependent Plasticity (STDP) algorithmically and in correspondingly low-power mixed analog-digital VLSI implements. On the same front of achieving a parsimonious artificial intelligence, we are investigating the outcomes of using our models of the primate visual attention to selectively sparsify computation in deep neural networks. At the NI front, we are developing an open-source multichannel potentiostat with parallel data acquisition capability. This work holds implications for rapid characterization and monitoring of neural MEAs often adopted in neural rehabilitation and in neuroscientific experiments. A standard characterization technique is the Electrochemical Impedance (EI) Spectrometry. However, the increasing channel counts in state-of-the-art MEAs (100x and 1000x) imposes the curse of prolonged acquisition time needed for high spectral resolution. Thus, a truly parallel EI spectrometer made available to the scientific community will ameliorate prolonged research time and cost.

Bio: Akwasi Akwaboah joined the Computational Sensory-Motor Systems (CSMS) Lab in Fall 2020 and is working towards his PhD. He received the MSE in Electrical Engineering from the Johns Hopkins University, Baltimore, MD in Summer 2022 en route the PhD. He received the B.Sc. Degree in Biomedical Engineering (First Class Honors) from the Kwame Nkrumah University of Science and Technology, Ghana in 2017. He also received the M.S. degree in Electronics Engineering from Norfolk State University, Norfolk, VA, USA in 2020. His master’s thesis there focused on the formulation of a heuristically optimized computational model of a stem cell-derived cardiomyocyte with implications in cardiac safety pharmacology. He subsequently worked at Dr. James Weiland’s BioElectronic Vision Lab at the University of Michigan, Ann Arbor, MI, USA in 2020; where he collaborated on research in retinal prostheses, calcium imaging and neural electrode characterization. His current interests include the following: neuromorphic circuits and systems, bio-inspired algorithms, computational biology, and neural interfaces. On the lighter side, Akwasi loves to cook and listen to classical and Afrobeats music. He lives by Marie Curie’s quote – “Nothing in life is to be feared, it is only to be understood …


Johns Hopkins University

Johns Hopkins University, Whiting School of Engineering

3400 North Charles Street, Baltimore, MD 21218-2608

Laboratory for Computational Sensing + Robotics