UGV Digital Twin for Supporting Innovative Environmental Treatments of Large Areas by using AI 

  • Antonio Giovannetti 
  • Mehrnoosh Mashayekhizadeh,  
  • c  Daniele Cefaliello,  
  • d  Farshad Shamlu,  
  • Hinda Taib
  • University of Genoa, Via Opera Pia 15, Genoa, 16145, Italy 
  • b,c,d,e  Simulation Team, Via Cadorna 2, Savona, 17100, Italy 
Cite as
Giovannetti A., Mashayekhizadeh M., Cefaliello D., Shamlu F., Taib H. (2022).,UGV Digital Twin for garbage detection through AI. Proceedings of the 10th International Workshop on Simulation for Energy, Sustainable Development & Environment (SESDE 2022). , 012 . DOI: https://doi.org/10.46354/i3m.2022.sesde.012

Abstract

The efforts to maintain low level of pollution in the environment need to meet sustainable and innovative solutions in order to be effective in the modern and complex world. Indeed, currently we are facing critical issues in terms of sustainability and new technologies are crucial to identify new solutions: recycling the abandoned wastes is a critical issue that needs to be considered and implemented beside their collection and processing. Due to these reasons, the purpose of this research is to develop an  intelligent cleaning complex system based on UGV (Unmanned Ground Vehicle), which focus is to enhance the ability of strategic decisions making and achieve satisfactory trash detection in the wild for deployment. The system stands on AI (Artificial Intelligence) based on deep neural networks, which behaviour is simulated in a 3D Unity synthetic environment, through the usage of a digital twin, that simulates the desired solution of detecting and collecting garbage. The developed virtual environment chosen by the authors is a contaminated beach, in which an armed and autonomous robot manages to collect and recycle the wastes; the scenario is flexible to changes and further ones can be developed for training and testing of the intelligent system. 

References

  1. A.G. Bruzzone et al. (2019a). Application of blockchain  in interoperable simulation for strategic decision  making. Summer Simulation Conference (pp. 1-10). 
  2. A.G. Bruzzone et al. (2019b). A digital twin approach to  develop a new autonomous system able to operate  in high temperature environment within industrial  plants. Summer Simulation Conference (pp. 22-24)
  3. A.G.Bruzzone et al. (2020). Modeling Human  Physiology Coupled with Hyperbaric Plant  Simulation for Oil and Gas. International Journal of  Privacy and Health Information Management  (IJPHIM), 8(1), 1-12.
  4. L.-C Chen, Z., P., S. and A. (2018). Encoder-decoder  with atrous separable convolution for semantic  image segmentation. Proceedings of the European  Conference on Computer Vision (ECCV) 
  5. G.-R Jocher et al. (2020). yolov5. Code repository 
  6. Q. Lei et al. (2021). Garbage Classification System with  YOLOV5 Based on Image Recognition. Intelligent  Robot & Equipment Center Guangzhou Institute of  Advanced Technology, Chinese Academy of Sciences  
  7. Currie, C. S., Fowler, J. W., Kotiadis, K [Kathy], Monks, T., Onggo, B. S., Robertson, D. A., & Tako, A. A. (2020). How simulation modelling can help reduce the impact of COVID-19. Journal of Simulation, 14(2), 83–97.
  8. S. Majchrowska et al. (2022). Deep learning-based  waste detection in natural and urban environments.  Waste Management, Volume 128
  9. L. Parker. (2018). Here’s how much plastic trash is  littering the Earth. National Geographic. 
  10. U. S. Environmental Protecting Agency (EPA). (2020).  EPA’s Report on the Environment (ROE). Human  Exposure & Health: Disease and Conditions 
  11. W. Zeng, R.L. Church. (2007). Finding shortest paths on  real road networks: the case of A*. Department of  Geography, University of California
  12. Z. Wu et all. (2021). Using YOLOv5 for Garbage  Classification. 2021 4th International Conference on  Pattern Recognition and Artificial Intelligence (PRAI) 
  13. A.G. Bruzzone et al. (2014). Simulation exploration experience: providing effective surveillance and defense for a moon base against threats from outer space. 18th International Symposium on Distributed Simulation and Real Time Applications (pp. 121-126). IEEE/ACM.
  14. A.G. Bruzzone et al. (2016). Autonomous Systems for operations in critical environments. Simulation Series, 48(5) 17-24