Global waste generation is projected to reach 3.40 billion tons by 2050, necessitating improved waste sorting for effective recycling and progress toward a circular economy. Achieving this transformation requires higher sorting intensity through intensified processes, increased efficiency, and enhanced yield. While manual sorting remains common, smaller plants often use positive sorting to recover recyclables, and larger plants combine automated systems with manual sorting. Negative sorting is employed to remove impurities and improve material quality. However, innovation in manual sorting has stagnated. Advances in Machine Learning and Artificial Intelligence offer transformative potential for waste management, with digitalisation and improved recyclate quality becoming priorities. Despite these trends, manual sorting is still largely treated as a digital black box. The presented research outlines the design of a novel, human-centric AI-powered assistance system to support sorting workers by enhancing decision-making and real-time assistance during the sorting process, driving the digitalisation of manual sorting. Potential use cases, system requirements, and essential components were explored. High-quality use case-specific data is essential for model training. Therefore, publicly available datasets were evaluated but found inadequate, necessitating use-case-specific data acquisition through near-industry-scale experiments. This data was used to train and develop key system components, such as object recognition, classification, and action recognition models. Results indicate that transfer learning with a balanced dataset is effective for waste-sorting applications. The classification model achieved 81% accuracy on an experimental acquired balanced dataset, outperforming the accuracy of the pre-trained model on its original dataset.

Influence-based data selection methods, such as TracIn, aim to estimate the impact of individual training samples on model predictions and are increasingly used for dataset curation and reduction. This study investigates whether selecting the most positively influential training examples can be used to create compressed yet effective training datasets for transfer learning in plastic waste classification. Using a ResNet-18 model trained on a custom dataset of plastic waste images, TracIn was applied to compute influence scores across multiple training checkpoints. The top 50 influential samples per class were extracted and used to train a new model. Contrary to expectations, models trained on these highly influential subsets significantly underperformed compared to models trained on either the full dataset or an equally sized random sample. Further analysis revealed that many top-ranked influential images originated from different classes, indicating model biases and potential label confusion. These findings highlight the limitations of using influence scores for dataset compression. However, TracIn proved valuable for identifying problematic or ambiguous samples, class imbalance issues, and issues with fuzzy class boundaries. Based on the results, the utilized TracIn approach is recommended as a diagnostic instrument rather than for dataset curation.

Innovations in manual waste sorting have stagnated for decades, despite the increasing global demand for efficient recycling solutions. The recAIcle system introduces an innovative AI-powered assistance system designed to modernise manual waste sorting processes. By integrating machine learning, continual learning, and projection-based augmentation, the system supports sorting workers by highlighting relevant waste objects on the conveyor belt in real time. The system learns from the decision-making patterns of experienced sorting workers, enabling it to adapt to operational realities and improve classification accuracy over time. Various hardware and software configurations were tested with and without active tracking and continual learning capabilities to ensure scalability and adaptability. The system was validated in initial trials, demonstrating its ability to detect and classify waste objects and providing augmented support for sorting workers with high precision under realistic recycling conditions. A survey complemented the trials and assessed industry interest in AI-based assistance systems. Survey results indicated that 82% of participating companies expressed interest in supporting their staff in manual sorting by using AI-based technologies. The recAIcle system represents a significant step toward digitising manual waste sorting, offering a scalable and sustainable solution for the recycling industry.