Education Information: India sent Lakhs of Students to US in 2018-19, Second Largest after China  |  Policy Indications: National Policy on Biofuels  |  Technology Inceptions: Asus unveils dual-screen laptop series  |  Teacher Insights: Social hardship harms language skills  |  Science Innovations: Strong storms can generate quake-like seismic activity  |  Parent Interventions: Community care system benefits youth  |  National Edu News: Interdisciplinary Centre for Energy Research launched  |  Education Information: SCHOOL EDUCATION QUALITY INDEX  |  Health Monitor: ‘Health System for a New India: Building Blocks–—Potential Pathways to Reform’  |  Policy Indications: WCD Ministry to announce Bharatiya Poshan Krishi Kosh  |  Science Innovations: Dr. Harsh Vardhan calls for Developing Innovative Cooling Solutions  |  Policy Indications: Rashtrapati Bhavan to Host Conference of Directors of IITS,NITS and IIEST 19 Nov  |  Policy Indications: PM proposes first meeting of BRICS Water Ministers in India  |  Policy Indications: First ever International Buyer- Seller Meet in Arunachal Pradesh  |  National Edu News: UNICEF-Department of Posts Conduct Stamp Design Contest for Children  |  
November 23, 2017 Thursday 04:48:06 PM IST

Human pilot beats AI in speed

Science Innovations

Washington: In a drone race that pitted a world-class pilot against Artificial Intelligence (AI), the human pilot emerged faster although the AI flew the drone more smoothly and consistently, NASA scientists have announced. The scientists raced drones controlled by AI against a professional human pilot on October 12 to put their work to the test. 

The results declared this week showed that world-class drone pilot Ken Loo averaged 11.1 seconds, compared to the autonomous drones, which averaged 13.9 seconds. "We pitted our algorithms against a human, who flies a lot more by feel," said the project's task manager Rob Reid of NASA's Jet Propulsion Laboratory in Pasadena, California.

"You can actually see that the A.I. flies the drone smoothly around the course, whereas human pilots tend to accelerate aggressively, so their path is jerkier," Reid added. The race capped off two years of research into drone autonomy funded by Google. 

The company was interested in JPL's work with vision-based navigation for spacecraft -- technologies that can also be applied to drones. To demonstrate the team's progress, JPL set up a timed trial between their AI and drone pilot Loo.


The team built three custom drones, named Batman, Joker and Nightwing, and developed the complex algorithms the drones needed to fly at high speeds while avoiding obstacles. These algorithms were integrated with Google's Tango technology, which JPL also worked on.

The drones were built to racing specifications and could easily go as fast as 129 kilometre per hour (kph) in a straight line. But on the obstacle course set up in a JPL warehouse, they could only fly at maximum 64 kph before they needed to apply the brakes.

Compared to Loo, the drones flew more cautiously but consistently. But Loo attained higher speeds and was able to perform impressive aerial corkscrews. But he was limited by exhaustion, something the AI-piloted drones did not have to deal with, NASA said. 


Comments