Smart Traffic Light Using YOLO Based Camera with Deep Reinforcement Learning Algorithm

Mochammad Sahal, Zulkifli Hidayat, Yusuf Bilfaqih, Mohamad Abdul Hady, Yosua Marthin Hawila Tampubolon

Abstract


Congestion is a common problem that often occurs in big cities. Congestion causes a lot of losses, such as in terms of time, economy, to the psychology of road users. One of the causes of congestion is traffic lights that are not adaptive to the dynamics of traffic flow. This final project tries to solve this problem using a Reinforcement Learning approach combined with a SUMO (Simulation of Urban Mobility) traffic simulator. The data used is the real video data of the KD Cowek intersection, Surabaya. The video data is processed using the YOLO algorithm which will detect and count vehicles. The output of the video processing will be used in Reinforcement Learning. The result of Reinforcement Learning is that the total length of the traffic queue at 06.00 – 09.00 has an average of 106 vehicles.

Full Text:

PDF

References


B. Pishue, “2021 INRIX Global Traffic Scorecard,” p. 21, 2021.

B. Pishue, “2020 INRIX Global Traffic Scorecard,” p. 23, 2020.

G. Nurinda Abdi, S. Priyanto, and S. Malkamah, “HUBUNGAN VOLUME, KECEPATAN DAN KEPADATAN LALU LINTAS PADA RUAS JALAN PADJAJARAN (RING ROAD UTARA), SLEMAN,” Teknisia, vol. XXIV, no. 1, pp. 55–64, May 2019, doi: 10.20885/teknisia.vol24.iss1.art6.

E. N. Julianto, “HUBUNGAN ANTARA KECEPATAN, VOLUME DAN KEPADATAN LALU LINTAS RUAS JALAN SILIWANGI SEMARANG,” p. 10, 2010.

J. D. Ansusanto and S. Tanggu, “ANALISIS KINERJA DAN MANAJEMEN PADA SIMPANG DENGAN DERAJAT KEJENUHAN TINGGI,” vol. 12, no. 2, p. 8, 2016.

A. N. Aulia Yusuf, A. Setyo Arifin, and F. Yuli Zulkifli, “Recent development of smart traffic lights,” IAES Int. J. Artif. Intell. IJ-AI, vol. 10, no. 1, p. 224, Mar. 2021, doi: 10.11591/ijai.v10.i1.pp224-233.

T.-N. Doan and M.-T. Truong, “Real-time vehicle detection and counting based on YOLO and DeepSORT,” in 2020 12th International Conference on Knowledge and Systems Engineering (KSE), Can Tho, Vietnam, Nov. 2020, pp. 67–72. doi: 10.1109/KSE50997.2020.9287483.

A. Gupta, A. Verma, A. Yadav, and A. M, “YOLO OBJECT DETECTION USING OPENCV,” Int. J. Eng. Appl. Sci. Technol., vol. 5, no. 10, Feb. 2021, doi: 10.33564/IJEAST.2021.v05i10.036.

J. D. Martín-Guerrero and L. Lamata, “Reinforcement Learning and Physics,” Appl. Sci., vol. 11, no. 18, p. 8589, Sep. 2021, doi: 10.3390/app11188589.

S. S. Mousavi, M. Schukat, and E. Howley, “Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning.” arXiv, May 27, 2017. Accessed: Jun. 12, 2022. [Online]. Available: http://arxiv.org/abs/1704.08883

X. Liang, X. Du, G. Wang, and Z. Han, “Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks,” IEEE Trans. Veh. Technol., vol. 68, no. 2, pp. 1243–1253, Feb. 2019, doi: 10.1109/TVT.2018.2890726.

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection.” arXiv, Apr. 22, 2020. Accessed: Jun. 13, 2022. [Online]. Available: http://arxiv.org/abs/2004.10934

M. Semrau, J. Erdmann, B. Friedrich, and R. Waldmann, “1 Simulation framework for testing ADAS in Chinese traffic situations,” p. 11, 2016.

A. Vidali, L. Crociani, G. Vizzari, and S. Bandini, “A Deep Reinforcement Learning Approach to Adaptive Traffic Lights Management,” p. 9, 2019.

K. G. Kim, “Book Review: Deep Learning,” Healthc. Inform. Res., vol. 22, no. 4, p. 351, 2016, doi: 10.4258/hir.2016.22.4.351.




DOI: https://doi.org/10.12962/jaree.v7i1.335

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.