Multi-Robot Fastslam for Large Domains

Abstract : For a robot to build a map of its surrounding area, it must have accurate position information within the area, and to obtain accurate position information within the area, the robot needs to have an accurate map of the area. This circular problem is the Simultaneous Localization and Mapping (SLAM) problem. An efficient algorithm to solve it is FastSLAM, which is based on the Rao-Blackwellized particle filter. FastSLAM solves the SLAM problem for single-robot mapping using particles to represent the posterior of the robot pose and the map. Each particle of the filter possesses its own global map which is likely to be a grid map. The memory space required for these maps poses a serious limitation to the algorithm's capability when the problem space is large. The problem will only get worse if the algorithm is adapted to multi-robot mapping. This thesis presents an alternate mapping algorithm that extends the single-robot FastSLAM algorithm to a multi-robot mapping algorithm that uses Absolute Space Representations (ASR) to represent the world. But each particle still maintains a local grid to map its vicinity and periodically this grid map is converted into an ASR. An ASR expresses a world in polygons requiring only a minimal amount of memory space. By using this altered mapping strategy, the problem faced in FastSLAM when mapping a large domain can be alleviated. In this algorithm, each robot maps separately, and when two robots encounter each other they exchange range and odometry readings from their last encounter to this encounter. Each robot then sets up another filter for the other robot's data and incrementally updates its own map, incorporating the passed data and its own data at the same time. The passed data is processed in reverse by the receiving robot as if a virtual robot is back-tracking the path of the other robot. The algorithm is demonstrated using three data sets collected using a single robot equipped with odometry and laser-range finder sensors.

[1]  Matthew R. Walter,et al.  An Experimental investigation of cooperative SLAM , 2004 .

[2]  Benjamin Kuipers,et al.  A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations , 1991, Robotics Auton. Syst..

[3]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[4]  Sebastian Thrun,et al.  Robotic mapping: a survey , 2003 .

[5]  Andrew Howard,et al.  Multi-robot Simultaneous Localization and Mapping using Particle Filters , 2005, Int. J. Robotics Res..

[6]  Juan Andrade-Cetto,et al.  Multirobot C-SLAM: Simultaneous localization, control, and mapping , 2005 .

[7]  R. Siegwart,et al.  Combining Topological and Metric: A Natural Integration for Simultaneous Localization and Map Building , 2001 .

[8]  Sebastian Thrun,et al.  Integrating Grid-Based and Topological Maps for Mobile Robot Navigation , 1996, AAAI/IAAI, Vol. 2.

[9]  Erik Wolfart.  Position Refinement for a Navigating Robot Using Motion Information Based on Honey Bee Strategies , 1994 .

[10]  Wolfram Burgard,et al.  Integrating Topological and Metric Maps for Mobile Robot Navigation: A Statistical Approach , 1998, AAAI/IAAI.

[11]  H. Lau,et al.  Behavioural Approach for Multi-Robot Exploration , 2003 .

[12]  W MurrayDavid,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002 .

[13]  Mark A. Paskin,et al.  Thin Junction Tree Filters for Simultaneous Localization and Mapping , 2002, IJCAI.

[14]  Gordon Wyeth,et al.  A modified particle filter for simultaneous robot localization and landmark tracking in an indoor environment , 2004 .

[15]  Kevin P. Murphy,et al.  Bayesian Map Learning in Dynamic Environments , 1999, NIPS.

[16]  Sebastian Thrun,et al.  Learning Maps for Indoor Mobile Robot Navigation. , 1996 .

[17]  Sebastian Thrun,et al.  Multi-robot SLAM with Sparse Extended Information Filers , 2003, ISRR.

[18]  Kurt Konolige,et al.  Markov Localization using Correlation , 1999, IJCAI.

[19]  Sebastian Thrun,et al.  Bayesian Landmark Learning for Mobile Robot Localization , 1998, Machine Learning.

[20]  Kristopher R. Beevers.  TOPOLOGICAL MAPPING AND MAP MERGING WITH SENSING-LIMITED ROBOTS , 2004 .

[21]  Maria L. Gini,et al.  Using visual features to build topological maps of indoor environments , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[22]  Carl F. R. Weiman,et al.  Helpmate autonomous mobile robot nav-igation system , 1991 .

