Videos – Medical Robotics and Interactive Intelligent Technologies (MERIIT@NYU) Laboratory

ICRA2023: Title: Upper-limb Geometric MyoPassivity Map for PhysicalHuman-Robot Interaction: Preprint: https://arxiv.org/pdf/2302.00495.pdf

ICRA2023:Title: Power-Based Velocity-Domain Variable Structure Passivity Signature Control for Physical Human-(Tele)Robot Interaction [Published in]: IEEE Transactions on Robotics [DOI]: 10.1109/TRO.2022.3197932

MERIIT Lab & NYU Agens of Optimism (2022):

MERIIT talks at IROS2022:

Telehealth & TeleMedicine Workshop: by S. Farokh Atashzar as part of the 2022 IEEE Symp. on Telepresence

IROS2022: Title: eDeep Augmentation for Electrode Shift Compensation in Transient-phase High-density EMG

IROS 2022: E. Tyacke et al., “Hand Gesture Recognition via Transient sEMG Using Transfer Learning of Dilated Efficient CapsNet: Towards Generalization for Neurorobotics,” in IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 9216-9223, Oct. 2022, doi: 10.1109/LRA.2022.3191238.

MERIIT Lab @ NYU (PI: S. Farokh Atashzar) – Undergraduate VIP Team: Wearable Mechanomyography

ICRA2022 – Deep Heterogeneous Dilation of LSTM for Transient-phase Gesture Prediction through HDsEMG

MERIIT Lab @ NYU Wireless 2021

IROS2021:IEEE RAL/IROS 2021 – Temporal Dilation of Deep LSTM for Agile NeuroRobotics

IEEE RAL/IROS 2021 – Mechanical Library for Soft Robotics

IEEE Haptics Symposium 2020: Dual-Frequency Wearable for Stiffness Perception

ICRA 2021 Workshop “Impact of COVID-19 on Medical Robotics and Wearables Research: Learning from the Past and Strategizing for the Future ”

Quanser Webinar – 2021

Highlight: Fighting hand tremors: First comes AI, then robots

Link:

To develop advanced rehabilitation and assistive robotic technologies for patients wit pathological hand tremor (PHT), accurate estimation and prediction of nonstationary PHT is critical. However, the required level of accuracy and latency has not yet been achieved. The lack of sizable datasets and generalizable modeling techniques that can fully represent the spectrotemporal characteristics of PHT have been a critical bottleneck in attaining this goal. This work addresses this unmet need through establishing a deep recurrent neural network model to predict and eliminate the PHT component of hand motion. More specifically, we propose a machine learning-based, assumption-free, and real-time PHT elimination framework, the PHTNet, by incorporating deep bidirectional recurrent neural networks. The PHTNet is the first intelligent systems model developed on this scale for PHT elimination that maximizes the resolution of estimation and allows for prediction of future and upcoming sub-movements.