Topological mapping using spectral clustering and classification Export

@proceedings{brunskill-etal-iros07, abstract = {In this work we present an online method for generating topological maps from raw sensor information. We first describe an algorithm to automatically decompose a map into submap segments using a graph partitioning technique known as spectral clustering. We then describe how to train a classifier to recognize graph submaps from laser signatures using the AdaBoost machine learning algorithm. We demonstrate that the we can perform topological mapping by incrementally segmenting the world as the robot moves through its environment, and we can close the loop when the learned classifier recognizes that the robot has returned to a previously visited location.}, author = {Brunskill, E. and Kollar, T. and Roy, N.}, booktitle = {Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on}, citeulike-article-id = {4402342}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/IROS.2007.4399611}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4399611}, doi = {10.1109/IROS.2007.4399611}, journal = {Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on}, keywords = {slam}, pages = {3491--3496}, posted-at = {2009-04-25 04:49:42}, priority = {2}, title = {Topological mapping using spectral clustering and classification}, url = {http://dx.doi.org/10.1109/IROS.2007.4399611}, year = {2007} }

TY - CONF ID - brunskill-etal-iros07 L3 - citeulike-article-id:4402342 N2 - In this work we present an online method for generating topological maps from raw sensor information. We first describe an algorithm to automatically decompose a map into submap segments using a graph partitioning technique known as spectral clustering. We then describe how to train a classifier to recognize graph submaps from laser signatures using the AdaBoost machine learning algorithm. We demonstrate that the we can perform topological mapping by incrementally segmenting the world as the robot moves through its environment, and we can close the loop when the learned classifier recognizes that the robot has returned to a previously visited location. JF - Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on EP - 3496 TI - Topological mapping using spectral clustering and classification T2 - Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on SP - 3491 KW - slam AU - Brunskill, E AU - Kollar, T AU - Roy, N PY - 2007/// UR - http://dx.doi.org/10.1109/IROS.2007.4399611 ER -