Self-Driving Vehicle Localization using Probabilistic Maps and Unscented-Kalman Filters
International Journal of Intelligent Transportation Systems Research - Tập 20 - Trang 623-638 - 2022
Tóm tắt
In this paper, a Real-Time Monte Carlo Localization (RT_MCL) method for autonomous cars is proposed. Unlike the other localization approaches, the balanced treatment of both pose estimation accuracy and its real-time performance is the main contribution. The RT_MCL method is based on the fusion of lidar and radar measurement data for object detection, a pole-like landmarks probabilistic map, and a tailored particle filter for pose estimation. The lidar and radar are fused using the Unscented Kalman Filter (UKF) to provide pole-like static-objects pose estimations that are well suited to serve as landmarks for vehicle localization in urban environments. These pose estimations are then clustered using the Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) algorithm to represent each pole landmarks in the form of a source-point model to reduce computational cost and memory requirements. A reference map that includes pole landmarks is generated off-line and extracted from a 3-D lidar to be used by a carefully designed Particle Filter (PF) for accurate ego-car localization. The particle filter is initialized by the fused GPS + IMU measurements and used an ego-car motion model to predict the states of the particles. The data association between the estimated landmarks by the UKF and that in the reference map is performed using Iterative Closest Point (ICP) algorithm. The RT_MCL is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Extensive simulation studies have been carried out to evaluate the performance of the RT_MCL in both longitudinal and lateral localization. The RT_MCL was able to estimate the ego-car pose with an 11-cm mean error in real-time.
Tài liệu tham khảo
Farag, W.: Cloning safe driving behavior for self-driving cars using convolutional neural networks. Recent Patents Comput. Sci., Bentham Science Publishers, The Netherlands 12(2), 120–127(8) (2019)
Farag, W.: Traffic signs classification by deep learning for advanced driving assistance systems. Intell. Decis. Technol., IOS Press 13(3), 215–231 (2019)
Farag, W., Saleh, Z.: Road lane-lines detection in real-time for advanced driving assistance systems. Intern. Conf. on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT'18). Bahrain, 18-20 Nov (2018)
Farag, W.: A lightweight vehicle detection and tracking technique for advanced driving assistance systems. J. Intell. Fuzzy Syst., IOS Press 39(3), 2693–2710, (2020)
Farag, W., Saleh, Z.: An advanced vehicle detection and tracking scheme for self-driving cars. 2nd Smart Cities Symposium (SCS’19). IET Digital Library, Bahrain, 24-26 March (2019)
Farag, W., Saleh, Z.: An advanced road-lanes finding scheme for self-driving cars. 2nd Smart Cities Symposium (SCS'19). IET Digital Library, Bahrain, 24-26 March (2019)
Farag, W.: Safe-driving cloning by deep learning for autonomous cars. Int. J. Adv. Mechatron. Syst., Inderscience Publishers 7(6), 390–397 (2019)
Woo, A., Fidan, B., Melek, W.W.: Localization for autonomous driving. In: Handbook of position location: theory, practice, and advances, 2nd Ed., Chapter 29. Wiley (2019). https://doi.org/10.1002/9781119434610.ch29
Osterwood, C., Noble, F.: Localization for the next generation of autonomous vehicles. Swift Navigation (www.swiftnav.com), white paper. (2017) https://www.swiftnav.com/sites/default/files/whitepapers/localization_white_paper_052617.pdf
Modsching, M., Kramer, R., ten Hagen, K.: Field trial on GPS accuracy in a medium-size city: the influence of built-up. In: 3rd Workshop on positioning, navigation and communication, vol. 2006, pp. 209–218 (2006)
Carlevaris-Bianco, N., Ushani, A.K., Eustice, R.M.: University of Michigan north campus long-term vision and lidar dataset. Int. J. Robot. Res. 35(9), 1023–1035 (2015)
Levinson,J., Thrun, S.: Robust vehicle localization in urban environments using probabilistic maps. In: 2010 IEEE International Conference on Robotics and Automation, pp. 4372–4378, May (2010)
Schaefer,A., Büscher, D., Vertens, J., Luft, L., Burgard, W.: Long-term urban vehicle localization using pole landmarks extracted from 3-D lidar scans. European Conference on Mobile Robots (ECMR), Czech Republic, 4–6 Sept (2019)
Kummerle,J., Sons, M., Poggenhans F., Kuehner, T., Lauer, M., Stiller, C.: Accurate and efficient self-localization on roads using basic geometric primitives. In: 2019 IEEE International Conference on Robotics and Automation, May (2019)
Miura, S., Hsu, L.T., Chen, F., Kamijo, S.: GPS error correction with pseudorange evaluation using three-dimensional maps. IEEE Trans. Intell. Transp. Syst. 16(6), 3104–3115 (2015)
Lee, B.-H., Song, J.-H., Im, J.-H., Im, S.-H., Heo, M.-B., Jee, G.-I.: GPS/DR error estimation for autonomous vehicle localization. Sensors, 15, MDPI 20779–20798 (2015). https://doi.org/10.3390/s150820779
