Measurement uncertainty plays an important role in every real-world perception task. This paper describes the influence of measurement uncertainty in state estimation, which is the main part of Dynamic Object Tracking. Its base is the probabilistic Bayesian Filtering approach. Practical examples and tools for choosing the correct filter implementation including measurement models and their conversion, for different kinds of sensors are presented.
Die korrekte Modellierung der Messunsicherheit ist eine große Herausforderung für die Wahrnehmung im Bereich Autonomes Fahren unter realen Bedingungen. In diesem Artikel beschreiben wir den Einfluss der Messunsicherheit sowie deren Behandlung in der Zustandsschätzung, welche die Grundlage für das Tracking dynamischer Objekte ist. Die Basis hierfür ist die probabilistische Bayessche Filterung. Weiterhin werden praktische Beispiele und Techniken zur korrekten Filterimplementierung einschließlich verschiedener Messmodelle sowie deren Konvertierung betrachtet.
About the authors
Benjamin Naujoks studied technomathematics (scientific computing & optimization) at the Technical University of Dresden. Since 2015 he has been researching autonomous driving at the University of the Bundeswehr Munich. His research interests include probabilistic filter algorithmic, object-detection, especially in LiDAR point-clouds, parallelization with CUDA and machine-learning algorithms.
Torsten Engler studied electrical engineering and information technologies at the Technical University Munich. He is researching in the context of autonomous driving at the University of the Bundeswehr Munich since 2014. His research focus lays on camera assisted driving in non urban environments including vision-based obstacle avoidance and 3D reconstruction of the environment.
Martin Michaelis studied mathematics at the University of Bonn. Afterwards, he worked two years as a research assistant at the Fraunhofer institute FKIE in Wachtberg. Since 2016, he is with the University of the Bundeswehr Munich. His main research interests are multi-object tracking, multi-sensor fusion and extended target tracking.
Thorsten Luettel studied electrical engineering (mechatronics) at the Leibniz Universität Hannover. Since 2006 he has been researching autonomous driving at the University of the Bundeswehr Munich. Recently, he has also led ‘Team MuCAR’ during successful international competitions. His research interests include sensor data fusion and system integration.
Hans-Joachim Wuensche got his PhD from University of the Bundeswehr Munich in 1987 with Ernst D. Dickmanns, where he co-developed the 4D-approach to computer vision. After many years in management, he returned to the same University to lead the Institute for Autonomous Systems Technology in 2004. His research interests include autonomous robots, especially on- and off-road vehicles exploring and navigating unknown terrain.
1. Y. Bar-Shalom, Tracking and Data Association. San Diego, CA, USA: Academic Press Professional, Inc., 1987.Search in Google Scholar
3. S. Reuter, B.-T. Vo, B.-N. Vo, and K. Dietmayer, “The Labeled Multi-Bernoulli Filter,” IEEE Transactions on Signal Processing, vol. 62, no. 12, 2014.10.1109/TSP.2014.2323064Search in Google Scholar
4. P. Burger and H.-J. Wuensche, “Fast Multi-pass 3D Point Segmentation Based on a Structured Mesh Graph for Ground Vehicles,” in Proceedings of IEEE Intelligent Vehicles Symposium (IV), Changshu, Suzhou, China, Jun. 2018.10.1109/IVS.2018.8500552Search in Google Scholar
5. B. Naujoks and H.-J. Wuensche, “An Orientation Corrected Bounding Box Fit Based on the Convex Hull under Real Time Constraints,” in Proceedings of IEEE Intelligent Vehicles Symposium (IV), Changshu, Suzhou, China, 2018.10.1109/IVS.2018.8500692Search in Google Scholar
7. F. Ebert, D. Fassbender, B. Naujoks, and H.-J. Wuensche, “Robust Long-Range Teach-and-Repeat in Non-Urban Environments,” in Proceedings of IEEE Intelligent Transportation Systems Conference (ITSC), Yokohama, Japan, 2017.10.1109/ITSC.2017.8317767Search in Google Scholar
11. A. Gning, B. Ristic, and L. Mihaylova, “Bernoulli Particle/Box-Particle Filters for Detection and Tracking in the Presence of Triple Measurement Uncertainty,” IEEE Transactions on Signal Processing, vol. 60, no. 5, 2012.10.1109/TSP.2012.2184538Search in Google Scholar
12. Y. Zhang, K. Fu, X. Sun, G. Xu, and H. Wang, “Model Accuracy Comparison for High Resolution Insar Coherence Statistics Over Urban Areas,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 41, 2016.10.5194/isprsarchives-XLI-B7-753-2016Search in Google Scholar