[23]  Larry D. Pyeatt,et al.  Multi-agent Mapping Using Dynamic Allocation Utilizing a Centralized Storage System , 2004 .

[24]  Liqiang Feng,et al.  Navigating Mobile Robots: Systems and Techniques , 1996 .

[25]  Leslie Pack Kaelbling,et al.  Learning Topological Maps with Weak Local Odometric Information , 1997, IJCAI.

[26]  Oscar Serrano Serrano.  Robot localization using wireless networks , 2003 .

[27]  Kurt Konolige,et al.  A practical, decision-theoretic approach to multi-robot mapping and exploration , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[28]  Steven M. LaValle,et al.  Optimal navigation and object finding without geometric maps or localization , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[29]  Gregory Dudek,et al.  Multi-Robot Exploration of an Unknown Environment, Efficiently Reducing the Odometry Error , 1997, IJCAI.

[30]  Wolfram Burgard,et al.  A Probabilistic Approach to Collaborative Multi-Robot Localization , 2000, Auton. Robots.

[31]  Juan Andrade-Cetto,et al.  Simultaneous Localization, Control and Mapping , 2006 .

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

[33]  Stefan B. Williams,et al.  An efficient approach to the simultaneous localisation and mapping problem , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[34]  Wolfram Burgard,et al.  Integrating global position estimation and position tracking for mobile robots: the dynamic Markov localization approach , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[35]  Andrew Howard,et al.  Multi-robot mapping using manifold representations , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[36]  Ingemar J. Cox,et al.  Modeling a Dynamic Environment Using a Bayesian Multiple Hypothesis Approach , 1994, Artif. Intell..

[37]  Kurt Konolige,et al.  Mobile robot sense net , 1999, Optics East.

[38]  Hugh F. Durrant-Whyte,et al.  Simultaneous Mapping and Localization with Sparse Extended Information Filters: Theory and Initial Results , 2004, WAFR.

[39]  Wolfram Burgard,et al.  A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[40]  Reid G. Simmons,et al.  Probabilistic Robot Navigation in Partially Observable Environments , 1995, IJCAI.

[41]  Eduardo Mario Nebot,et al.  Optimization of the simultaneous localization and map-building algorithm for real-time implementation , 2001, IEEE Trans. Robotics Autom..

[42]  Stefan B. Williams,et al.  Towards multi-vehicle simultaneous localisation and mapping , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[43]  Arnaud Doucet,et al.  Sequential Monte Carlo Methods , 2006, Handbook of Graphical Models.

[44]  Ian D. Reid,et al.  Towards constant time SLAM using postponement , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[45]  Nando de Freitas,et al.  Sequential Monte Carlo in Practice , 2001 .

[46]  Evangelos E. Milios,et al.  Globally Consistent Range Scan Alignment for Environment Mapping , 1997, Auton. Robots.

[47]  John J. Leonard,et al.  Cooperative concurrent mapping and localization , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[48]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[49]  Wolfram Burgard,et al.  Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids , 1996, AAAI/IAAI, Vol. 2.

[50]  Ryo Kurazume,et al.  Cooperative positioning with multiple robots , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[51]  Kurt Konolige,et al.  Map merging for distributed robot navigation , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[52]  W. Burgard,et al.  Markov Localization for Mobile Robots in Dynamic Environments , 1999, J. Artif. Intell. Res..

[53]  Roland Siegwart,et al.  Hybrid simultaneous localization and map building: closing the loop with multi-hypotheses tracking , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[54]  Oscar Serrano Serrano,et al.  Robot localization using WiFi signal without intensity map , 2004 .

[55]  Patric Jensfelt,et al.  Active global localization for a mobile robot using multiple hypothesis tracking , 2001, IEEE Trans. Robotics Autom..

[56]  J.-S. Gutmann,et al.  AMOS: comparison of scan matching approaches for self-localization in indoor environments , 1996, Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96).

[57]  Dieter Fox.  Distributed Multi-Robot Exploration and Mapping , 2005, CRV.

[58]  Sebastian Thrun,et al.  Simultaneous localization and mapping with unknown data association using FastSLAM , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).