Uma Arquitetura Baseada em Redes Neurais Recorrentes para Predição de Trajetórias Veiculares em Ambientes Urbanos

• Breno Krohling UFES
• Giovanni Comarela UFES
• Vinícius F. S. Mota UFES

DOI: https://doi.org/10.5753/sbrc.2024.1399

Resumo

A predição de trajetórias veiculares permite otimizar o gerenciamento de tráfego e facilitar a comunicação entre veículos. Neste sentido, este trabalho propõe uma arquitetura baseada em Long Short-Term Memory empilhadas (stacked LSTM), na qual a saída de uma LSTM atua como entrada na camada subsequente. As múltiplas camadas LSTM permitem que a arquitetura proposta possa predizer a posição de veículos em um futuro próximo e distante. Foram propostas duas métricas de desempenho: o erro absoluto da distância entre a posição real e predita e a acurácia do modelo para predizer regiões de interesse. Para avaliar o modelo, foram utilizados datasets de trajetórias de táxis das cidades do Porto, Portugal, e São Francisco, EUA. Os resultados demonstram bom desempenho da arquitetura para ambos os cenários de predição, alcançando uma acurácia de 83% para predição de áreas de interesse no futuro próximo.

Referências

ECML/PKDD (2015). Porto taxi dataset. [link]. Acesso: 2024-01-22.

Feng, J., Rong, C., Sun, F., Guo, D., and Li, Y. (2020). Pmf: A privacy-preserving human mobility prediction framework via federated learning. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 4(1):1–21.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.

Ip, A., Irio, L., and Oliveira, R. (2021). Vehicle trajectory prediction based on lstm recurrent neural networks. In IEEE Vehicular Technology Conference, pages 1–5. IEEE.

Karatzoglou, A., Köhler, D., and Beigl, M. (2018). Semantic-enhanced multi-dimensional markov chains on semantic trajectories for predicting future locations. Sensors, 18(10):3582.

Khansari, N., Mostashari, A., and Mansouri, M. (2014). Impacting sustainable behavior and planning in smart city. International journal of sustainable land Use and Urban planning, 1(2).

Kim, B., Kang, C. M., Kim, J., Lee, S. H., Chung, C. C., and Choi, J. W. (2017). Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network. In Conference on intelligent transportation systems, pages 399–404. IEEE.

King, S. M., Nawab, F., and Obraczka, K. (2021). A survey of open source user activity traces with applications to user mobility characterization and modeling. arXiv:2110.06382.

Kong, X., Xia, F., Wang, J., Rahim, A., and Das, S. K. (2017). Time-location-relationship combined service recommendation based on taxi trajectory data. IEEE Transactions on Industrial Informatics, 13(3):1202–1212.

Koolwal, V. and Mohbey, K. K. (2020). A comprehensive survey on trajectory-based location prediction. Iran Journal of Computer Science, 3:65–91.

Lv, J., Li, Q., Sun, Q., and Wang, X. (2018). T-conv: A convolutional neural network for multi-scale taxi trajectory prediction. In 2018 IEEE international conference on big data and smart computing (bigcomp), pages 82–89. IEEE.

Maggi, E. and Vallino, E. (2016). Understanding urban mobility and the impact of public policies: The role of the agent-based models. Research in Transportation Economics, 55:50–59.

Mehmood, Y., Ahmad, F., Yaqoob, I., Adnane, A., Imran, M., and Guizani, S. (2017). Internet-of-things-based smart cities: Recent advances and challenges. IEEE Communications Magazine, 55(9):16–24.

Park, S. H., Kim, B., Kang, C. M., Chung, C. C., and Choi, J. W. (2018). Sequence-to-sequence prediction of vehicle trajectory via lstm encoder-decoder architecture. In 2018 IEEE intelligent vehicles symposium (IV), pages 1672–1678. IEEE.

Piorkowski, M., Sarafijanovic-Djukic, N., and Grossglauser, M. (2009). Crawdad data set epfl/mobility (v. 2009-02-24).

Qiao, J., Li, S., and Lin, S. (2017). Location prediction based on user mobile behavior similarity. In 2017 IEEE 23rd International Conference on Parallel and Distributed Systems (ICPADS), pages 783–786. IEEE.

Rathore, P., Kumar, D., Rajasegarar, S., Palaniswami, M., and Bezdek, J. C. (2019). A scalable framework for trajectory prediction. IEEE Transactions on Intelligent Transportation Systems, 20(10):3860–3874.

Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. nature, 323(6088):533–536.

Saleh, K., Hossny, M., and Nahavandi, S. (2018). Cyclist trajectory prediction using bidirectional recurrent neural networks. In Advances in Artificial Intelligence, Wellington, New Zealand, pages 284–295. Springer.

Sharma, S. and Kaushik, B. (2019). A survey on internet of vehicles: Applications, security issues & solutions. Vehicular Communications, 20:100182.

Thomé, M., Prestes, A., Gomes, R., and Mota, V. (2020). Um arcabouço para detecção e alerta de anomalias de mobilidade urbana em tempo real. In Anais do XXXVIII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 784–797, Porto Alegre, RS, Brasil. SBC.

Van Brummelen, G. (2012). Heavenly mathematics: The forgotten art of spherical trigonometry. Princeton University Press.

Zhang, J., Meng, W., Liu, Q., Jiang, H., Feng, Y., and Wang, G. (2016). Efficient vehicles path planning algorithm based on taxi gps big data. Optik, 127(5):2579–2585.

Zhang, P., Ouyang, W., Zhang, P., Xue, J., and Zheng, N. (2019). Sr-lstm: State refinement for lstm towards pedestrian trajectory prediction. In Conference on Computer Vision and Pattern Recognition, pages 12085–12094.