When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

Seoul Robotics converts non-autonomous cars into self-driving vehicles

Seoul Robotics and NVIDIA logo

A South Korean Software company, Seoul Robotics, is employing NVIDIA technology to convert non-autonomous cars into self-driving vehicles. Rather than positioning its Level 5 Control Tower, dubbed LV5 CTRL TWR, which is a mesh network of sensors and computers, on individual cars, the system is placed on infrastructures around a facility like buildings or light poles to get a holistic view of the environment.

Seoul Robotics' Vice President of Product and Solutions, Jerone Floor, commented on the autonomy through infrastructure approach, stating:

Instead of outfitting the vehicles themselves with sensors, we’re outfitting the surrounding infrastructure with sensors. No matter how smart a vehicle is, if another car is coming from around a corner, for example, it won’t be able to see it. LV5 CTRL TWR provides vehicles with the last bits of information gathered from having a holistic view of the environment, so they’re never ‘blind.’

By directing the vehicle-to-everything (V2X) communication systems, Seoul Robotics' LV5 CTRL TWR platform, which is in early commercial deployment at a BMW manufacturing facility in Munich, allows the cars to move autonomously. The V2X technology aids in enhancing road safety, traffic efficiency, and energy savings. Currently, the company is focusing on first- and last-mile logistics such as parking.

LV5 CTRL TWR accumulates 3D data from the environment with the help of cameras and lidar. The accumulated data is then analyzed by computer vision, and deep learning-based AI to determine efficient and safe paths for vehicles within the range. Afterward, to move the car from one place to another, it uses V2X technology to control its existing features including adaptive-cruise-control, lane-keeping, and brake-assist functions.

The LV5 CTRL TWR platform has been developed using NVIDIA CUDA libraries for producing GPU-accelerated applications, along with the Jetson AGX Orin module for high-performance at the edge. For global fleet path planning, NVIDIA GPUs are employed in the cloud.

Report a problem with article
Call of Duty posters
Next Article

Call of Duty: Modern Warfare II campaign to open early on Xbox for those who pre-order

ebook offer
Previous Article

2022 Cloud Security Report — Free report