An Efficient Generative Intelligent Multiobjective Grasping Model for Kitchen Waste Sorting

The key challenge in automated kitchen waste sorting on conveyor belts is how robots execute grasping tasks. Current methods, dependent on object detection, struggle to adopt generative architectures due to data scarcity and algorithmic inefficiency. To solve these issues, this article proposes solutions in three aspects: dataset construction, annotation data processing, and generative model lightweighting. First, we built the KWG2024 dataset, which includes 3116 RGB-D images, 18231 standard annotations, and three new evaluation metrics. Second, we proposed two novel annotation processing methods to address the issue of excessive and incorrect grasps generated by generative networks in single-attempt grasp planning of multiobjects. Third, we constructed an efficient network with classification capabilities, AMI-LiteNet, by integrating the advantages of PP-LiteSeg and AMI-NanoNet. On the public Cornell dataset, AMI-LiteNet achieved a grasping accuracy of 98.3% and an efficiency of 118 frames per second (FPS). In extensive comparative experiments on KWG2024, our model reached a leading computational efficiency compared with recent state-of-the-art methods. It acquired a grasp planning generation accuracy of 87.96% while only requiring a computational effort of 2.79 GFLOPs. Finally, our model was deployed on an edge computing device and achieved a maximum grasping accuracy of 90.91% and a classification accuracy (CA) of 97.48% in our actual robotic system. To our knowledge, this is the first time that a generative grasp method has been applied independently to kitchen waste sorting tasks on a conveyor belt.