Obstacle Avoidance: This 3D visualization of a 2D simulation shows a robotic aircraft (unmanned aerial vehicle, or UAV) flying autonomously through a previously unknown forest. The only sensing onboard is a monocular camera and an inertial measurement unit, or IMU. The aircraft simultaneously estimates the locations of trees and its own location and velocity, allowing it to plan a path around the obstacles and to the goal posts. The translucent red cyclinders represent the uncertainty associated with the estimated position of each tree. See my Research page for more information. [MPEG]

Autonomous Navigation: This video shows autonomous navigation using only vision and inertial measurements. The small uninhabited ground vehicle (UGV) was given a command to drive to a goal at the far end of the "forest" shown in the picture. It planned a trajectory and began to drive. As obstacles were detected, they were added to the map and included in the trajectory planning algorithm. The video shows both the view from the on-board camera and a reconstruction of the vehicle's surroundings based on the estimated vehicle state and the state of the obstacles. Near the end of the video a piece of white paper will come into view: this was placed on the ground at the goal location to show when the vehicle reached the goal. See my Research page for more information. [MPEG 39Mb]