NASA Drone Race Pits Man Against Machine (Video)


To show NASA's achievements in artificially intelligent navigation, the agency invited professional drone racer Ken Loo to be involved in its software.

The race on October 12 followed two years of AI research by the Jet Propulsion Laboratory (JPL) in Pasadena, California. The JPL's success in navigating spacecraft attracted Google, who funded research into drone autonomy, NASA said in the statement accompanying a video released on Tuesday (November 21).

JPL built three Quadcopter drones – nicknamed Batman, Joker and Nightwing – to test the new software. The algorithms use two cameras mounted on each drone and compare what they see with a preloaded map of the area. The program also takes advantage of Google Tango, an augmented reality technology that the company developed to use vision and allow a device to determine its position and location. [10 Ways Robots Move on Mars]

  Two wide-angle cameras allow the AI ​​to compare the environment of the drone with a preloaded map of the area.

Two wide-angle cameras allow the AI ​​to compare the environment of the drone with a preloaded map of the area.

Credit: NASA / JPL-Caltech

The team set up an obstacle course in one of the JPL warehouses to test the software. "We put our algorithms against a human, who flies much more for the sensation," Rob Reid, the project's task manager, said in the statement.

The two riders started with similar lap times. However, Loo was able to learn the course after many laps. He achieved higher speeds with impressive aerial maneuvers, reducing his total times. On the contrary, the AI ​​took the course more cautiously, but also more consistently. "The AI ​​was able to fly the same race line on every lap," NASA said.

The pilots also faced unique challenges. Sometimes, the race-ready drones moved so fast that the cameras could not focus properly, which disoriented the computer that was flying them. But as the day progressed, Loo had to fight fatigue, a problem that the AI ​​pilot does not have to worry about. You will have to watch the video to see who won the race.

Most autonomous drones use GPS to navigate. But this will not work for interior spaces and crowded urban environments, hence the efforts to develop alternative forms of computer navigation. These technologies can be used in warehouses, roads and disaster sites, said Reid.

E-mail Harrison Tasoff to [email protected] or follow him @harrisontasoff . Follow us @Spacedotcom Facebook and Google+. Original article on

Source link

Leave a Reply

Your email address will not be published.