Scalable Gas Sensing, Mapping, and Path Planning via Decentralized Hilbert Maps

This paper develops a decentralized approach to gas distribution mapping (GDM) and information-driven path planning for large-scale distributed sensing systems. Gas mapping is performed using a probabilistic representation known as a Hilbert map, which formulates the mapping problem as a multi-class classification task and uses kernel logistic regression to train a discriminative classifier online. A novel Hilbert map information fusion method is presented for rapidly merging the information from individual robot maps using limited data communication. A communication strategy that implements data fusion among many robots is also presented for the decentralized computation of GDMs. New entropy-based information-driven path-planning methods are developed and compared to existing approaches, such as particle swarm optimization (PSO) and random walks (RW). Numerical experiments conducted in simulated indoor and outdoor environments show that the information-driven approaches proposed in this paper far outperform other approaches, and avoid mutual collisions in real time.

[1]  Wenjie Lu,et al.  Multi-kernel probability distribution regressions , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[2]  Wolfram Burgard,et al.  Gas Distribution Modeling using Sparse Gaussian Process Mixture Models , 2008, Robotics: Science and Systems.

[3]  Silvia Ferrari,et al.  Distributed optimal control for multi-agent trajectory optimization , 2014, Autom..

[4]  Silvia Ferrari,et al.  A Generalized Reduced Gradient Method for the Optimal Control of Very-Large-Scale Robotic Systems , 2017, IEEE Transactions on Robotics.

[5]  Rishemjit Kaur,et al.  Cooperative control of multi-agent systems to locate source of an odor , 2017, ArXiv.

[6]  W. Jatmiko,et al.  Distributed odor source localization in dynamic environment , 2005, IEEE Sensors, 2005..

[7]  Silvia Ferrari,et al.  Fugitive gas emission rate estimation using multiple heterogeneous mobile sensors , 2017, 2017 ISOCS/IEEE International Symposium on Olfaction and Electronic Nose (ISOEN).

[8]  T. Moriizumi,et al.  Remote sensing of gas/odor source location and concentration distribution using mobile system , 1998 .

[9]  Badong Chen,et al.  Learning Nonlinear Generative Models of Time Series With a Kalman Filter in RKHS , 2014, IEEE Transactions on Signal Processing.

[10]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[11]  Cipriano Galindo,et al.  Integrating SLAM into gas distribution mapping , 2007 .

[12]  Badong Chen,et al.  Extended Kalman filter using a kernel recursive least squares observer , 2011, The 2011 International Joint Conference on Neural Networks.

[13]  Silvia Ferrari,et al.  A generalized reduced gradient method for the optimal control of multiscale dynamical systems , 2013, 52nd IEEE Conference on Decision and Control.

[14]  Hans P. Moravec,et al.  High resolution maps from wide angle sonar , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[15]  Richard A. Davis,et al.  Remarks on Some Nonparametric Estimates of a Density Function , 2011 .

[16]  Rodney M. Goodman,et al.  Distributed odor source localization , 2002 .

[17]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[18]  L. Benini,et al.  Context-Adaptive Multimodal Wireless Sensor Network for Energy-Efficient Gas Monitoring , 2013, IEEE Sensors Journal.

[19]  Silvia Ferrari,et al.  A Mobile Sensing Approach for Regional Surveillance of Fugitive Methane Emissions in Oil and Gas Production. , 2016, Environmental science & technology.

[20]  Lino Marques,et al.  Experimental studies on chemical concentration map building by a multi-robot system using bio-inspired algorithms , 2012, Autonomous Agents and Multi-Agent Systems.

[21]  Tom Duckett,et al.  Building gas concentration gridmaps with a mobile robot , 2003, Robotics Auton. Syst..

[22]  Tom Duckett,et al.  Creating gas concentration gridmaps with a mobile robot , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[23]  Badong Chen,et al.  A novel extended kernel recursive least squares algorithm , 2012, Neural Networks.

[24]  Silvia Ferrari,et al.  Distributed Optimal Control of Multiscale Dynamical Systems: A Tutorial , 2016, IEEE Control Systems.

[25]  Davide Brunelli,et al.  Autonomous Gas Detection and Mapping With Unmanned Aerial Vehicles , 2016, IEEE Transactions on Instrumentation and Measurement.

[26]  P. Zhu.  Kalman filtering in reproducing kernel Hilbert spaces , 2013 .

[27]  Vicente García-Díaz,et al.  A Decentralized Framework for Multi-Agent Robotic Systems , 2018, Sensors.

[28]  Sahar Asadi,et al.  Autonomous Gas-Sensitive Microdrone: Wind Vector Estimation and Gas Distribution Mapping , 2012, IEEE Robotics & Automation Magazine.

[29]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[30]  A. Ijspeert,et al.  Environmental monitoring using autonomous vehicles: a survey of recent searching techniques. , 2017, Current Opinion in Biotechnology.

[31]  Fabio Tozeto Ramos,et al.  Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent , 2015, Robotics: Science and Systems.

[32]  Silvia Ferrari,et al.  Distributed Optimal Control of Sensor Networks for Dynamic Target Tracking , 2018, IEEE Transactions on Control of Network Systems.

[33]  Bryce Doerr,et al.  Random Finite Set Theory and Optimal Control for Large Spacecraft Swarms , 2018, ArXiv.

[34]  Veysel Gazi,et al.  Asynchronous Particle Swarm Optimization Based Search with a Multi-Robot System: Simulation and Impl , 2010 .