Ashutosh Saxena PhD candidate Computer Science Department, Stanford University asaxena at cs.stanford.edu advisor: Prof. Andrew Y. Ng Research agenda:     To let robots learn to "see" and operate in novel uncertain environments. Research interests:     Machine Learning, Robotics Perception and Manipulation, Computer Vision.

SELECTED PROJECTS

Make3D: Single Image Depth Perception

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.

STAIR: Mobile Robot Manipulation

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.

Visual Navigation: High speed obstacle avoidance

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

Other projects

See projects page for more. E.g., 6-D wireless sourceless mouse, Bio-sensitive watch to prevent electric Shock, Noise tolerant Locally Linear Isomaps, Data driven robotics, etc.