End-To-End Imitation Learning of Lane Following Policies Using Sum-Product Networks

  • Renato Geh Universidade de São Paulo
  • Denis Mauá Universidade de São Paulo

Resumo


Recent research has shown the potential of learning lane following policies from annotated video sequences through the use of advanced machine learning techniques. They however require high computational power, prohibiting their use in low-budget projects such as educational robotic kits and embedded devices. Sum-product networks (SPNs) are a class of deep probabilistic models with clear probabilistic semantics and competitive performance. Importantly, SPNs learned from data are usually several times smaller than deep neural networks trained for the same task. In this work, we develop an end-to-end imitation learning solution to lane following using SPNs to classify images into a finite set of actions. Images are obtained from a monocular camera, which is part of the low-cost custom made mobile robot. Our results show that our solution generalizes training conditions with relatively few data. We investigate the trade-off between computational and predictive performance, and conclude that sacrificing accuracy for the benefit of faster inference results in improved performance in the real world, especially in resource constrained environments.

Palavras-chave: Applications of Artificial Intelligence, Machine Learning, Deep Learning, Intelligent Robotics

Referências

Bojarski, M., Testa, D. D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M. P., Muller, U., Zhang, J., Zhang, X., Zhao, J. J., and Zieba, K. (2016). End to end learning for self-driving cars. CoRR, abs/1604.07316.

Chen, Z. and Huang, X. (2017). End-to-end learning for lane keeping of self-driving cars. In 2017 IEEE Intelligent Vehicles Symposium (IV), pages 1856–1860.

Conaty, D., de Campos, C. P., and Mauá, D. D. (2017). Approximation complexity of maximum A posteriori inference in sum-product networks. In Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence.

Dennis, A. and Ventura, D. (2012). Learning the architecture of sum-product networks using clustering on variables. In Advances in Neural Information Processing Systems 25, pages 2033–2041. NIPS.

Ester, M., Kriegel, H.-P., Sander, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD’96, pages 226–231. AAAI Press.

Gens, R. and Domingos, P. (2012). Discriminative learning of sum-product networks. In Advances in Neural Information Processing Systems 25, pages 3239–3247. NIPS.

Gens, R. and Pedro, D. (2013). Learning the structure of sum-product networks. In Proceedings of the 30th International Conference on Machine Learning, volume 28 of Proceedings of Machine Learning Research, pages 873–880, Atlanta, Georgia, USA. PMLR.

Hussein, A., Gaber, M. M., Elyan, E., and Jayne, C. (2017). Imitation learning: A survey of learning methods. ACM Computing Surveys, 50(2):21:1–21:35.

Levinson, J., Askeland, J., Becker, J., Dolson, J., Held, D., Kammel, S., Kolter, J. Z., Langer, D., Pink, O., Pratt, V., Sokolsky, M., Stanek, G., Stavens, D., Teichman, A., Werling, M., , and Thrun, S. (2011). Towards fully autonomous driving: Systems and algorithms. In Proceedings of the IEEE Intelligent Vehicles Symposium, pages 163–168.

Mei, J., Jiang, Y., and Tu, K. (2018). Maximum a posteriori inference in sum-product networks. In AAAI Conference on Artificial Intelligence.

Moraes, P. and Salvatore, F. (2018). Self-driving pi car. https://github.com/ felipessalvatore/self_driving_pi_car.

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66.

Paden, B., Cap, M., Yong, S. Z., Yershov, D., and Frazzoli, E. (2016). A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Transactions on Intelligent Vehicles, 1(1):33–55.

Pan, Y., Cheng, C.-A., Saigol, K., Lee, K., Yan, X., Theodorou, E. A., and Boots, B. (2018). Agile autonomous driving using end-to-end deep imitation learning. In Proceedings of Robotics: Science and Systems XIV.

Peharz, R. (2015). Foundations of Sum-Product Networks for Probabilistic Modeling. PhD thesis, Graz University of Technology.

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., and Ghahramani, Z. (2018). Probabilistic deep learning using random sum-product networks. CoRR, abs/1806.01910.

Pfeiffer, M., Schaeuble, M., Nieto, J., Siegwart, R., and Cadena, C. (2017). From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 1527–1533.

Pomerleau, D. A. (1989). Alvinn: An autonomous land vehicle in a neural network. In Advances in Neural Information Processing Systems, pages 305–313.

Poon, H. and Domingos, P. (2011). Sum-product networks: A new deep architecture. In Proceedings of the Twenty-Seventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-11), pages 337–346, Corvallis, Oregon. AUAI Press.

Rashwan, A., Poupart, P., and Zhitang, C. (2018). Discriminative training of sum-product networks by extended baum-welch. In Proceedings of the Ninth International Conference on Probabilistic Graphical Models, volume 72 of Proceedings of Machine Learning Research, pages 356–367, Prague, Czech Republic. PMLR.

Sguerra, B. M. and Cozman, F. G. (2016). Image classification using sum-product networks for autonomous flight of micro aerial vehicles. In 2016 5th Brazilian Conference on Intelligent Systems (BRACIS), pages 139–144.

Vergari, A., Mauro, N. D., and Esposito, F. (2015). Simplifying, regularizing and strengthening sum-product network structure learning. In ECML/PKDD.

Zhao, H., Adel, T., Gordon, G., and Amos, B. (2016a). Collapsed variational inference for sum-product networks. In Proceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 1310–1318. PMLR.

Zhao, H., Poupart, P., and Gordon, G. J. (2016b). A unified approach for learning the parameters of sum-product networks. In Advances in Neural Information Processing Systems 29, pages 433–441. NIPS.
Publicado
15/10/2019
GEH, Renato; MAUÁ, Denis. End-To-End Imitation Learning of Lane Following Policies Using Sum-Product Networks. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 16. , 2019, Salvador. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 297-308. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2019.9292.