Artificial intelligence takes over the drones
Artificial intelligence takes over the drones
An MIT mapping system allows unmanned aircraft to dodge obstacles at low speed
Can a drone only dodge an obstacle? The answer is yes. The Laboratory of Computer Science and Artificial Intelligence (CSAIL) of the Massachusetts Institute of Technology has managed to provide artificial intelligence to a small aircraft to fly through forests and warehouses.
Nanomap, the new alternative navigation system allows you to fly over and avoid obstacles, as long as the speed of the device does not exceed 30 kilometers per hour.
Excessively safe maps will not help if you want drones that can operate at higher speeds in human environments," says graduate student Pete Florence, lead author of a new related document. "An approach that is more aware of uncertainty gives us a much higher level of reliability in terms of being able to fly close and avoid obstacles ."
Shocks
Many existing approaches are based on complex maps that aim to tell drones exactly where they are related to obstacles, which is not particularly practical in real-world environments with unpredictable objects. If your estimated location is out by only a small margin, they can easily collide.
This depth detection system to join a series of measurements on the immediate environment of the drone. This allows you not only to make movement plans for your current field of vision , but also to anticipate how you should move in the hidden fields of vision you have already seen.
The document was co-written by Florence and MIT professor Russ Tedrake, along with research software engineers John Carter and Jake Ware. Recently, he was accepted at the IEEE International Conference on Robotics and Automation (ICRA), which will take place in May in Brisbane, Australia.
Comments
Post a Comment