We are developing machine learning algorithms to automatically track, model, and control multibody dynamic systems. Our efficient algorithms are deployed on mobile devices and control hardware units. Applications include markerless tracking of human movement biomechanics, control of autonomous vehicles, automotive powertrain models, and environment recognition systems for robotic lower-limb exoskeletons and prostheses.
• Deep Learning and Computer Vision
• Convolutional Neural Networks
• Reinforcement Learning
• Human Movement Biomechanics
• Autonomous Vehicles
• Environment Recognition Systems
• McNally W, Wong A, and McPhee J. (2019). STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection. arXiv:1902.10024.
• McNally W, Vats K, Pinto T, Dulhanty C, McPhee J, and Wong A. (2019). GolfDB: A Video Database for Golf Swing Sequencing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). arXiv:1903.06528.