LG Electronics announced it is advancing its robotics collaboration with NVIDIA. Senior executives from LG Electronics and LG Group affiliates met with NVIDIA officials at LG’s Data Factory, under construction at the company’s Yangjae R&D Campus in Seoul, to review the collaboration and discuss further steps.
LG Group and NVIDIA signed a memorandum of understanding for strategic collaboration on future business initiatives at NVIDIA’s headquarters in Santa Clara, California, on August 13. The companies reconvened four days later at the Data Factory.
Officials reviewed the status of the Data Factory, scheduled to become fully operational by the end of the year. LG has deployed its LG CLOiD home robots at the facility to generate, collect and learn from data.
The Data Factory includes training spaces for robots to practice tasks, areas for validating and refining data sets, a replicated home environment where LG CLOiD units learn and repeat cleaning tasks, and a simulated manufacturing space modeled on LG’s washing machine plant in Tennessee, where the robots move, stack and assemble parts. The robots are also deployed in LG CNS logistics automation solutions and in a space where LG Innotek trains robotic hands. Data collected from these environments will be linked with NVIDIA’s robotics stack, where it is augmented and synthesized for robot learning.
LG is combining decades of manufacturing and logistics data with NVIDIA’s open robotics development platform to build a data flywheel for robot learning. The Data Factory functions as a site where robots collect data through physical learning and as a base for expanding, synthesizing and amplifying robot-learning data from LG’s manufacturing and logistics sites and home appliances worldwide. NVIDIA’s physical AI technologies, including NVIDIA Omniverse libraries, NVIDIA Cosmos open world models and the open NVIDIA Isaac robotics development platform, are used from data to deployment.
The Yangjae facility spans four floors (one basement level and three above ground) with a total floor area of 10,000 square meters and is planned to house several hundred robots by the end of the year. LG plans to continue upgrading its data-learning systems. By the end of this year, training data collected at the facility and data synthetically generated and augmented using NVIDIA Cosmos open world models are expected to total 100,000 hours, equivalent to roughly 12 years of data.
LG plans to use this data to advance its Robot Foundation Model, which underpins the performance of humanoid robots.
LG has designated this year as the starting point of its robotics push. Last month, the company established a Robotics Business Center that reports directly to the CEO and oversees the companywide robotics business. LG has a presence in the industrial and commercial robotics markets and plans to expand into home robotics. The company has expertise in manufacturing and developing core robotic components, including actuators.
“Through the synergy built on ‘One LG’ – bringing together core capabilities across the Group – and strategic collaboration with global partners, we will secure our competitiveness in physical AI and become a comprehensive robotics solutions provider,” said Lyu Jae-cheol, CEO of LG Electronics.
