US firm eyes smarter, faster factory robots to speed up work with new South Korean deal

A US technology company has announced a strategic partnership with a South Korean robotics firm to accelerate the adoption of Physical AI across manufacturing and logistics industries. Under the collaboration, Grid Dynamics will provide Doosan Robotics’ industrial collaborative robot (cobot) customers with an end-to-end software stack for physical AI, along with integration services designed to simplify deployment. The combined offering aims to enable advanced automation tasks, including inspection of complex-shaped objects, assembly involving variable components, and packaging of previously unseen or deformable items. The companies say the partnership will help manufacturers deploy AI-powered robotic systems more quickly while expanding physical AI applications across industrial operations. Automation beyond robots Doosan Robotics is one of the world’s leading collaborative robot (cobot) manufacturers, with its robots deployed across manufacturing, logistics, food and beverage, electronics, automotive, and healthcare industries. Unlike traditional industrial robots that operate inside safety cages, Doosan’s cobots are designed to work safely alongside human workers using integrated force and torque sensors that detect collisions and limit contact forces. The company’s product portfolio includes the lightweight A Series for general-purpose automation, the M Series for high-precision tasks, the H Series for heavy-duty applications with payloads up to 55 pounds (25 kilograms), and the P Series, which offers food-grade, NSF-certified models suitable for food-handling and pharmaceutical environments. Depending on the model, Doosan cobots can perform pick-and-place operations, machine tending, palletizing, welding, quality inspection, dispensing, polishing, and packaging. Their open software architecture and support for AI-based vision systems allow manufacturers to automate more complex, variable tasks while reducing deployment time and improving workplace flexibility. Meanwhile, Grid Dynamics’ GAIN (Grid Dynamics AI-Native) Platform for Physical AI is designed to help manufacturers deploy AI-powered robotic systems across factory and warehouse operations. The platform combines robotic manipulation, digital twin simulation, computer vision, and IoT monitoring into a single software stack for industrial automation. Its robotic manipulation capabilities support AI-driven tasks such as pick-and-place operations, flexible assembly, toolpath execution, and bimanual workflows using Vision-Language-Action (VLA) models on ROS-compatible robots. NVIDIA Omniverse-powered digital twins enable manufacturers to simulate, validate, and optimize production lines before deployment, reducing downtime and improving throughput. The platform also uses vision-language models to monitor production processes, detect safety violations, verify packaging accuracy, and track workflow performance in real time. An integrated IoT control tower combines data from robots, machines, cameras, and sensors to enable predictive maintenance and anomaly detection. Grid Dynamics says the platform has delivered measurable gains, including inspection cycles up to 1,000 times faster and anomaly detection 24 times quicker in industrial deployments. AI powers cobots As part of the partnership, Grid Dynamics will now offer Doosan cobot users access to its GAIN Platform, which supports integrating physical AI models and enables optimization and monitoring of robotic operations through digital twin technology. The combined solution is intended to address automation tasks that are difficult for conventional robotics software, including processing and inspection of complex-shaped objects, assembly involving variable components, and packaging of previously unseen or deformable items. By combining AI-driven software with collaborative robotic hardware, the companies aim to expand the range of manufacturing and logistics applications that can be automated. The partnership also includes a joint go-to-market strategy focused on delivering an integrated hardware-and-software physical AI stack as a turnkey solution for industrial customers. In addition to commercial deployment, the companies plan to collaborate on research and development to advance robotics policy control technologies, which govern how robots learn and execute complex manipulation tasks. “Our mission is to provide industrial users with production-grade solutions for unlocking high-value use cases such as dual-arm assembly and packaging. Our partnership with Doosan enables the full-stack solution approach and more efficient go-to-market execution using global footprints of both companies,” said Ilya Katsov, CTO, Americas for Grid Dynamics, in a statement. Recommended ArticlesGet the latest in engineering, tech, space & science - delivered daily to your inbox.Jijo is an automotive and business journalist based in India. Armed with a BA in History (Honors) from St. Stephen's College, Delhi University, and a PG diploma in Journalism from the Indian Institute of Mass Communication, Delhi, he has worked for news agencies, national newspapers, and automotive magazines. In his spare time, he likes to go off-roading, engage in political discourse, travel, and teach languages.