Ujas Mandavia have a solid understanding of multiview geometry vision, 3D point cloud processing, non-linear least square optimization, and probabilistic filtering method that has been used in robot localization and mapping. Ujas' interests are in: • Robotics • Spatial AI • Computer Vision • 3D Geometry • Deep Learning Ujas have recent project experience in: • Convolutional Neural Networks • Recurrent Neural Networks and LSTMs • Deep Learning for Geometric Tasks • IMUs, CAMERAs,LiDARs, and Sensor Fusion • Structure from Motion (SfM) / SLAM • 3D Reconstruction • Autonomous Robotics Tools: C++, Python, PyTorch, Tensorflow, ROS