14. A. Zea, F. Faion, M. Baum, and U. D. Hanebeck, “Level-Set Random Hypersurface Models for Tracking Non-Convex Extended Objects,” in Proceedings of International Conference on Information Fusion (FUSION), Istanbul, Turkey, 2013.Search in Google Scholar
16. B. Anderson and J. Moore, Optimal Filtering. Englewood Cliffs, NJ: Prentice-Hall, 1979.Search in Google Scholar
20. E. A. Wan and R. van der Merwe, “The Unscented Kalman Filter for Nonlinear Estimation,” in Proceedings of the IEEE Adaptive Systems for Signal Processing, Communications, and Control Symposium, Lake Louise, AB, Canada, 2000.Search in Google Scholar
23. D. L. Alspach and H. W. Sorenson, “Nonlinear Bayesian Estimation using Gaussian Sum Approximations,” IEEE Transactions on Automatic Control, vol. 17, no. 4, 1972.10.1109/TAC.1972.1100034Search in Google Scholar
26. R. Niu, P. K. Varshney, M. G. Alford, A. Bubalo, E. K. Jones, and M. Scalzo, “Curvature Nonlinearity Measure and Filter Divergence Detector for Nonlinear Tracking Problems,” in Proceedings of International Conference on Information Fusion (FUSION), Cologne, Germany, 2008.Search in Google Scholar
29. X. R. Li and V. P. Jilkov, “Survey of Maneuvering Target Tracking: III. Measurement models,” Proceedings of SPIE Conference on Signal and Data Processing of Small Targets, vol. 4473, San Diego, CA, USA, 2001.Search in Google Scholar
30. D. Lerro and Y. Bar-Shalom, “Tracking with Debiased Consistent Converted Measurements versus EKF,” IEEE Transactions on Aerospace and Electronic Systems, vol. 29, no. 3, Jul. 1993.10.1109/7.220948Search in Google Scholar
31. L. Mo, X. Song, Y. Zhou, and Z. Sun, “Alternative Unbiased Consistent Converted Measurements for Target Tracking,” in Proceedings of SPIE: Acquisition, Tracking and Pointing, vol. 3086, 1997.10.1117/12.277196Search in Google Scholar
32. S. J. Julier and J. K. Uhlmann, “Consistent Debiased Method for Converting Between Polar and Cartesian Coordinate Systems,” in Proceedings of SPIE: Acquisition, Tracking and Pointing, vol. 3086, pp. 110–121, 1997.10.1117/12.277178Search in Google Scholar
34. H. Hirschmueller, “Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 2005.Search in Google Scholar
35. L. M. Gabe Sibley and G. Sukhatme, “Bias Reduction and Filter Convergence for Long Range Stereo,” in International Symposium on Robotics Research (ISRR), San Francisco, CA, USA, 2005.Search in Google Scholar
36. P. Berthold, M. Michaelis, T. Luettel, D. Meissner, and H. J. Wuensche, “Radar Reflection Characteristics of Vehicles for Contour and Feature Estimation,” in Sensor Data Fusion: Trends, Solutions, Applications (SDF), Bonn, Germany, 2017.10.1109/SDF.2017.8126352Search in Google Scholar
37. Velodyne Lidar, Inc., “High Definition Lidar HDL-64E S2 Specifications.” [Online]. Available: http://velodynelidar.com/lidar/hdlproducts/hdl64e.aspx.Search in Google Scholar
38. M. Michaelis, P. Berthold, D. Meissner, and H. J. Wuensche, “Heterogeneous Multi-Sensor Fusion for Extended Objects in Automotive Scenarios using Gaussian Processes and a GMPHD-filter,” in 2017 Sensor Data Fusion: Trends, Solutions, Applications (SDF), Oct 2017, pp. 1–6.10.1109/SDF.2017.8126351Search in Google Scholar
39. A. F. Foka and P. E. Trahanias, “Probabilistic Autonomous Robot Navigation in Dynamic Environments with Human Motion Prediction,” International Journal of Social Robotics, vol. 2, 2010.10.1007/s12369-009-0037-zSearch in Google Scholar
40. M. Sefati, J. Chandiramani, K. Kreiskoether, A. Kampker, and S. Baldi, “Towards Tactical Behaviour Planning Under Uncertainties for Automated Vehicles in Urban Scenarios,” in IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Maui, Hawaii, USA, 2018.10.1109/ITSC.2017.8317819Search in Google Scholar
41. S. Ulbrich and M. Maurer, “Towards Tactical Lane Change Behavior Planning for Automated Vehicles,” in IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2015.10.1109/ITSC.2015.165Search in Google Scholar
42. D. K. Kye, S. W. Kim, and S. W. Seo, “Decision Making for Automated Driving at Unsignalized Intersection,” in ICCAS 2015 – 2015 15th International Conference on Control, Automation and Systems, Proceedings, Los Angeles, CA, USA, 2015.10.1109/ICCAS.2015.7364974Search in Google Scholar
43. S. Brechtel, T. Gindele, and R. Dillmann, “Probabilistic Decision-Making under Uncertainty for Autonomous Driving using Continuous POMDPs,” in 2014 IEEE 17th International Conference on Intelligent Transportation Systems (ITSC), Qingdoa, China, 2014.10.1109/ITSC.2014.6957722Search in Google Scholar
© 2018 Walter de Gruyter GmbH, Berlin/Boston