State Prediction of High-speed Ballistic Vehicles with Gaussian Process

다국어 초록 (Multilingual Abstract)

This paper proposes a new method of predicting the future state of a ballistic target trajectory. There have been a number of estimation methods that utilize the variations of Kalman filters, and the prediction of the future states followed the simple propagations of the target dynamic equations. However, these simple propagations suffered from no observation of the future state, so this propagation could not estimate a key parameter of the dynamics equation, such as the ballistic coefficient. We resolved this limitation by applying a data-driven approach to predict the ballistic coefficient. From this learning of the ballistic coefficient, we calculated the future state with the future ballistic parameter that differs over time. Our proposed model shows the better performance than the traditional simple propagation method in this state prediction task. The value of this research could be recognized as an application of machine learning techniques to the aerodynamics domains. Our framework suggests how to maximize the synergy by linking the traditional filtering aproaches and diverse machine learning techniques, i.e., Gaussian process regression, support vector regression and regularized linear regression.

참고문헌 (Reference)

1 Y. Bar-Shalom, "Tracking and Data Fusion" YBS publishing 2011

2 J. K. Jung, "The novel impact point prediction of a ballistic target with interacting multiple models" 450-453, 2013

3 H. A. Blom, "The interacting multiple model algorithm for systems with Markovian switching coefficients" 33 (33): 780-783, 1988

4 D. Basak, "Support vector regression" 11 (11): 203-224, 2007

5 V. C. Ravindra, "Projectile identification and impact point prediction" 46 (46): 2004-2021, 2010

6 B. Ristic, "Performance bounds and comparison of nonlinear filters for tracking a ballistic object on re-entry" 150 (150): 65-70, 2003

7 E. Waltz, "Multisensor Data Fusion" Artech house 1990

8 N. Xiong, "Multi-sensor management for information fusion: issues and approaches" 3 (3): 163-186, 2002

9 A. Schwaighofer, "Learning Gaussian process kernels via hierarchical bayes" 1209-1216, 2005

10 T. L. Song, "Iterative joint integrated probabilistic data association" 1714-1720, 2013

11 E. Mazor, "Interacting multiple model methods in target tracking: a survey" 34 (34): 103-123, 1998

12 W. J. Farrell, "Interacting multiple model filter for tactical ballistic missile tracking" 44 (44): 418-426, 2008

13 J. Romito, "Hit to kill: the new battle over shielding america from missile attack" 52 (52): 57-58, 2005

14 J. O. Ogutu, "Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions" 6 (6): 2012

15 Y. Altun, "Gaussian process classification for segmenting and annotating sequences" 2004

16 C. E. Rasmussen, "Gaussian Processes for Machine Learning" MIT press 2006

17 S. M. Aly, "Extended kalman filtering and interacting multiple model for tracking maneuvering targets in sensor netwotrks" 149-156, 2009

18 K. Song, "Datadriven ballistic coefficient learning for future state prediction of high-speed vehicles" 17-24, 2016

19 문경록, "Comparison of Ballistic-Coefficient-Based Estimation Algorithms for Precise Tracking of a Re-Entry Vehicle and its Impact Point Prediction" 한국우주과학회 29 (29): 363-374, 2012

20 A. Farina, "Classification and launch-impact point prediction of ballistic target via multiple model maximum likelihood estimator (MM-MLE)" 802-806, 2006

21 A. B. Carter, "Ballistic Missile Defense" Brookings Institution Press 2010

22 L. Qiang, "Artificial neural networks for estimation and fusion in long-haul sensor networks" 460-467, 2015

23 X. R. Li, "A survey of maneuvering target trackingPart II: ballistic target models" 559-581, 2001

24 T. Yuan, "A multiple IMM estimation approach with unbiased mixing for thrusting projectiles" 48 (48): 3250-3267, 2012

25 J. K. Zico, "A large-scale study on predicting and contextualizing building energy usage" 1349-1356, 2011