QRPos: Indoor positioning system for self-balancing robots based on QR codes

Abstract

Localization systems for mobile robots are a trade-off between accuracy, robustness and costs. Current solutions for landmark based indoor localization are either expensive or inaccurate and unreliable. Accurate solutions for instance require costly infrastructure and/or high computational power. Additionally, self-balancing robots have particular challenges due to the unstable nature of the system. In this work, we design and develop an accurate landmark-based positioning system (QRPos) with low computational requirements that is based on QR codes mounted on the ceiling. Extended QR codes are recorded with a standard low-cost camera and are extracted and decoded with low computational requirements. Self-localization is implemented with 3D pose estimation based solely on camera data to allow for inexpensive positioning with arbitrary camera orientations. We evaluate QRPos by simulation and experiments with a low-end embedded camera against a baseline approach that is not capable of handling arbitrary camera orientations. We find that QRPos estimates pose with satisfactory accuracy and achieves positioning accuracy and robustness suitable for self-balancing robots.