AI insights from wearable sensors

Tian Tan is a Postdoctoral Scholar at Stanford University, working with Prof. Akshay Chaudhari and Prof. Scott Delp in the Wu-Tsai Human Performance Alliance. Prior to joining Stanford, he obtained his PhD degree in Mechanical Engineering from Shanghai Jiao Tong University. He seeks to advance biomechanics and healthcare through wearable sensing and data science. Target applications include monitoring movement in real life, inspiring novel therapeutic interventions, and guiding treatment decisions. 

Quantifying human gait dynamics, including kinematics, external forces, and joint moments, can help diagnose diseases, prevent injuries, and customize rehabilitation programs. My research aims to use deep learning to model human movement dynamics, thereby enabling wearable-based gait dynamics analysis. To achieve this, I use generative deep learning to model human kinematics and external forces. I also use self-supervised learning to leverage knowledge from wearable sensors without requiring ground-truth kinematics or forces. The outcomes of these studies can be applied to model and monitor human gait dynamics in real life, potentially benefiting millions of underserved patients.

Sneha leads the Motion Sensors Software team at Meta, a multidisciplinary team of engineers and researchers, responsible for the end-to-end technology roadmap of motion sensors for all Meta AR/VR and wearable products. Her team has played a key role in launching some of the world’s leading VR products with state-of-the-art localization & tracking capabilities, such as Quest 3 and Quest 3S.

Before joining Meta, Sneha held Engineering Manager positions at Spotify and Apple, where she developed machine learning and signal processing algorithms for resource-constrained edge devices. Sneha holds an M.S. degree (2011) in Electrical Engineering from Pennsylvania State University and a B.E. degree (2009) in Electrical and Electronics Engineering from Visvesvaraya Technological University. Her interests include machine learning and signal processing algorithms, simulation, and control systems.

Sneha discusses the concept of the Metaverse and explores how MEMS and sensors contribute to enhanced features and experiences in Augmented Reality (AR) and Virtual Reality (VR). Additionally, she delves into the various challenges faced by AR/VR and shares insights on the innovative areas her team is investigating for the development of new AR/VR experiences.