The CircuBot Project aims to revolutionize waste management by introducing an advanced modular robotic system equipped with cutting-edge technologies like artificial intelligence, collaborative robotics, and cloud computing. Addressing the challenges posed by inefficient recycling methods, the project strives to align with the European Union’s 2018/850 Waste Directive, which mandates reducing landfill waste to less than 10% by 2035. Serbia, currently recycling only 15% of its waste, falls significantly short of this target, with over 79% of municipal waste being landfilled without treatment. CircuBot seeks to bridge this gap through innovative solutions, particularly focusing on hazardous workplace conditions and the need for scalable, efficient, and safe waste sorting systems​.

At the heart of CircuBot lies a focus on versatile waste detection and sorting powered by deep learning, combined with a robotic system designed for human-robot collaboration. This approach allows for precise recognition, classification, and handling of waste materials such as PET, metal cans, and electronics. By utilizing advanced grippers and intelligent pick-and-toss manipulation strategies, CircuBot enhances operational efficiency while ensuring safe interaction between humans and robots. Additionally, a cloud-based management platform integrated into the system enables real-time data analytics and monitoring, fostering digital transformation in an otherwise labor-intensive industry​.

References

  1. World Economic Forum – Circular Economy and Value Chains.
  2. Directive (EU) 2018/850 of the European Parliament and of the Council of 30 May 2018 amending Directive 1999/31/EC on the landfill of waste.
  3. The European Environment Agency – Waste recycling in Europe.
  4. EU for environment- Promoting waste source separation in 4 regions.
  5. Национална стратегија управљања отпадом са националним планом управљања отпадом за период 2020-2025. године.
  6. European Agency for Safety & Health at Work.
  7. Ramadurai, S., & Jeong, H. (2022) Effect of Human Involvement on Work Performance and Fluency in Human-Robot Collaboration for Recycling. arXiv preprint arXiv:2201.07990.
  8. Della Santina, C.et al (2019) Learning from humans how to grasp: a data-driven architecture for autonomous grasping with anthropomorphic soft hands. IEEE Robotics and Automation Letters, 4, No. 2, pp. 1533-1540.
  9. Bombile, M., and Billard, A. (2022) Dual-Arm Control for Coordinated Fast Grabbing and Tossing of an Object: Proposing a New Approach. IEEE Robotics & Automation Magazine, Vol. 29, No. 3, pp. 127-138.
  10. Liu, Y., Nayak, A. and Billard, A. (2022) A Solution to Adaptive Mobile Manipulator Throwing. arXiv preprint arXiv:2207.10629.