Jo, K., Jo, Y., Suhr, J.K., Jung, H.G., Sunwoo, M.: Precise localization of an autonomous car based on probabilistic noise models of road surface marker features using multiple cameras. IEEE Trans. Intell. Transp. Syst. 16(6), 3377–3392 (2015)
Alrousan, Q., Alzu'bi, H., Pfeil, A., Tasky, T.: Autonomous vehicle multi-sensors localization in unstructured environment. SAE Technical Paper 2020-01-1029 (2020). https://doi.org/10.4271/2020-01-1029
Sefati, M., Daum, M., Sondermann, B., Kreisk, K.D., Kampker, A.: Improving vehicle localization using semantic and pole-like landmarks. In: 2017 IEEE Intelligent Vehicles Symposium, pp. 13–19, June (2017)
Farag, W.: A comprehensive real-time road-lanes tracking technique for autonomous driving. Int. J. Comput. Digit. Syst. 9(3), 349–362 (2020)
Weng, L., Yang, M., Guo, L., Wang, B., Wang, C.: Pole-based realtime localization for autonomous driving in congested urban scenarios. In: 2018 IEEE International Conference on Real-time Computing and Robotics, pp. 96–101, August (2018)
Fischler, M., Bolles, R.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM 24(6), 381–395 (1981)
Suhr, J.K., Jang, J., Min, D., Jung, H.G.: Sensor fusion-based low-cost vehicle localization system for complex urban environments. IEEE Trans. Intell. Transp. Syst. 18(5) (2017)
Kellner, D., Klappstein, J., Dietmayer, K.C.J.: Grid-based DBSCAN for clustering extended objects in radar data. In: 2012 IEEE Intelligent Vehicles Symposium, pp. 365–370, Alcala de Henares, Spain (2012)
Lu, F., Milios, E.: Robot pose estimation in unknown environments by matching 2d range scans. J. Intell. Rob. Syst. 18(3), 249–275 (1997)
Thrun S.: Particle filters in robotics. In: Proceedings of 18th Annual Conf. On Uncertainty in AI (UAI), Edmonton (2002)
Zarchan, P., Musoff, H.: Fundamentals of Kalman filtering: a practical approach. American Institute of Aeronautics and Astronautics, Incorporated, 4th Ed., ISBN 978–1–62410–276–9 (2013)
Wan, E.A., Van Der Merwe, R.: The unscented Kalman filter for nonlinear estimation. In: IEEE Adaptive Sys. For Signal Processing, Comm., and Control Symposium, pp. 153–156. Alberta (2000)
Einicke, G.A., White, L.B.: Robust extended Kalman filtering. IEEE Trans. Signal Process. 47(9), 2596–2599 (1999)
Schubert, R., Richter, E., Wanielik, G.: Comparison and evaluation of advanced motion models for vehicle tracking. In: 11th Inter. Conf. On Information Fusion, Cologne, Germany (2008)
Farag, W.: Road-objects tracking for autonomous driving using lidar and radar fusion. J. Electr. Eng. 71(3), 138–149 (2020)
Farag, W.: Real-time Lidar and radar fusion for road-objects detection and tracking. Intelligent Decision Technologies (IDT). 15(2), 291–304, IOS Press, The Netherlands (2021)
Sander,J., Xu, X., Ester, M., Kriegel, H.-P.: A density-based algorithm for discovering clusters in large spatial databases with noise: Proc. of the 2nd Inter. Conf. on Knowledge Discovery and Data Mining, pp. 226–231. August (1996)
GCC C++, https://gcc.gnu.org/, accessed on 11th March, (2020)
Ubuntu Linux, https://www.ubuntu.com/, accessed on 11th March, (2020)
Eigen, http://eigen.tuxfamily.org/index.php?title=Main_Page, accessed on 11th March, (2020)
Piché, R.: Online tests of Kalman filter consistency. Int. J. Adapt. Control Signal Process. 30(1), 115–124 (2016)
Zhao,S., Huang, B.: On initialization of the Kalman filter. 6th Inter. Symposium on Adv. Control of Ind. Processes (AdCONIP), Taipei, Taiwan, May 28–31 (2017)
Farag, W.: Synthesis of intelligent hybrid systems for modeling and control. PhD Thesis, University of Waterloo, Ontario (1998)
Levinson, J., Montemerlo, M., Thrun, S.: Map-based precision vehicle localization in urban environments. Conference: Robotics: Science and Systems III, Georgia Institute of Technology, Atlanta, Georgia, USA, June 27–30 (2007)
Farag, W.: Complex trajectory tracking using PID control for autonomous driving. Int. J. Intell. Transp. Syst. Res. 19(4), 112–127 (2019)
Farag, W.: Complex-track following in real-time using model-based predictive control. Int. J. Intell. Transp. Syst. Res. 18(5), 356–366 (2020)
CARLA driving simulator, https://carla.org/, retrieved on 16 Aug (2020)
Farag, W.A., Quintana, V.H., Lambert-Torres, G.: Neuro-fuzzy modeling of complex systems using genetic algorithms. IEEE International Conference on Neural Networks (IEEE ICNN'97) 1, pp. 444–449 (1997)
Nagiub, M., Farag, W.: Automatic selection of compiler options using genetic techniques for embedded software design. IEEE 14th Inter. Symposium on Comp. Intelligence and Informatics (CINTI), Budapest, pp. 69–74 (2013). https://doi.org/10.1109/CINTI.2013.6705166
Yurtsever, E., Lambert, J., Carballo, A., Takeda, K.: A survey of autonomous driving: common practices and emerging technologies. IEEE Access. 8, 58443–58469 (2020). https://doi.org/10.1109/ACCESS.2020.2983149
Farag, W., Saleh Z.: Behavior cloning for autonomous driving using convolutional neural networks. Intern. Conf. on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT'18), Bahrain, 18–20 Nov (2018)