Long term vehicle motion prediction and tracking in large environments

Vehicle motion tracking and prediction over large areas is of significant importance in many industrial applications. This paper presents algorithms for long term vehicle prediction and tracking based on a model of the vehicle that incorporates the properties of the working environment. It uses a limited number of data collection points distributed around the field to update estimates when vehicles are in range of the collection points. The algorithm evaluates the prediction and tracking of vehicle positions using speed and timing profiles built for the particular environment and considering vehicle stopping probability. Positive and negative information from observers is also introduced in the fusion stage. Experimental results from a large scale mining operation using peer to peer communication system are presented to validate the algorithm.

[1]  Yihua Yu,et al.  Particle filters for maneuvering target tracking problem , 2006, Signal Process..

[2]  Eduardo Mario Nebot,et al.  Robust Inference of Principal Road Paths for Intelligent Transportation Systems , 2011, IEEE Transactions on Intelligent Transportation Systems.

[3]  Sung-Soo Kim,et al.  Congestion Avoidance Algorithm Using Extended Kalman Filter , 2007, 2007 International Conference on Convergence Information Technology (ICCIT 2007).

[4]  Alfred O. Hero,et al.  Using proximity and quantized RSS for sensor localization in wireless networks , 2003, WSNA '03.

[5]  J. Serrat,et al.  Multiple vehicle 3D tracking using an unscented Kalman , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[6]  Michael Spranger,et al.  Making use of what you don't see: negative information in Markov localization , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Ümit Özgüner,et al.  Cooperative multitarget tracking and surveillance with mobile sensing agents: A decentralized approach , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[8]  Wu Chen,et al.  Adaptive Kalman Filtering for Vehicle Navigation , 2003 .

[9]  Carsten Hasberg,et al.  Simultaneous Localization and Mapping for Path-Constrained Motion , 2012, IEEE Transactions on Intelligent Transportation Systems.

[10]  Manuela M. Veloso,et al.  Effective Multi-Model Motion Tracking using Action Models , 2009, Int. J. Robotics Res..

[11]  Ming Yang,et al.  Laser radar based real-time ego-motion estimation for intelligent vehicles , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[12]  N. Floudas,et al.  A survey of filtering techniques for vehicle tracking by radar equipped automotive platforms , 2005, 2005 7th International Conference on Information Fusion.

[13]  Stewart Worrall,et al.  A probabilistic method for detecting impending vehicle interactions , 2008, 2008 IEEE International Conference on Robotics and Automation.

[14]  Franz Kummert,et al.  Vehicle tracking and motion prediction in complex urban scenarios , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[15]  Se-Young Oh,et al.  Modeling of vehicle dynamics from real vehicle measurements using a neural network with two-stage hybrid learning for accurate long-term prediction , 2004, IEEE Trans. Veh. Technol..

[16]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[17]  Tieniu Tan,et al.  A system for learning statistical motion patterns , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Lennart Svensson,et al.  A New Multiple Model Filter With Switch Time Conditions , 2010, IEEE Transactions on Signal Processing.

[19]  Stewart Worrall,et al.  Using Non-Parametric Filters and Sparse Observations to Localise a Fleet of Mining Vehicles , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[20]  Tieniu Tan,et al.  Learning activity patterns using fuzzy self-organizing neural network , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  E. Nebot,et al.  Wireless Network for Mining Applications , 2004 .

[22]  K. Punithakumar,et al.  Multiple-model probability hypothesis density filter for tracking maneuvering targets , 2004, IEEE Transactions on Aerospace and Electronic Systems.

[23]  T. Kirubarajan,et al.  Multiple-model probability hypothesis density filter for tracking maneuvering targets , 2008 .

[24]  Shahzad Memon,et al.  On demand radio frequency identification based vehicle tracking system , 2010, Int. J. Bus. Inf. Syst..

[25]  Eduardo Mario Nebot,et al.  Mining GPS data for extracting significant places , 2009, 2009 IEEE International Conference on Robotics and Automation.

[26]  Fei-Yue Wang,et al.  Data-Driven Intelligent Transportation Systems: A Survey , 2011, IEEE Transactions on Intelligent Transportation Systems.

[27]  Raj Madhavan,et al.  Prediction in Dynamic Environments for Autonomous On-Road Driving , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[28]  Dewang Chen,et al.  Freeway traffic stream modeling based on principal curves , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[29]  Kevin J. Sullivan,et al.  Utilizing negative information to track ground vehicles through move-stop-move cycles , 2004, SPIE Defense + Commercial Sensing.

[30]  Leonhard M. Reindl,et al.  Unscented and Extended Kalman Estimators for non Linear Indoor Tracking Using Distance Measurements , 2007, 2007 4th Workshop on Positioning, Navigation and Communication.

[31]  Stephen J. Maybank,et al.  Vehicle Trajectory Approximation and Classification , 1998, BMVC.

[32]  Chang Choi,et al.  Comparing Ontologies Using Entropy , 2007, 2007 International Conference on Convergence Information Technology (ICCIT 2007).

[33]  Christian Laugier,et al.  Incremental Learning of Statistical Motion Patterns With Growing Hidden Markov Models , 2007, IEEE Transactions on Intelligent Transportation Systems.

[34]  Christoph Hermes,et al.  Long-term vehicle motion prediction , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[35]  Wolfram Burgard,et al.  Learning Motion Patterns of People for Compliant Robot Motion , 2005, Int. J. Robotics Res..