Autonomous robot and its position calibration method

This technology corrects sensor and control errors that occur during the localization and mapping process of autonomous mobile robots. It generates a noise-minimized map by inputting real-time robot-centric maps and global maps into a style-transfer learning model, using the result to calibrate the robot's position.

Existing autonomous robots often suffer from degraded localization performance in real-world operation due to discrepancies between simulated and actual environments, as well as measurement errors from odometry sensors and motor control inaccuracies.

This technology utilizes an operation control program to generate robot-centric and global maps. By applying a style-transfer learning model between ground-truth image sets and real-world image sets, it produces transformed map data used to calibrate the navigation agent's position estimates, enabling precise localization and mapping in real-world environments. Because it bridges the gap between simulation and reality using only a learning model—without the need for additional sensors—it significantly reduces development costs and trial-and-error during the commercialization of logistics and service robots.

‍

‍

Key Features:

• Drive unit, camera, and odometry sensors for moving the autonomous robot
• Control unit that estimates the autonomous robot's position using captured video and distance data
• Operation control program that generates a robot-centric map based on real-time video and a global map based on localization data
• Calibrating position by inputting the robot-centric and global maps into a style-transfer learning model to generate a transformed map