This post is also available in: heעברית (Hebrew)

Autonomous vehicles require 3D vision to understand what lies ahead and to give the vehicle enough time to plan a safe path given a complex and changing environment. 

3D vision systems will be developed for US military off-road autonomous ground vehicles. Within the framework of a $1.67M SBIR Phase II contract, NODAR will be working with the US Army in developing 3D vision systems for autonomous military vehicles operating in off-road and harsh environments. 

Rather than detecting pedestrians, traffic signs, and signals as done for passenger vehicles, the company’s Hammerhead technology will be used to sense terrain, vegetation, and other off-road obstacles in degraded visual environments that have low or no light, dust, smoke, rain, or other harsh conditions.

The long-range, high resolution, real-time 3D sensing is achieved through the use of independently mounted cameras while remaining resilient to unfriendly environmental conditions, according to the company. “3D vision system produces dense 3D point clouds with highly accurate distance estimates to each pixel in the scene. These data provide the detail needed to navigate through difficult terrain and around obstacles.”

The long-range vision systems can sense up to 1,000 meters, which allows the perception system to detect hidden threats long before the vehicle enters the area. To achieve this, NODAR mounts multiple cameras with overlapping views on the vehicle and applies patent-pending computer vision software to maintain alignment between cameras. 

Hammerhead uniquely provides 360 degrees, long-range, high-density, high frame-rate 3D data in real-time to the vehicle’s navigation system, according to