Yasir Latif

PhD Candidate, Universidad de Zaragoza, Spain


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.

Research Visits

Marine Robotics Group, MIT

Supervisor: John Leonard

Jan 2014

I worked with Prof. John Leonard on representing loop closing as a sparse optimization problem.

Imperial College London

Supervisor: Andrew Davison

Jan 2013

I was working with Andrew Davison and his PhD students on DTAM like methods for monocular Dense SLAM.


Universidad de Zaragoza, Spain

Doctoral Candidate


PhD Candidate under the supervision of Jose Neira

Munich University of Technology (TUM), Germany

MSc. in Communication Engineering

Sept 2009

GIK Institute of Science and Technology, Pakistan

BS in Computer System Engineering

Jul 2006


Robust SLAM Realizing, Reversing, Recovering (RRR) algorithm

The code accompanying our work on Robustifying the SLAM backend can be found at https://github.com/ylatif/rrr

Robust SLAM Benchmarking Dataset

Dataset that we developed for benchmarking Robust SLAM methods https://github.com/ylatif/dataset-RobustSLAM

Publications (in reverse chronological order)