Seoul Robotics Announces LiDAR Enabled Autonomous Logistics Platform

The task of transporting cars from the end of the assembly line to its final destination is currently a manual and expensive logistics problem. It includes loading and unloading of vehicles from the factory floor to trucks, ships and rail, with interim stops at parking lots. Seoul Robotics aims to change this. The company has just launched Level 5 Control Tower (LV5 CTRL TWR) system which BMW is leveraging to automate last-mile fleet logistics at their manufacturing facility in Munich.

The system uses SENSR™, a proprietary perception software powered by artificial intelligence (AI) algorithms. SENSR™ works in conjunction with a mesh network of computers and LiDAR sensors located on fixed infrastructure (light poles, roof overhangs, etc) that guides vehicles autonomously through a 5G communications network. Data from the sensor network is processed to enable path planning and coordinated movement for a large population of vehicles. Drive instructions are transmitted to the vehicles (which have drive-by-wire and self-parking capabilities) via 5G or V2X communication channels. The vehicles guide themselves to parking lots (Figure 2), awaiting loading into truck or rail wagons which transport them to their final destinations.

Finished vehicle logistics is one of the least automated processes in the manufacturing and supply chain aspect of automobiles. According to Han Bin Lee, CEO of Seoul Robotics, a typical vehicle journeys through 3-6 different parking lots after exiting the factory production floor until its final sale to a customer. Manual movement incurs labor costs, and has risks associated with damage, accidents and worker safety. Automation of finished vehicle logistics has the potential to save on average $10B/year (based on ~100M new vehicles produced every year). Yearly software licensing fees are (charged on a per site basis) provide for improved capabilities in terms of vehicle capacities, accident reduction and logistics optimization.

LV5 CTRL TWR has installation costs of several million dollars per site (typically spanning ~ 2 square km, and handling automated movement of 500K cars/year). Hundreds of LiDARs are required to span an area this size. The SENSR™ perception stack is LIDAR agnostic and utilizes a combination of different LiDARs optimized for performance (range, resolution, viewing area) and cost, based on its location within the fixed infrastructure. Use of LiDAR and 3D imaging is critical for the levels of positioning accuracy required (3-5 cm), ease of initial system calibration, and enabling operation in all lighting and weather conditions. Deploying sensor networks on fixed infrastructure is highly economical since costs are proportional to the serviced and shared across a larger volume of cars.

With the successful implementation of LV5 CTRL TWR at BMW’s Munich plant, Seoul Robotics is in the early stage of commercial deployment with the OEM. Mr. Lee indicates that discussions with other automotive OEMs and Tier 1 companies are ongoing, and expects deployments to expand beyond factory-to-parking lot automation to other use cases. These include like parking-lots-to-trucks/ships as well as autonomous EV charging and vehicle testing.