Discrete and Continuous, Probabilistic Anticipation for Autonomous Robots in Urban Environments

This paper develops a probabilistic anticipation algorithm for dynamic objects observed by an autonomous robot in an urban environment. Predictive Gaussian mixture models are used due to their ability to probabilistically capture continuous and discrete obstacle decisions and behaviors; the predictive system uses the probabilistic output (state estimate and covariance) of a tracking system and map of the environment to compute the probability distribution over future obstacle states for a specified anticipation horizon. A Gaussian splitting method is proposed based on the sigma-point transform and the nonlinear dynamics function, which enables increased accuracy as the number of mixands grows. An approach to caching elements of this optimal splitting method is proposed, in order to enable real-time implementation. Simulation results and evaluations on data from the research community demonstrate that the proposed algorithm can accurately anticipate the probability distributions over future states of nonlinear systems.

[1]  Sebastian Thrun,et al.  Towards fully autonomous driving: Systems and algorithms , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[2]  John R. Hershey,et al.  Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[3]  Uwe D. Hanebeck,et al.  Progressive Gaussian mixture reduction , 2008, 2008 11th International Conference on Information Fusion.

[4]  Friedrich Faubel,et al.  The Split and Merge Unscented Gaussian Mixture Filter , 2009, IEEE Signal Processing Letters.

[5]  William Whittaker,et al.  Autonomous driving in urban environments: Boss and the Urban Challenge , 2008, J. Field Robotics.

[6]  Jindrich Dunik,et al.  SIGMA POINT GAUSSIAN SUM FILTER DESIGN USING SQUARE ROOT UNSCENTED FILTERS , 2005 .

[7]  Mike McDonald,et al.  Socio-economic impact assessment of intelligent transport systems , 2006 .

[8]  Ephrahim Garcia,et al.  Team Cornell's Skynet: Robust perception and planning in an urban environment , 2008, J. Field Robotics.

[9]  Mark L. Psiaki,et al.  Gaussian Mixture Approximation by Another Gaussian Mixture for "Blob" Filter Re-Sampling , 2010 .

[10]  Yoshiaki Shirai,et al.  Probabilistic Uncertainty Modeling of Obstacle Motion for Robot Motion Planning , 2002, J. Robotics Mechatronics.

[11]  Christian Laugier,et al.  Probabilistic Rapidly-exploring Random Trees for autonomous navigation among moving obstacles , 2009 .

[12]  Richard Bishop.  Intelligent Vehicle Applications Worldwide , 2000, IEEE Intell. Syst..

[13]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[14]  S. Julier,et al.  A General Method for Approximating Nonlinear Transformations of Probability Distributions , 1996 .

[15]  Marco F. Huber.  Adaptive Gaussian mixture filter based on statistical linearization , 2011, 14th International Conference on Information Fusion.

[16]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[17]  Kazuya Yoshida,et al.  Collision avoidance method for mobile robot considering motion and personal spaces of evacuees , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Mark Campbell,et al.  Discrete and continuous, probabilistic anticipation for autonomous robots in urban environments , 2010, Security + Defence.

[19]  Joel W. Burdick,et al.  Robotic motion planning in dynamic, cluttered, uncertain environments , 2010, 2010 IEEE International Conference on Robotics and Automation.

[20]  Mark E. Campbell,et al.  Contingency planning over probabilistic hybrid obstacle predictions for autonomous road vehicles , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  Christian Hennig,et al.  Methods for merging Gaussian mixture components , 2010, Adv. Data Anal. Classif..

[22]  Simo Ali-Loytty,et al.  Gaussian Mixture Filter in Hybrid Navigation , 2007 .

[23]  Ephrahim Garcia,et al.  Team Cornell's Skynet: Robust perception and planning in an urban environment , 2008 .

[24]  Joel W. Burdick,et al.  Robot Motion Planning in Dynamic, Uncertain Environments , 2012, IEEE Transactions on Robotics.

[25]  Hagai Aronowitz,et al.  A distance measure between GMMs based on the unscented transform and its application to speaker recognition , 2005, INTERSPEECH.

[26]  Frank Nielsen,et al.  Levels of Details for Gaussian Mixture Models , 2009, ACCV.

[27]  Evgueni A. Haroutunian,et al.  Information Theory and Statistics , 2011, International Encyclopedia of Statistical Science.

[28]  Han-Pang Huang,et al.  Robot Motion Planning in Dynamic Uncertain Environments , 2011, Adv. Robotics.

[29]  Luke Fletcher,et al.  The MIT - Cornell Collision and Why It Happened , 2009, The DARPA Urban Challenge.

[30]  Thierry Fraichard,et al.  Safe motion planning in dynamic environments , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[31]  K..  Dynamic Map Building and Localization : New Theoretical Foundations , 2015 .

[32]  A.R. Runnalls,et al.  A Kullback-Leibler Approach to Gaussian Mixture Reduction , 2007 .

[33]  R. L. Moose,et al.  A modified Gaussian sum approach to estimation of non-Gaussian signals , 1993 .

[34]  T. Singh,et al.  Uncertainty Propagation for Nonlinear Dynamic Systems Using Gaussian Mixture Models , 2008 .

[35]  Robin J. Evans,et al.  Measurement Gaussian Sum Mixture Target Tracking , 2006, 2006 9th International Conference on Information Fusion.

[36]  P. S. Maybeck,et al.  Cost-function-based gaussian mixture reduction for target tracking , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[37]  S. Kolski,et al.  Detection, prediction, and avoidance of dynamic obstacles in urban environments , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[38]  D.J. Salmond,et al.  Mixture Reduction Algorithms for Point and Extended Object Tracking in Clutter , 2009, IEEE Transactions on Aerospace and Electronic Systems.

[39]  Beom Hee Lee,et al.  Analytic collision anticipation technology considering agents' future behavior , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[40]  Petar M. Djuric,et al.  Gaussian sum particle filtering , 2003, IEEE Trans. Signal Process..

[41]  Zhihua Zhang,et al.  EM algorithms for Gaussian mixtures with split-and-merge operation , 2003, Pattern Recognition.

[42]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[43]  Rudolph van der Merwe,et al.  Sigma-point kalman filters for probabilistic inference in dynamic state-space models , 2004 .

[44]  H. Sorenson,et al.  Recursive bayesian estimation using gaussian sums , 1971 .

[45]  Peter King,et al.  Odin: Team VictorTango's entry in the DARPA Urban Challenge , 2008, J. Field Robotics.

[46]  H. Sorenson,et al.  Nonlinear Bayesian estimation using Gaussian sum approximations , 1972 .

[47]  Siddhartha S. Srinivasa,et al.  Planning-based prediction for pedestrians , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[48]  Geoffrey E. Hinton,et al.  SMEM Algorithm for Mixture Models , 1998, Neural Computation.

[49]  Solomon Kullback,et al.  Information Theory and Statistics , 1970, The Mathematical Gazette.

[50]  Tyler C. Folsom.  Social ramifications of autonomous urban land vehicles , 2011, 2011 IEEE International Symposium on Technology and Society (ISTAS).