An Information-Theoretic Approach to Persistent Environment Monitoring Through Low Rank Model Based Planning and Prediction

Robots can be used to collect environmental data in regions that are difficult for humans to traverse. However, limitations remain in the size of region that a robot can directly observe per unit time. We introduce a method for selecting a limited number of observation points in a large region, from which we can predict the state of unobserved points in the region. We combine a low rank model of a target attribute with an information-maximizing path planner to predict the state of the attribute throughout a region. Our approach is agnostic to the choice of target attribute and robot monitoring platform. We evaluate our method in simulation on two real-world environment datasets, each containing observations from one to two million possible sampling locations. We compare against a random sampler and four variations of a baseline sampler from the ecology literature. Our method outperforms the baselines in terms of average Fisher information gain per samples taken and performs comparably for average reconstruction error in most trials.

[1]  Stephen P. Boyd,et al.  Generalized Low Rank Models , 2014, Found. Trends Mach. Learn..

[2]  Mac Schwager,et al.  Persistent monitoring of changing environments using a robot with limited range sensing , 2011, 2011 IEEE International Conference on Robotics and Automation.

[3]  John S. Langford,et al.  An Unmanned Aircraft for Dropwindsonde Deployment and Hurricane Reconnaissance , 1993 .

[4]  Gaurav S. Sukhatme,et al.  An information-driven and disturbance-aware planning method for long-term ocean monitoring , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[5]  Yevgeniy Vorobeychik,et al.  Submodular Optimization with Routing Constraints , 2016, AAAI.

[6]  Ashish Kapoor,et al.  On Greedy Maximization of Entropy , 2015, ICML.

[7]  Ann Cowling Line‐Transect Sampling , 2006 .

[8]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[9]  Mac Schwager,et al.  Correlated Orienteering Problem and its application to informative path planning for persistent monitoring tasks , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Gaurav S. Sukhatme,et al.  Persistent ocean monitoring with underwater gliders: Adapting sampling resolution , 2011, J. Field Robotics.

[11]  Vijay Kumar,et al.  Information-Theoretic Planning with Trajectory Optimization for Dense 3D Mapping , 2015, Robotics: Science and Systems.

[12]  R. E. Harrison,et al.  Review of Satellite Remote Sensing Use in Forest Health Studies~!2010-01-27~!2010-04-05~!2010-06-29~! , 2010 .

[13]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..

[14]  B. Roy Frieden,et al.  Science from Fisher Information: A Unification , 2004 .

[15]  Geoffrey A. Hollinger,et al.  Sampling-based robotic information gathering algorithms , 2014, Int. J. Robotics Res..

[16]  Kian Hsiang Low,et al.  Active Markov information-theoretic path planning for robotic environmental sensing , 2011, AAMAS.

[17]  Silvia Ferrari,et al.  Information-Driven Sensor Path Planning by Approximate Cell Decomposition , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Gaurav S. Sukhatme,et al.  Data‐driven learning and planning for environmental sampling , 2017, J. Field Robotics.

[19]  N. Pettorelli,et al.  Using the satellite-derived NDVI to assess ecological responses to environmental change. , 2005, Trends in ecology & evolution.

[20]  Kian Hsiang Low,et al.  Information-Theoretic Approach to Efficient Adaptive Path Planning for Mobile Robotic Environmental Sensing , 2009, ICAPS.

[21]  John A. Silander,et al.  Green-up of deciduous forest communities of northeastern North America in response to climate variation and climate change , 2014, Landscape Ecology.

[22]  Madeleine Udell,et al.  OBOE: Collaborative Filtering for AutoML Initialization. , 2018 .

[23]  Wenjie Lu,et al.  An Information Potential Approach to Integrated Sensor Path Planning and Control , 2014, IEEE Transactions on Robotics.

[24]  Andreas Krause,et al.  Nonmyopic Adaptive Informative Path Planning for Multiple Robots , 2009, IJCAI.

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

[26]  Paul Scerri,et al.  Path planning for autonomous information collecting vehicles , 2008, 2008 11th International Conference on Information Fusion.

[27]  Ufuk Topcu,et al.  A Randomized Greedy Algorithm for Near-Optimal Sensor Scheduling in Large-Scale Sensor Networks , 2017, 2018 Annual American Control Conference (ACC).

[28]  G. Zhang,et al.  An Information Roadmap Method for Robotic Sensor Path Planning , 2009, J. Intell. Robotic Syst..

[29]  Gamini Dissanayake,et al.  Planning under uncertainty using model predictive control for information gathering , 2006, Robotics Auton. Syst..

[30]  Lawrence Bodin,et al.  Approximate Traveling Salesman Algorithms , 1980, Oper. Res..

[31]  Marco Pavone,et al.  The Team Surviving Orienteers problem: routing teams of robots in uncertain environments with survival constraints , 2018, Auton. Robots.

[32]  Nicholas R. J. Lawrance,et al.  Real-time path planning for long-term information gathering with an aerial glider , 2016, Auton. Robots.

[33]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.