Intelligent Maps for Autonomous Kilometer-Scale Science Survey

We present a new approach for site survey by autonomous surface robots. In our method the agent constructs an intelligent map, a multi-scale model of the explored environment incorporating in situ and remote sensing data. The agent learns the model’s parameters on the fly and exploits its predictions to guide adaptive navigation and sampling. In this manner the agent can respond appropriately to novel correlations, resource constraints and execution errors. Rover tests at Amboy Crater, California demonstrate improved performance over non-adaptive strategies for a geologic survey task.

[1]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[2]  John F. Mustard,et al.  Deconvolution of spectra for intimate mixtures , 1987 .

[3]  David J. C. MacKay,et al.  Information-Based Objective Functions for Active Data Selection , 1992, Neural Computation.

[4]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .

[5]  Maurice Queyranne,et al.  An Exact Algorithm for Maximum Entropy Sampling , 1995, Oper. Res..

[6]  Jon Lee.  Constrained Maximum-Entropy Sampling , 1998, Oper. Res..

[7]  Wolfram Burgard,et al.  Coordination for Multi-Robot Exploration and Mapping , 2000, AAAI/IAAI.

[8]  H. Wynn,et al.  Maximum entropy sampling and optimal Bayesian experimental design , 2000 .

[9]  Reid G. Simmons,et al.  Recent progress in local and global traversability for planetary rovers , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[10]  Stewart J. Moorehead,et al.  A Multiple Information Source Planner for Autonomous Planetary Exploration , 2001 .

[11]  William Whittaker,et al.  Autonomous robotic meteorite identification in Antarctica , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[12]  Jon Lee.  Maximum entropy sampling , 2001 .

[13]  Virginia C. Gulick,et al.  HiRISE: The High Resolution Imaging Science Experiment for Mars Reconnaissance Orbiter , 2002 .

[14]  Mark J. Schervish,et al.  Nonstationary Covariance Functions for Gaussian Process Regression , 2003, NIPS.

[15]  Bayesian Adaptive Exploration in a Nutshell , 2003 .

[16]  Tara Estlin,et al.  Rover traverse science for increased mission science return , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[17]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[18]  Rob Sherwood,et al.  Using Autonomy Flight Software to Improve Science Return on Earth Observing One , 2005, J. Aerosp. Comput. Inf. Commun..

[19]  William Whittaker,et al.  First Experiments in the Robotic Investigation of Life in the Atacama Desert of Chile , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[20]  Andreas Krause,et al.  Near-optimal sensor placements in Gaussian processes , 2005, ICML.

[21]  David S. Wettergreen,et al.  SECOND EXPERIMENTS IN THE ROBOTIC INVESTIGATION OF LIFE IN THE ATACAMA DESERT OF CHILE , 2005 .

[22]  Chandra Chekuri,et al.  A recursive greedy algorithm for walks in directed graphs , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[23]  C. Rasmussen,et al.  Nonstationary Gaussian Process Regression using a Latent Extension of the Input Space , 2006 .

[24]  Alex S. Fukunaga,et al.  Automatic detection of dust devils and clouds on Mars , 2008, Machine Vision and Applications.

[25]  Andreas Krause,et al.  Efficient Planning of Informative Paths for Multiple Robots , 2006, IJCAI.

[26]  David R. Thompson,et al.  Generating Exponentially Smaller POMDP Models Using Conditionally Irrelevant Variable Abstraction , 2007, ICAPS.

[27]  Andreas Krause,et al.  Nonmyopic Informative Path Planning in Spatio-Temporal Models , 2007, AAAI.

[28]  David R. Thompson,et al.  Autonomous Rover Reflectance Spectroscopy with Dozens of Targets , 2008 .