Marine Robotics Group, MIT
Supervisor: John Leonard
Jan 2014I worked with Prof. John Leonard on representing loop closing as a sparse optimization problem.
PhD candidate working in robotics at Universidad de Zaragoza Spain. My main focus during my PhD has been Roboust methods for solving the Simultaneous Localization And Mapping (SLAM) problem. The need for which arises from (presently) unavoidable false positives in place recognition algorithms.
I am also interested in the SLAM problem in general and the current development of Dense SLAM methods in particular.
I worked with Prof. John Leonard on representing loop closing as a sparse optimization problem.
I was working with Andrew Davison and his PhD students on DTAM like methods for monocular Dense SLAM.
PhD Candidate under the supervision of Jose Neira
The code accompanying our work on Robustifying the SLAM backend can be found at https://github.com/ylatif/rrr
Dataset that we developed for benchmarking Robust SLAM methods https://github.com/ylatif/dataset-RobustSLAM
[IROS] Robust Graph SLAM Back-ends: A Comparative Analysis,
Y. Latif, C. Cadena and J. Neira,
IEEE / RSJ International Conference on Intelligent Robots and Systems, September 2014, Chicago, IL, USA.
[IROS] Place Categorization using Sparse and Redundant Representations,
H. Carrillo,Y. Latif, J. Neira and J. A. Castellanos,
IEEE / RSJ International Conference on Intelligent Robots and Systems, September 2014, Chicago, IL, USA.
[RSS] An Online Sparsity-Cognizant Loop-Closure Algorithm for Visual Navigation,
Y. Latif, G. Huang, J. Leonard and J. Neira,
Robotics: Science and Systems (RSS), Berkely, July, 2014
[ICRA-WS] Applying Sparse l-1 Optimzation to problems in Robotics,
Y. Latif, G. Huang, J. Leonard and J. Neira,
Workshop on Long Term Autonomy,
IEEE Int. Conf. Robotics and Automation, Hong Kong, June, 2014
[ECMR] Go Straight, Turn Right: Pose Graph Reduction through Trajectory Segmentation using Line Segments,
Y. Latif and J. Neira,
European Conference on Mobile Robots
Sep 25-27, 2013 , Barcelona, Catalonia, Spain.
[IJRR] Robust Loop Closing for Pose-Graph SLAM
Y. Latif, C. Cadena and J. Neira,
International Journal of Robotics Research (IJRR), Special Issue on Long Term Autonomy, 2013.
[ICIP] Speeded-up SURF: Design of an Efficient Multiscale Feature Detector,
F. Schweiger, G. Schroth, R. Huitl, Y. Latif, E. Steinbach,
IEEE International Conference on Image Processing (ICIP), Melbourne, Australia, September 2013.
[ICRA-WS] Detecting the Correct Graph Structure in Pose Graph SLAM,
Y. Latif, C. Cadena and J. Neira,
1st Workshop on Robust and Multimodal Inference in Factor Graphs,
2013 IEEE Int. Conf. Robotics and Automation, Karsrhure, Germany, May, 2013
[IROS] Realizing, Reversing, Recovering : Incremental Robust Loop Closing over time using the iRRR algorithm,
Y. Latif, C. Cadena, and J. Neira,
IEEE/RSJ Int.Conf.on Intelligent Robots and Systems, October 7-12, 2012, Vilamoura, Portugal,
[IROS] Fast Minimum Uncertainty Search on a Graph Map Representation,
H. Carrillo, Y. Latif, J. Neira and J.A. Castellanos,
IEEE/RSJ Int.Conf.on Intelligent Robots and Systems, October 7-12, 2012, Vilamoura, Portugal,
[RSS] Robust Loop Closing Over Time,
Y. Latif, C. Cadena, and J. Neira,
Robotics: Science snd Systems, Sydney, Australia, July 2012.