Policy compression for aircraft collision avoidance systems

AIAA/IEEE Digital Avionics Systems Conference - Proceedings

Volumn 2016-December, Issue , 2016, Pages

  Julian, Kyle D ^a   Lopez, Jessica ^b   Brush, Jeffrey S ^b   Owen, Michael P ^c   Kochenderfer, Mykel J ^a  

^a Stanford University   (United States)

^b JOHNS HOPKINS UNIVERSITY APPLIED PHYSICS LABORATORY   (United States)

^c MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AVIONICS; BEHAVIORAL RESEARCH; COLLISION AVOIDANCE; COMPLEX NETWORKS; DECISION MAKING; DIGITAL AVIONICS; DYNAMIC PROGRAMMING; FUNCTIONS; MARKOV PROCESSES; SAFETY DEVICES; TABLE LOOKUP;

AIRCRAFT COLLISION AVOIDANCE SYSTEMS; ASYMMETRIC LOSS FUNCTION; COLLISION AVOIDANCE SYSTEMS; DEEP NEURAL NETWORKS; GRADIENT DESCENT ALGORITHMS; HIGH DIMENSIONALITY; MARKOV DECISION PROCESSES; NONLINEAR FUNCTIONS;

AIRCRAFT ACCIDENTS;

EID: 85009468187     PISSN: 21557195     EISSN: 21557209     Source Type: Conference Proceeding    
DOI: 10.1109/DASC.2016.7778091     Document Type: Conference Paper

References (24)

1. J. K. Kuchar and L. C. Yang, "A review of conflict detection and resolution modeling methods," IEEE Transactions on Intelligent Transportation Systems, vol. 1, no. 4, pp. 179-189, 2000.
2. M. J. Kochenderfer, "Optimized airborne collision avoidance," in Decision Making under Uncertainty: Theory and Application, MIT Press, 2015.
3. M. J. Kochenderfer, J. E. Holland, and J. P. Chryssanthacopoulos, "Next generation airborne collision avoidance system," Lincoln Laboratory Journal, vol. 19, no. 1, pp. 17-33, 2012.
4. M. J. Kochenderfer and J. P. Chryssanthacopoulos, "Robust airborne collision avoidance through dynamic programming," Massachusetts Institute of Technology, Lincoln Laboratory, Project Report ATC-371, 2011. [Online]. Available: http://www.ll.mit.edu/mission/aviation/publications/publication-files/atc-reports/Kochenderfer2011ATC-371WW-21458.pdf.
5. M. Marston and G. Baca, "ACAS-Xu initial selfseparation flight tests," NASA, Tech. Rep. DFRC-EDAA- TN22968, 2015. [Online]. Available: http://hdl. handle.net/2060/20150008347.
6. Y. Engel, S. Mannor, and R. Meir, "Reinforcement learning with Gaussian processes," in International Conference on Machine Learning (ICML), 2005.
7. R. Munos and A. Moore, "Variable resolution discretization in optimal control," Machine Learning, vol. 49, no. 2, pp. 291-323, 2002.
8. M. J. Kochenderfer and N. Monath, "Compression of optimal value functions for Markov decision processes," in Data Compression Conference, 2013.
9. J. P. Chryssanthacopoulos and M. J. Kochenderfer, "Accounting for state uncertainty in collision avoidance," AIAA Journal on Guidance, Control, and Dynamics, vol. 34, no. 4, pp. 951-960, 2011.
10. S. Julier and J. Uhlmann, "Unscented filtering and nonlinear estimation," Proceedings of the IEEE, vol. 92, no. 3, pp. 401-422, 2004.
11. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems (NIPS), 2012.
12. G. E. Dahl, T. N. Sainath, and G. E. Hinton, "Improving deep neural networks for lvcsr using rectified linear units and dropout," in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
13. T. Tieleman and G. Hinton, "Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude," COURSERA: Neural Networks for Machine Learning, vol. 4, p. 2, 2012.
14. J. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," Journal of Machine Learning, vol. 12, pp. 2121-2159, 2011.
15. M. D. Zeiler. (2012). ADADELTA: an adaptive learning rate method. arXiv: 1212.5701.
16. D. Kingma and J. Ba, "Adam: A method for stochastic optimization," 2014. arXiv: 1412.6980.
17. G. P. Zhang, "Neural networks for classification: A survey," IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 30, no. 4, pp. 451-462, 2000.
18. S. F. Crone, "Training artificial neural networks for time series prediction using asymmetric cost functions," in International Conference on Neural Information Processing (ICONIP), vol. 5, 2002.
19. F. Chollet. (2016). Keras: Deep learning library for Theano and TensorFlow, [Online]. Available: keras.io.
20. Theano Development Team. (2016). Theano: A Python framework for fast computation of mathematical expressions. arXiv: 1605.02688.
21. Y. A. LeCun, L. Bottou, G. B. Orr, and K.-R. Müller, "Efficient backprop," in Neural Networks: Tricks of the Trade, G. Montavon, G. B. Orr, and K.-R. Müller, Eds., 2nd ed., Berlin: Springer, 2012, pp. 9-48.
22. M. J. Kochenderfer, M. W. M. Edwards, L. P. Espindle, J. K. Kuchar, and J. D. Griffith, "Airspace encounter models for estimating collision risk," AIAA Journal on Guidance, Control, and Dynamics, vol. 33, no. 2, pp. 487-499, 2010.
23. R. W. Gardner and J. S. Brush, "Enabling real-time execution: Runtime-efficiency improvements for the next generation airborne collision avoidance algorithms," in Digital Avionics Systems Conference (DASC), 2016.
24. H. Y. Ong and M. J. Kochenderfer, "Short-term conflict resolution for unmanned aircraft traffic management," in Digital Avionics Systems Conference (DASC), 2015.