Smart Vision-Guided Robotic Depalletising System
Author
Term
4. semester
Education
Publication year
2026
Submitted on
2026-01-30
Pages
51
Abstract
Automated depalletising is a massive chal- lenge in warehouse automation due to high variability in parcel size, shape, material, and stacking configuration. While recent advances in AI-based perception have en- abled robotic systems to operate in mixed- SKU environments, limitations remain in ro- bustness, autonomy, and generalisation un- der unstructured conditions. This thesis in- vestigates the design and implementation of a robotic depalletising system that integrates vision-based object detection, segmentation, and pose estimation. A modular percep- tion pipeline is developed to process RGB-D data and extract graspable objects from pal- let scenes. The system employs depth-based segmentation combined with edge-based de- tection for accurate box identification, and RANSAC-based plane fitting for pose es- timation without requiring prior knowledge of parcel dimensions. The system is im- plemented within a ROS2-based architec- ture using a UR10 collaborative robot, VG10 vacuum gripper, and Intel RealSense D455 RGB-D camera. Experimental evaluation across three scenarios of increasing com- plexity shows 93.3% detection accuracy and 83.3% overall pick-and-place success rate.
Documents