Rosota Selected for TIPS to Standardize Surgical Data

Recap

Source: 테크월드, report of Oct. 2, 2026

According to the report, Rosota, a surgical data-based AI robotics company, announced on October 2 that it was selected for the Ministry of SMEs and Startups' '2026 TIPS R&D General Track' program. The selected project focuses on developing technology to collect and standardize surgical technique data for training a 'Surgical Robotics Foundation Model.'

Rosota is developing a system that uses its proprietary collection device, 'SurgiLogger,' to systematically gather data generated during actual surgeries and standardize it for AI learning. The company emphasizes that video alone is often insufficient to capture the nuances of instrument manipulation. Therefore, the system utilizes kinetic, motion, and gyro sensors to acquire physical-based data. SurgiLogger is designed to attach directly to existing laparoscopic instruments without altering their internal insertion parts or basic usage methods. It collects manipulation information—including instrument position, direction, movement, insertion depth, jaw opening/closing state, and force data—synchronized with video. The company is currently verifying instrument compatibility, sterilization methods, and practical usability in the field.

CEO Seo Ye-chan stated that acquiring systematic physical data from the surgical site is essential for AI to learn surgical techniques but has been difficult to achieve. He noted that Rosota is one of the few companies collecting this type of data via SurgiLogger. The company plans to use the standardized data to train its foundation model and envisions a future 'copilot' service that allows surgeons to monitor the surgical process in real-time.

Context

TIPS (Tech Incubation Program in Startup) is a prominent Korean government startup support program that links private investment with public R&D funding. Private operators identify promising startups, invest in them, and recommend them to the government, which then provides research and development support. This program is a key pathway for early-stage Korean tech companies seeking to scale their technology with reduced financial risk.

In the broader field of surgical robotics, most AI development has historically relied heavily on visual data from cameras. However, recent trends in foundation models suggest that multimodal data, including haptic and kinematic information, is crucial for understanding the physical interaction between instruments and tissue. Rosota's approach aligns with this shift by focusing on the physical manipulation data that is often missing from standard video feeds.

Robot's take

Rosota's focus on physical data collection is a significant differentiator in a market dominated by vision-only AI. By capturing force and motion data, the company may be able to train models that understand the 'feel' of surgery, which is critical for safe robotic assistance. However, the challenge lies in the practicality of the hardware. Attaching sensors to existing instruments without disrupting the sterile field or surgeon workflow is a non-trivial engineering problem. The success of this project will depend on whether the SurgiLogger can be seamlessly integrated into high-pressure operating room environments. If they can standardize this data, it could become a valuable asset for training general-purpose surgical AI models, but widespread adoption will require rigorous clinical validation and regulatory approval.