Event Location: NSH 1507

Abstract: Learning algorithms to predict depth and infer 3-d models, given just a single still image. Applications included creating immersive 3-d experience from users’ photos, improving performance of stereovision, creating large-scale models from a few images, robot navigation, etc.

Learning algorithms to predict robotic grasps, even for objects of types never seen before by the robot. Applied to tasks such as unloading items from a dishwasher, clearing up a cluttered table, opening new doors, etc.

Use monocular depth perception and reinforcement learning techniques to drive a small rc-car at high speeds in unstructured environments.