LG CNS on the 7th unveiled PhysicalWorks, a robot transformation (RX) platform that cuts the on-site deployment period for industrial robots from several months to 1–2 months. The company said it will use this as a starting point to aggressively expand its Robotics business, cited as a future growth engine.
At the RX Media Day held that day at LG Science Park in Magok, Seoul, LG CNS introduced PhysicalWorks, which integrates and manages the entire cycle from robot data collection, training, verification, field application, operation, to control. LG CNS is the first to debut an end-to-end RX platform brand that spans from robot training to operation. The key is to quickly train intelligent robots and settle them into the field.
PhysicalWorks consists largely of two core platforms: PhysicalWorks Forge and PhysicalWorks Baton.
PhysicalWorks Forge is designed with the goal of training and hardening robots to a level where they can be deployed in real-world sites. It handles the entire process in one place, from data collection needed for robot training to robot verification and field application. Forge means "to harden."
A key feature of Forge is its use of simulation data training. An LG CNS official said, "Moving beyond the conventional method where robots mimic human actions thousands of times, we improved efficiency by using simulation data that implements real sites and tasks in a 3D virtual environment for training." The company plans to additionally apply methods that convert videos of human work into training data or use motion capture.
The selection process for the collected data is also automated to filter, organize, and process data to improve training efficiency. For example, during training where a robot picks up products in a factory, it selects only successful actions or removes unnecessary sections.
Robots that complete training are validated for task feasibility and stability through simulation in a 3D virtual environment, then optimized for actual sites before deployment. The company emphasized, "With this, the time from robot training to field deployment can be shortened from several months to 1–2 months."
Baton is a platform that issues work instructions to, and provides integrated control and management for, various types of robots, including bipedal, quadrupedal, and wheeled types. It helps operate robots of different manufacturers and forms within a single system.
An LG CNS official said, "Baton standardizes and systematizes robot operating status and control information so robots of different manufacturers and types can be managed efficiently."
Baton automatically allocates tasks to each robot using mathematical optimization and optimizes movement routes to prevent collisions. Agentic AI reflects task progress and changes in equipment status in real time to adjust workflows. For example, if a conveyor belt stops, it automatically restructures logistics routes, and if a specific robot stops, it immediately transfers the task to another robot.
LG CNS projected that applying PhysicalWorks Baton to a robot operation environment with about 100 units, such as autonomous mobile robots (AMR) and automated guided vehicles (AGV), would increase productivity by about 15% or more and cut operating costs by up to 18%. The company said the effect is greater in environments where robots from various manufacturers are mixed, as redundant movement, congestion, and manual intervention are reduced.
According to LG CNS, PhysicalWorks Forge is currently being used in proof-of-concept (PoC) projects with more than 20 customers. PhysicalWorks Baton is being used in the Busan Smart City national pilot city project to provide integrated control for four types of robots: patrol, barista, baggage-carrying, and cleaning.
Hyun Shin-Gyoon, CEO of LG CNS, said, "The key to RX is not determined by simply acquiring robots, but by whether you can quickly settle robots into the field so they can work, and operate them sustainably even as environments change."
He added, "Based on full-stack capabilities that span from establishing robot adoption strategies optimized for customer sites, securing robot foundation models (RFM) specialized for industries, to robot training, application, and operation, we will set a new standard for commercializing Physical AI and ultimately realize an autonomous operation system centered on robots."
At the event, LG CNS also demonstrated for the first time in Korea heterogeneous robots autonomously performing tasks through learning without human remote control. Four types of robots—bipedal, quadrupedal, wheeled, and autonomous mobile robots (AMR)—that completed training with PhysicalWorks Forge worked organically together in a logistics site based on PhysicalWorks Baton to carry out tasks.