<![CDATA[In the advanced era of technology has accelerated automation across various sectors, including the logistics industry, which requires material handling processes to be fast, efficient, and safe. One of the key pieces of equipment supporting these operations is the forklift. However, manual forklift operation remains prone to accidents due to limited visibility, operator fatigue, insufficient skills and concentration, as well as inadequate forklift maintenance. According to the National Safety Council, more than 24,000 forklift-related accidents were recorded in 2022. As an automation solution, Automated Guided Vehicles (AGVs) have been widely developed for material handling applications. Nevertheless, most AGVs still rely primarily on sensor-based navigation and have not yet integrated computer vision for object recognition and destination determination. Therefore, this study proposes the design and development of a forklift robot that integrates YOLOv8-based computer vision with line follower navigation to perform autonomous material handling based on QR Code information. YOLOv8 is employed to detect QR Codes, while the decoded information is used to determine the destination for object placement. The transported object is a square-shaped item measuring 10 × 10 cm, equipped with a 4 × 4 cm QR Code facing the robot to ensure successful detection. System evaluation was conducted in a laboratory environment using a line follower track to simulate an automated material handling process. The experimental results show that the QR Code recognition system achieved a 100% detection accuracy across 40 test trials. The overall material handling effectiveness reached 74%, with 177 successful tasks out of 240 trials. The success rates for object lifting, intersection detection, and object placement were 100%, 98%, and 93%, respectively. Performance degradation occurred during intersection exit, returning to the main path, and returning to the home position due to limitations in line sensor readings, track conditions, and motor speed stability. The results demonstrate that the integration of YOLOv8-based computer vision and line follower navigation is capable of supporting autonomous material handling in a laboratory-scale environment.]]>
