Marker-based Detection and Pose Estimation of Custom Pallet using Camera and Laser Rangefinder

Abstract

This paper presents an innovative approach to detect and estimate the pose of pallets in a warehouse environment using a combination of ArUco fiducial markers and a laser rangefinder sensor. ArUco markers are unique patterns placed on pallets to assist the detection process. Computer vision algorithms process the camera’s information to estimate the pallet’s position and orientation. Adding the laser rangefinder sensor enhances the accuracy of the distance estimation. Experiments and evaluations were conducted to examine the accuracy and reliability of the proposed system, showing highly accurate and reliable results. The study showed that the combined approach outperformed using ArUco or laser rangefinder separately. The distance measurement had an error rate below 1 percent and 0.82cm for the standard deviation. The orientation measurement had an average error of 1.21 degrees. Consequently, the combination method offers excellent accuracy and precision for distance and orientation measurements. The proposed method could be a solution for implementing an autonomous forklift to increase efficiency and productivity while reducing human error in the warehouse system.