Intelligent robot gripper using embedded AI sensor for box re-sequencing system integrated with spatial layout optimization

Abstract

The integration of artificial intelligence into robotic systems has resulted in a significant revolution in various industrial procedures, particularly impacting logistics and warehouse management. This impact is particularly notable due to the increasing need for automated and flexible logistics systems. A crucial factor to consider during the loading phase is the precise measurement of the weight of loaded boxes and their optimal spatial arrangement. Moreover, the possibility of boxes remaining undisturbed for extended periods underscores the significance of correctly arranging and stacking them. Incorrect stacking could result in damaged boxes, particularly if heavier boxes are placed atop lighter ones. This study presents a solution incorporating a sensory gripper with artificial intelligence to tackle the challenges of weight-based box re-sequencing and spatial optimization through Deep Reinforcement Learning. The integrated system proposed facilitates the dynamic re-sequencing of boxes based on weight during palletization. The proposed model successfully arranged eight boxes of the same size, weighing between 62 and 326 g. The arrangement of the stacked boxes also varied according to weight, from the heaviest to the lightest, demonstrating the effectiveness of the re-sequencing algorithm utilizing both fundamental and embedded artificial intelligence models. The embedded artificial intelligence model provides similar accuracy levels while emphasizing its advantage of being 88.6 % smaller compared to the basic model.