POSCO DX is embarking on the joint development of Physical AI-based robot intelligence technology applicable to various robots for performing high-risk and high-intensity tasks in industrial sites, together with NC AI, an AI specialist company.

POSCO DX (CEO Shim Min-suk) signed a Memorandum of Understanding (MOU) for the implementation of an AI-based autonomous robot work system on the 29th at NC AI (CEO Lee Youn-soo)’s Pangyo headquarters, with the attendance of officials from both companies, including Yoon Suk-june, Head of POSCO DX’s Robot Automation Center, and Kim Min-jae, CTO of NC AI. We plan to proceed with the implementation of a robot foundation model that combines POSCO DX’s robot simulation and control technologies with NC AI’s AI models.

Under this agreement, POSCO DX plans to perform motion planning and control simulation verification for robots to be applied to industrial sites, and to configure and provide a digital twin- based virtual test environment to ensure stable operation of the robots.

NC AI is responsible for developing AI models for the Robot Foundation. By collecting and analyzing industrial site data to enable robots to understand various work situations, the company plans to enhance robots’ decision-making capabilities and operational accuracy by developing and applying Vision Language Action(VLA) models based on this data. Furthermore, it will collaborate with POSCO DX on establishing and stabilizing a digital twin-based VLA simulation environment.

It is expected that when the Robot Foundation model jointly developed by the two companies is applied, industrial robots will be able to simultaneously understand visual information and verbal instructions to interpret and judge work situations on their own. This means that by enabling flexible responses to various variable factors that frequently occur in industrial settings, such as deviations in workpiece position or differences in interfaces between equipment, robots can handle even non-standard tasks that were previously limited by the rule-based control of existing industrial robots.

Through this, VLA- based robots are expected to not only replace hazardous or repetitive tasks previously handled by human workers but also naturally establish a collaborative system with other industrial robots on-site, thereby significantly enhancing safety, precision, and efficiency in manufacturing environments.

POSCO DX is continuously advancing industrial robot automation technology, centered around its Robot Automation Center. By implementing simulation-based verification and establishing standardized models, the company is enhancing the stability and deployment speed of industrial robots. Furthermore, by developing a heterogeneous robot operation platform, it is strengthening operational efficiency through the integrated management of various robots and real-time data analysis. This collaboration is significant as it represents an attempt to advance physical AI technology in industrial robot automation to the next level by combining POSCO DX’s foundational technologies with NC AI’s advanced AI capabilities.

Yoon Suk-june, Head of the Robot Automation Center at POSCO DX, stated, “Through continuous collaboration with companies possessing specialized technology, we are internalizing core solutions such as robot control and operation platforms and elevating the level of automation technology for high-risk and high-intensity sites.” He added, “We expect this collaboration to confirm the potential for utilizing general-purpose robots in industrial settings.”

Kim Min-jae, CTO of NC AI, said, “General-purpose robot technology is rapidly evolving into next-generation AI technology applicable in various industrial environments.” He continued, “Through our collaboration with POSCO DX, we will strengthen our competitiveness in robot AI technology and jointly lead the general-purpose physical AI ecosystem targeting the global market.”

Leading the spread of AX in the industrial field with applications such as coil unloading systems for tens of tons of steel products

POSCO DX (President Shim Min-suk) is accelerating its manufacturing AX (AI Transformation) by advancing its ‘Physical AI’ technology based on virtual environment simulation and applying it to the field one after another.

POSCO DX announced that it has developed an AI model that replicates a real-world factory in a virtual environment and established a ‘physical AI’ development system that efficiently supports AI learning and verification prior to field application. Facilities and sensors at industrial sites are greatly affected by the physical environment such as inertia, acceleration, and noise, and by implementing conditions that can be encountered in the real world in a virtual space and conducting various simulations, AI can learn the optimal movement of facilities.

At actual industrial sites, there were limitations in acquiring field data and testing AI models due to disruption of operations or safety and security reasons. POSCO DX utilized virtual environment simulation to solve these issues and is expected to significantly reduce the time and cost of AI model development and field application.

POSCO DX has implemented virtual environment simulation by adopting Isaac Sim of NVIDIA Omniverse platform. Isaac Sim is a SW that supports verification by simulating the physical environment precisely with actual sensors and systems in a virtual environment.

POSCO DX recently built a specialized optical laboratory in its Pangyo office building to further advance its ‘physical AI’. The optical laboratory is a space where the response of sensors and precision according to specifications, which are difficult to identify in AI simulations, are tested by artificially creating an environment similar to the actual site in terms of lighting, temperature, and movement. By reflecting the sensor data verified here in the AI ​​simulation, it is evaluated that the gap between the virtual and actual sites has been minimized, enabling more efficient simulations.

On the other hand, ‘Physical AI’, which was the topic of this year’s CES 2025, refers to AI that recognizes the surrounding environment and interacts with the real world by controlling physical systems. ‘Physical AI’By applying , AI can recognize and judge various operation situations and control and operate facilities directly with the on-site control system (PLC, Programmable Logic Controller), enabling unmanned operation. POSCO DX is leading the spread of ‘Physical AI’ in industrial sites by converging AI technology with existing IT (information technology) and OT(automation technology).

POSCO DX ‘physical AI’ to cranes that transport atypical products with different sizes and packaging forms.is prioritizing the application of In the first half of this year, POSCO DX developed an AI model to automate the unloading of coil products transported on trailers into cranes, and plans to spread it horizontally by conducting virtual test drives and applying it to the field.

Yoon Il-yong, head of POSCO DX AI Technology Development Center, emphasized, “POSCO DX is pursuing the implementation of ‘physical AI’ technology with the goal of ‘autonomous physical systemization of manufacturing facilities’ based on the convergence of AI, IT, and OT technologies,” and added, “We will strive to establish ourselves as a leading company in intelligent factories by advancing ‘physical AI’ utilizing physical development methodologies such as virtual environment simulation.”

▲POSCO DX AI researchers are testing the physical environment, such as light and distance, of the coil loading and unloading site in the optical laboratory of the Pangyo building.