Abstract
A highly accurate and reliable vehicle position estimation system is an important component of an autonomous driving system. In generally, a global positioning system (GPS) receiver is employed for the vehicle position estimation of autonomous vehicles. However, a stand-alone GPS does not always provide accurate and reliable information of the vehicle position due to frequent GPS blockages and multipath errors. In order to overcome these problems, a sensor fusion scheme that combines the data from the GPS receiver and several on-board sensors has been studied. In previous researches, a single model filter-based sensor fusion algorithm was used to integrate information from the GPS and on-board sensors. However, an estimate obtained from a single model is difficult to cover the various driving environments, including urban areas, off-road areas, and highways. Thus, a multiple models filter (MMF) has been introduced to address this limitation by adapting multiple models to a wide range of driving conditions. An adaptation of the multiple model is achieved through the use of the model probability. The MMF combines several vehicle models using the model probabilities, which indicate the suitability of the current driving condition. In this paper, we propose a vehicle position estimation algorithm for an autonomous vehicle that is based on a neural network (NN)-based MMF. The model probabilities are determined through the NN. The proposed position estimation system was evaluated through simulations and experiments. The experimental results show that the proposed position estimation algorithm is suitable for application in an autonomous driving system over a wide range of driving conditions.
Similar content being viewed by others
References
Caron, F., Duflos, E., Pomorski, D. and Vanheeghe, P. (2006). GPS/IMU data fusion using multisensor Kalman filtering: Introduction of contextual aspects. Information Fusion, 7, 221–230.
Chao, H., Zheng, Y. F. and Ahalt, S. C. (2002). Object tracking using the Gabor wavelet transform and the golden section algorithm. Multimedia, IEEE Trans. 4, 528–538.
Chong, E. K. P. and Żak, S. H. (2008). An Introduction to Optimization. Wiley-Interscience. New York.
Dongliang, H. and Henry, L. (2004). EM-IMM based landvehicle navigation with GPS/INS. Intelligent Transportation Systems, Proc. 7th Int. IEEE Conf. 2004. 624–629.
Drevelle, V. and Bonnifait, P. (2011). Global positioning in urban areas with 3-D maps. Intelligent Vehicles Symp. (IV), IEEE, 764–769.
Hagan, M. T., Demuth, H. B. and Beale, M. H. (1996). Neural Network Design. PWS Pub. Boston.
Honghui, Q. and Moore, J. B. (2002). Direct Kalman filtering approach for GPS/INS integration. Aerospace and Electronic Systems, IEEE Trans. 38, 687–693.
Jazar, R. N. (2008). Vehicle Dynamics: Theory and Applications. Springer. New York.
Jianguo, J., Wang, J. W., David, S. and Leo, W. (2006). A neural network and Kalman filter hybrid approach for GPS/INS integration. 12th IAIN Cong. and 2006 Int. Symp. GPS/GNSS. Jeju, Korea.
Jo, K., Chu, K. and Sunwoo, M. (2011). Interacting multiple model filter-based sensor fusion of GPS with in-vehicle sensors for real-time vehicle positioning. Intelligent Transportation Systems, IEEE Trans., 1–15.
Jo, K., Chu, K. and Sunwoo, M. (2012). Interacting multiple model filter-based sensor fusion of gps with in-vehicle sensors for real-time vehicle positioning. Intelligent Transportation Systems, IEEE Transa., 13, 329–343.
Jo, K., Chu, K., Lee, K. and Sunwoo, M. (2010). Integration of multiple vehicle models with an IMM filter for vehicle localization. IEEE Intelligent Vehicles Symp. Proc., 2010 La Jolla, CA. 746–751.
Julier, S. J. and Durrant-Whyte, H. F. (2003). On the role of process models in autonomous land vehicle navigation systems. Robotics and Automation, IEEE Trans., 19, 1–14.
Lee, K. B., Kim, Y. J., Ahn, O. S. and Kim, Y. B. (2002). Lateral control of autonomous vehicle using levenbergmarquardt neural network algorithm. Int. J. Automotive Technology 3,2, 71–77.
Park, Y., Oh, B., Lee, M. and Sunwoo, M. (2010). Development of turbine mass flow rate model for variable geometry turbocharger using artificial neural network. Trans. Korean Society of Mechanical Engineers — B, 34, 783–790.
Pitre, R. R., Jilkov, V. P. and Li, X. R. (2005). A comparative study of multiple-model algorithms for maneuvering target tracking. Proc. SPIE, 549–560.
Rajamani, R. (2006). Vehicle Dynamics and Control. Springer Science. New York.
Rezaei, S. and Sengupta, R. (2005). Kalman filter based integration of DGPS and vehicle sensors for localization. Mechatronics and Automation, 2005 IEEE Int. Conf., 1, 455–460.
Ristic, B., Arulampalam, S. and Gordon, N. (2004). Beyond the Kalman Filter: Particle Filters for Tracking Applications. Artech House. Boseon.
Rossetter, E. J., Switkes, J. P. and Gerdes, J. C. (2004). Experimental validation of the potential field lanekeeping system. Int. J. Automotive Technology 5,2, 95–108.
Simon, D. (2006). Optimal State Estimation: Kalman, H [Infinity] and Nonlinear Approaches. John Wiley and Sons. Hoboken.
Skog, I. and Handel, P. (2009). In-car positioning and navigation technologies — A survey. Intelligent Transportation Systems, IEEE Trans. 10, 4–21.
ST-Pierre, M. and Gingras, D. (2004). Comparison between the unscented Kalman filter and the extended Kalman filter for the position estimation module of an integrated navigation information system. Intelligent Vehicles Symp., IEEE, 831–835.
Toledo-Moreo, R. and Zamora-Izquierdo, M. A. (2009). IMM-based lane-change prediction in highways with low-cost GPS/INS. Intelligent Transportation Systems, IEEE Trans., 10, 180–185.
Toledo-Moreo, R., Zamora-Izquierdo, M. A., Ubeda-Miarro, B. and Gomez-skarmeta, A. F. (2007). Highintegrity IMM-EKF-based road vehicle navigation with low-cost GPS/SBAS/INS. Intelligent Transportation Systems, IEEE Trans., 8, 491–511.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gwak, M., Jo, K. & Sunwoo, M. Neural-network multiple models filter (NMM)-based position estimation system for autonomous vehicles. Int.J Automot. Technol. 14, 265–274 (2013). https://doi.org/10.1007/s12239-013-0030-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12239-013-0030-2