Sign in

Tatiana Verbitskaya

Tatiana Verbitskaya

Tatiana Verbitskaya is a Solutions Engineer dedicated to solving complex problems. In addition to her client-facing work at Keymakr, she is also an active contributor to the computer vision community.

Camera Calibration Validation Datasets: Ensuring Geometric Accuracy for Vision AI

Camera Calibration Validation Datasets: Ensuring Geometric Accuracy for Vision AI

Camera calibration is one of the fundamental stages in building modern computer vision systems, as it ensures an accurate geometric correspondence between the scene's three-dimensional space and its two-dimensional image. Determining the camera's internal and external parameters, as well as compensating for optical distortions,

Sensor fusion annotation for ADAS

Sensor fusion annotation for ADAS

Driver assistance systems (ADAS) combine information from cameras, lidar, radar, GPS, inertial module, and other sensors to create a comprehensive view of the road. This process, known as sensor fusion, improves the accuracy of perception, object detection, and decision-making in complex environments. However, effective sensor fusion requires precisely synchronized

Building Multi-Robot Coordination Datasets

Building Multi-Robot Coordination Datasets

Modern automation of logistical and industrial facilities requires a radical change in artificial intelligence architecture: a transition from egocentric behavioral models to collective interaction systems. Traditional training datasets instill a purely individual logic of actions in a robot, where the machine relies exclusively on its own sensors, independently calculates its

Surgical Robotics Data Annotation: Ensuring Precision in AI-Assisted Surgery

Surgical Robotics Data Annotation: Ensuring Precision in AI-Assisted Surgery

The rapid advancement of AI and robotic technologies has significantly transformed modern healthcare, particularly in surgery. AI-assisted surgical robotics systems are increasingly being integrated into clinical practice to enhance procedural accuracy, support decision-making, and improve patient outcomes. However, the effectiveness and reliability of these intelligent systems depend heavily

Sim-to-real transfer: Bridging the gap between simulated and real-world robot data

Sim-to-real transfer: Bridging the gap between simulated and real-world robot data

Modern robotics relies on simulation environments to accelerate AI development. Rather than relying on physical robots operating in real-world environments, organizations are generating large amounts of synthetic training data in virtual worlds. Simulation platforms allow for experimentation, testing, and large-scale scenario generation. However, a challenge in robotics remains

Annotating Data for Humanoid Robot Training

Annotating Data for Humanoid Robot Training

Unlike simpler automated systems, a humanoid robot's perception is built on a complex fusion of dozens of disparate information streams that must be synchronized in time with millisecond precision. The process of collecting and preparing data for such machines goes far beyond the framework of classic two-dimensional

Annotating robot demonstration data

Annotating robot demonstration data

Instead of manually programming robot behavior, robots are trained using human demonstrations, teleoperation sessions, and multimodal interaction data. This approach allows robots to learn complex manipulation, navigation, and decision-making skills. At the heart of this are simulation learning and scalable annotation datasets. They help machine learning models understand which