- Charl Jooste
Drone Vision Better Than Human Eyes
Image: Iris Automation
We are all aware that machine learning, artificial intelligence and other technologies will soon start taking over many many human functions and jobs. Iris Automation are now starting to realize the full potential of their system and, according to their CEO Alexander Harmesen, they believe that their new creation has better vision than humans.
Haremsen is co-fonder of Iris Automation which is has experienced specialists including computer programmers, pilots and engineers. Many of their seasoned aviation experts come from companies such as Boeing and NASA. The team set out to create a system of sensors and digital cameras that are driven by powerful computers and software for artificial vision with amazing situational awareness. The result is a system that is more accurate and powerful than that of the human eyes and brain.
This claim comes after 7,000 purposely created real-world close encounters and in excess of 40,000 accurate computer simulated encounters. The reality of human aviation interaction and accident avoidance is that it has may shortcomings in these types of situations. Midair collisions were accurately reconstructed including a South Carolina collision between a Cessna 150 and a United States Air force F-16 in 2015. Their simulation revealed that the pilots of both aircraft had obstructed views at critical times prior to the collision.
With the right equipment, drones do not have these challenges. Cameras can be mounted in a number of areas to avoid blind spots and give a much better view than a pilot would have from the cockpit. These cameras capture light in many different wavelengths. The images are then processed by the small but powerful artificial situational awareness system known as Casia This system have been commercially available since April 26.
Within a fraction of a second the system can access everything in view and uses the current trajectory and speed to determine the safest and best path. The system then automatically controls the drone to execute the accident avoidance maneuver.
“One of the things our system is quite good at is to always be on, and always be looking at the outside world,” said Harmsen, whose 10 years of experience as a manned pilot has informed his view that distractions often interfere with seeing and avoiding traffic. He cited research that determined the average human pilot needs 12.5 seconds to see and react to converging traffic, and “for our system, it’s about 200 milliseconds. There’s a huge difference between humans and what our technology would be able to do.”
Casia equipment on left and shown mounted on a drone on right.
Images: Iris Automation
This detect-and-avoid system that Iris Automation have created is the first to effectively improve safety by avoiding objects including “non-cooperative” manned aircraft that do not use transponder signals or Automatic Dependent Surveillance-Broadcast (ADS-B) Out systems to broadcast their position. The AOPA is urging the FAA to consider this when regulating major drone exercises particularity those that beyond visual line of sight.
“There are numerous types of manned aircraft flying every day that do not and will not have a transponder or ADS-B installed,” said Rune Duke, AOPA senior director of airspace, air traffic, and aviation security. “Many general aviation aircraft do not have an electrical system that can support cooperative technology. We support the innovative work by Iris Automation and other companies who are leading the industry in detect-and-avoid solutions that are compatible with all types of manned aircraft flying in the same airspace.”
This is an important issue especially when you consider the recent approval of Google subsidiary Wing's commercial drone delivery service. Beyond visual line of sight flights will become more popular and a sophisticated and reliable system to avoid obstacles and collisions is essential. Without it, the future of the industry will be severely limited.
Harmsen believes that that quality active-detection systems that can be used on a large scale will pave the way for successful beyond line of sight operations and allow for safe and effective drone operations for infrastructure inspections, disaster relief, emergency response and a host of other applications.
After making progress with the UAV market they intend to pursue manned aircraft as well. The system has the potential to make our air safer for all and open up many opportunities in the UAV commercial and humanitarian fields.