Collision-avoidance system provides 'eyes and brain' for drones

April 29, 2019 //By Rich Pell
Collision-avoidance system provides 'eyes and brain' for drones
AI and safety avionics startup Iris Automation (San Francisco, CA) has announced that it has launched the first commercially available computer vision detect-and-avoid solution to enable Beyond Visual Line of Sight (BVLOS) operations for autonomous vehicles.

The system, called Casia, detects other aircraft, uses machine learning to classify them, makes intelligent decisions about the threat they may pose to the vehicle, and triggers automated maneuvers to avoid collisions. Casia, says the company, is the first system that allows an Unmanned Aircraft System (UAS) to truly understand the aviation environment around it as if a pilot were on board.

"Casia is the critical piece our industry has been dreaming about for years – finally allowing us to use drones to their full commercial potential," says Iris Automation CEO Alexander Harmsen. "By unlocking BVLOS flight with Casia, operators all over the world will be able to use their aircraft in every conceivable scenario."

A combination of both hardware and software that's ultra lightweight, low power, and small in size, Casia comprises sophisticated artificial intelligence algorithms and software packaged in a self-contained supercomputer that works with a machine vision camera. The Casia technology, says the company, has been extensively tested, with 7,000+ real-world test flights and mid-air collision scenarios – flying various manned aircraft against UAS – and over 40,000 encounters in simulation.

Casia also ran a successful early adopter program with more than 30 participating beta customers from five countries. The company says it is working directly with regulators around the world to make drones safer and more accessible, ensuring Casia achieves the highest levels of safety for national airspace use.

With the Casia launch, the company will also offer customers regulatory support for Part 107 waiver writing and regulatory approval processes to secure the necessary permissions for their unique UAS operations.

Iris Automation

Related articles:
NASA drone race pits human pro vs AI
Drones learn autonomic navigation from cars and bicycles
Frankfurt airport operator tests concepts for autonomous air taxis
Autonomous drone algorithm herds bird flocks away from airports
Microsoft, DJI deal brings advanced drone tech to businesses


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.