A robot that picks up drinks and snacks by itself and organizes them in front of a supermarket display shelf. It is still an unfamiliar scene, but a domestic startup has brought it to the stage of applying it to actual industrial sites. Cairovada, a spin-off from the research team of Professor Kim Hee-won of the Soongsil University artificial intelligence (AI) convergence security department.
Cairova is an AI robot corporations that designs both the software (SW) that serves as the robot's "brain" and the hardware (HW) that serves as its "body." Unlike the conventional approach of developing only robot control software or producing only hardware, it provides an integrated robot solution that can operate immediately in actual industrial settings.
The problem Cairova focuses on is a longstanding limitation of the robotics industry. It is difficult for existing robots to work properly in environments where the location of objects changes even slightly or where people and obstacles move together. In spaces without fixed rules, such as supermarkets, logistics centers, and production sites, automation has progressed slowly.
The company chose a method of first training robots in a virtual space and then applying the results to real robots. Using Nvidia's robot simulation platform "Isaac Sim," it completes thousands and tens of thousands of trial-and-error runs in a virtual environment and then has the robot perform tasks immediately in the real world. This can significantly reduce the time and expense incurred during physical experimentation.
Cairova has already completed the proof-of-concept (PoC) stage. It implemented convenience store and supermarket display shelves in a virtual environment and succeeded in reliably performing tasks to recognize, pick up, and display drinks and snacks.
To that end, it also built a mobile dual-arm robot for demonstration in-house. Combining a mobile platform with two robot arms, it verified whether the software and hardware work together in an environment similar to an actual store.
CEO Kim Hee-won said, "Our strength is that we designed the entire architecture ourselves, from robot control to sensor input and AI decision-making," adding, "We conducted precise analyses of work procedures, logistics routes, and robot motion ranges and reflected them in the hardware design."
Cairova's goal does not end with convenience store shelf-stocking robots. It is currently advancing simulations that also take into account supermarket and large logistics center environments. It is refining technology so that in logistics sites where travel routes are complex and obstacles change frequently, robots can make their own decisions and continue working.
Going forward, it plans to expand applications to manufacturing processes and service robots. The architecture does not depend on a specific robot maker, allowing the company to apply only software to existing robots or, if needed, to provide custom robot hardware together.
Cairova's technical foundation has already been validated in academia. CEO Kim Hee-won has presented numerous papers at global AI societies such as the Computer Vision and Pattern Recognition Society (CCVPR) and the Association for the Advancement of Artificial Intelligence (AAAI). In the international competition that tests robot manipulation capabilities (Arnold Challenge), it ranked No. 1 in the world this year and No. 3 last year, demonstrating competitiveness in practical control technology.
The company currently has 16 master's and doctoral-level researchers, and talent with hands-on experience at Nvidia, Qualcomm, and the Korea Institute of Science and Technology (KIST) is leading development.
Cairova emphasizes its social role alongside technology development. Supermarkets, logistics centers, and production sites suffer from chronic labor shortages. If robots can take on repetitive and strenuous tasks, two benefits can be expected at once: easing labor shortages and improving working conditions.
Kim said, "Rather than replacing people, we hope robots become tools that take on jobs that are hard for people," adding, "Our goal is to build technology that can actually be used in the field."
Cairova moved into the Soongsil University Campus Town as part of the Seoul City Campus Town project. The Soongsil University Campus Town Promotion Team selects promising startups as resident corporations and provides startup space, practical training, business advancement support, and consultations with experts in each field.