Robotic plane dodges obstacles: CNET News Video
CNET News Video: Robotic plane dodges obstacles2:46 /
MIT's Robust Robotics Group has developed an autonomous robotic plane that can avoid obstacles inside a parking garage without the need for GPS navigation.
Micro air vehicles capable of operating in constrained environments without the use of an external motion capture system are typically limited to slow and conservative flight. As a consequence almost all of this research is done with rotor craft in the -- -- In the robust robotics group -- C sale -- MIT we've developed a fixed wing vehicle capable of flying at high speeds through obstacles using only onboard sensors. The vehicle is equipped with an inertial measurement unit and a laser range scanner. All the computation for state estimation and control is done on board using an Intel atom processor. Similar to what is found in a commercially available netbook. We designed a custom airplane to carry the sensing and computation payload while still being able to maneuver in confined spaces. Our platform has a two metre wingspan and weighs approximately two kilograms. At any given time the laser can only see a two dimensional picture of the environment. Laser scans are depicted with yellow points for presenting obstacles and blue representing free space. Even with the pre computed map. Individual two. 3-D position velocity and orientation of the vehicle. To overcome this difficulty we aggregate successive scans and combined laser information with the inertial measurement unit to perform state estimation. Another technical challenge is sufficiently generating trajectories for the vehicle to follow. The complicated vehicle dynamics create substantial computational difficulties in determining a path to -- from point a to point B. To overcome this difficulty will use an approximate dynamics model that makes it easy to map the control inputs. Elevator -- Taylor on and throttle to corresponding XYZ trajectories. We start by connecting a set of high level -- points with line and arc segments. We then use our approximate model to construct dynamically feasible -- my -- rising an offset from this underlying trajectory. Here we demonstrate the accuracy and reliability of the system flying through parking garage. In places the parking garage is less than 2.5 meters from floor to ceiling. Creating extremely tight tolerances for our two metre vehicle. Our algorithms allow the vehicle to complete a seven minute flight through the environment traveling at over ten meters per second. Or 22 miles per hour covering almost three miles of distance and repeatedly coming within a few centimeters of obstacles. --