This post is also available in: heעברית (Hebrew)

A new LiDAR perception system delivers highly accurate object detection, tracking, and classification, bringing the enhanced capabilities that enable autonomous vehicles to new industries. 

Endeavor is a multi-sensor plug-and-play LiDAR solution that offers edge processing with deep learning. The system developed by Seoul Robotics is equipped with SENSR, the company’s proprietary perception software that uses deep learning to analyze and understand 3D data, as well as LiDAR sensors and a GPU. 

The flexible solution can mix and match different makes and models of LiDAR, even 3D sensors from different brands. This versatility makes the system an all-purpose solution for a range of applications, including smart cities, intelligent transportation systems, retail analytics, crowd monitoring, security, and more.

The kit can connect up to eight 32-beam rotating sensors at one time, capturing a surface area of up to 50,000 square meters.

The system shortens the time to deployment and is more accessible to industries that often face bandwidth and cost constraints. 

The backbone of this solution is SENSR, a computer vision software that uses deep learning to create accurate 3D models of the world in real time. It can detect more than 500 objects at one time within a four-centimeter radius, up to 200 meters, and predict up to three seconds in advance. 

SENSR is equipped with weather-filtering AI, enabling it to detect and track fast-moving, partially obstructed, or clustered objects even in heavy snow or rain.