Data-Driven Measurement Models for Active Localization in Sparse Environments

We develop an algorithm to explore an environment to generate a measurement model for use in future localization tasks. Ergodic exploration with respect to the likelihood of a particular class of measurement (e.g., a contact detection measurement in tactile sensing) enables construction of the measurement model. Exploration with respect to the information density based on the data-driven measurement model enables localization. We test the two-stage approach in simulations of tactile sensing, illustrating that the algorithm is capable of identifying and localizing objects based on sparsely distributed binary contacts. Comparisons with our method show that visiting low probability regions lead to acquisition of new information rather than increasing the likelihood of known information. Experiments with the Sphero SPRK robot validate the efficacy of this method for collision-based estimation and localization of the environment.

[1]  M. Hartmann,et al.  Ergodic Exploration Using Binary Sensing for Nonparametric Shape Estimation , 2017, IEEE Robotics and Automation Letters.

[2]  Todd Murphey,et al.  Projection-based iterative mode scheduling for switched systems , 2016 .

[3]  Jana Kosecka,et al.  Synthesizing Training Data for Object Detection in Indoor Scenes , 2017, Robotics: Science and Systems.

[4]  E. Guic-Robles,et al.  Rats can learn a roughness discrimination using only their vibrissal system , 1989, Behavioural Brain Research.

[5]  R. C. St.  D-Optimality for Regression Designs: A Review , 1975 .

[6]  John J. Leonard,et al.  Adaptive Mobile Robot Navigation and Mapping , 1999, Int. J. Robotics Res..

[7]  Brent Schwarz,et al.  LIDAR: Mapping the world in 3D , 2010 .

[8]  Ralph Helmar Rasshofer,et al.  Automotive Radar and Lidar Systems for Next Generation Driver Assistance Functions , 2005 .

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

[10]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[11]  Magnus Egerstedt,et al.  Transition-time optimization for switched-mode dynamical systems , 2006, IEEE Transactions on Automatic Control.

[12]  G. Chirikjian,et al.  Engineering Applications of Noncommutative Harmonic Analysis: With Emphasis on Rotation and Motion Groups , 2000 .

[13]  Andreas Krause,et al.  Nonmyopic active learning of Gaussian processes: an exploration-exploitation approach , 2007, ICML '07.

[14]  M. Hartmann,et al.  Spatiotemporal Patterns of Contact Across the Rat Vibrissal Array During Exploratory Behavior , 2016, Front. Behav. Neurosci..

[15]  Todd D. Murphey,et al.  Trajectory optimization for continuous ergodic exploration , 2013, 2013 American Control Conference.

[16]  Maja J. Matarić,et al.  Ergodic Dynamics by Design: A Route to Predictable Multi-Robot Systems , 2005 .

[17]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[18]  Todd D. Murphey,et al.  Real-Time Area Coverage and Target Localization Using Receding-Horizon Ergodic Exploration , 2017, IEEE Transactions on Robotics.

[19]  Alfred O. Hero,et al.  Sensor management using an active sensing approach , 2005, Signal Process..

[20]  John W. Wegrzyn,et al.  Multiplatform information-based sensor management: an inverted UAV demonstration , 2007, SPIE Defense + Commercial Sensing.

[21]  Valerii V. Fedorov,et al.  Optimal experimental design , 2010 .

[22]  Claire Dune,et al.  Active rough shape estimation of unknown objects , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  S. Shankar Sastry,et al.  Consistent Approximations for the Optimal Control of Constrained Switched Systems - Part 1: A Conceptual Algorithm , 2013, SIAM J. Control. Optim..

[24]  Mathew H. Evans,et al.  Tactile SLAM with a biomimetic whiskered robot , 2012, 2012 IEEE International Conference on Robotics and Automation.

[25]  Jan Peters,et al.  Active tactile object exploration with Gaussian processes , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[26]  Todd D. Murphey,et al.  Optimal planning for target localization and coverage using range sensing , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[27]  D. Simons,et al.  Biometric analyses of vibrissal tactile discrimination in the rat , 1990, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[28]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[29]  Tony J. Dodd,et al.  Active sensorimotor control for tactile exploration , 2017, Robotics Auton. Syst..

[30]  Ben Mitchinson,et al.  Feedback control in active sensing: rat exploratory whisking is modulated by environmental contact , 2007, Proceedings of the Royal Society B: Biological Sciences.

[31]  Juan D. Tardós,et al.  Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM , 2015, Robotics: Science and Systems.

[32]  I. Mezić,et al.  Metrics for ergodicity and design of ergodic dynamics for multi-agent systems , 2011 .

[33]  Nathan F. Lepora,et al.  Active Bayesian Perception for Simultaneous Object Localization and Identification , 2013, Robotics: Science and Systems.

[34]  Helge J. Ritter,et al.  A Probabilistic Approach to Tactile Shape Reconstruction , 2011, IEEE Transactions on Robotics.

[35]  Nando de Freitas,et al.  The Unscented Particle Filter , 2000, NIPS.

[36]  Marc Pollefeys,et al.  Self-calibration and visual SLAM with a multi-camera system on a micro aerial vehicle , 2014, Auton. Robots.

[37]  Erik I. Verriest,et al.  Gradient Descent Approach to Optimal Mode Scheduling in Hybrid Dynamical Systems , 2008 .

[38]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[39]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[40]  Siddhartha S. Srinivasa,et al.  Pose estimation for planar contact manipulation with manifold particle filters , 2015, Int. J. Robotics Res..

[41]  Beno Benhabib,et al.  Multicamera fusion for shape estimation and visibility analysis of unknown deforming objects , 2016, J. Electronic Imaging.

[42]  Takamitsu Matsubara,et al.  Active touch point selection with travel cost in tactile exploration for fast shape estimation of unknown objects , 2016, 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM).

[43]  Todd D. Murphey,et al.  Ergodic Exploration of Distributed Information , 2016, IEEE Transactions on Robotics.

[44]  Wolfram Burgard,et al.  Active Markov localization for mobile robots , 1998, Robotics Auton. Syst..

[45]  Gregory D. Hager,et al.  Tactile-Object Recognition From Appearance Information , 2011, IEEE Transactions on Robotics.

[46]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .