I am Emanuele Vespa, a Ph.D student under the supervision of Professor Paul Kelly at Imperial College London. I am affiliated with the Software Performance Optimisation group. My current research focus is on domain-specific optimisations for computer vision applications, in particular for Simultaneous Localisation and Mapping (SLAM).
My research is kindly funded by ARM and the Engineering and Physical Sciences Research Council (EPSRC).
Email: e.vespa14_XYZ@imperial.ac.uk (remove _XYZ)
Simultaneous Localisation and Mapping (SLAM) is a family of algorithms that enables a moving agent (such as a robot or a smartphone) equipped with vision/motion sensors to localise itself in the environment, while at the same time building a coherent map of the observed world. Understanding an unknown environment is a complex task which involves a variety of aspects, from inferring the scene geometry to recognising objects in the scene. Most application scenarios require real-time performance, which are often hard to achieve. My work focuses on developing cutting-edge tools to break this performance barriers. Either via novel algorithms or low-level performance optimisations, I aim at producing tools which enable real-time interaction for a variety of applications, from mobile robotics to AR/VR devices.
E. Vespa, N. Nikolov, M. Grimm, L. Nardi, P. H. J. Kelly and S. Leutenegger. Efficient Octree-Based Volumetric SLAM Supporting Signed-Distance and Occupancy Mapping. In IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 1144-1151, April 2018.
B. Bodin, H. Wagstaff, S. Saeedi, L. Nardi, E. Vespa, J.H. Mayer, A. Nisbet, M. Luján, S. Furber, A.J. Davison, P. HJ Kelly and M. O'Boyle, SLAMBench2: Multi-Objective Head-to-Head Benchmarking for Visual SLAM. in Proc. of The International Conference in Robotics and Automation (ICRA 2018), Brisbane, Australia, May 2018.
M. Z. Zia, L. Nardi, A. Jack, E. Vespa, B. