AI-Driven Robotic Waste Sorting for Techno-Economic Assessment in Urban Indonesia

Urban centers in Indonesia are facing increasing pressure in managing municipal solid waste as a result of rapid population growth, rising labor costs, and stricter demands for high-purity recyclable materials. Manual sorting at Material Recovery Facilities has become progressively less efficient and economically burdensome under these conditions. This study presents an artificial intelligence-driven robotic waste sorting system designed and evaluated under real operational conditions in Jakarta and South Tangerang. The system integrates YOLO based object detection, vision-guided robotic manipulation, real-time processing hardware, a multi-axis gantry system with stepper motors, and a custom conveyor mechanism to deliver waste items to the sorting cell. Unlike previous studies that mainly focus on algorithmic accuracy or laboratory-scale validation, this work combines real-world technical performance assessment with a localized techno-economic analysis. Experimental results show an average sorting accuracy of 90%, a material purity of 95.1%, and a throughput of 50 items per minute, outperforming typical manual sorting performance. An economic evaluation based on local wage levels, electricity tariffs, and recyclable market prices indicates a payback period of 4.3 to 4.9 years. The main contributions of this study lie in integrating AI vision and robotic sorting into unstructured urban waste environments, in empirical validation under Indonesian operating conditions, and in demonstrating economic feasibility for emerging economies. Although the case study focuses on Jakarta and South Tangerang, the findings are relevant for metropolitan areas across the Global South seeking more efficient and sustainable waste management solutions.

@article{Nurhaida2026,
  title     = {AI-Driven Robotic Waste Sorting for Techno-Economic Assessment in Urban Indonesia},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {2},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Ida Nurhaida and Mohammad Nasucha and Hari Nugraha},
  doi       = {10.14569/IJACSA.2026.0170226},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170226}
}