AI Technology Helps Drones Sense and Avoid Obstacles

Iris Automation, a Vancouver-based startup, raised $1.5M to bring their technology to industrial-type drones.

Using NVIDIA GPUs on the Amazon cloud to train their deep learning models and a Jetson TX1 onboard the UAV, Iris’ technology analyzes and draws insights from videos captured by the drone’s cameras in real-time. Its system has a detection range of over 500 meters, significantly farther than what others can currently do.

“We’re designing this to work like a human pilot’s vision and decision-making process,” says Iris Automation CEO and co-founder Alexander Harmsen.

Iris Automation’s artificial intelligence module combines 3D maps and real-time images to avoid mid-air collisions.

The company mentions that industrial drones need a special collision avoidance system versus consumer drones, since they need to cover long distances and capture video of expansive infrastructure that doesn’t show up on a street map, such as a change in weather or new construction.

An Iris investor believes their technology is applicable beyond drones and can be used for other situational awareness systems in cars or ships.

Read more >

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter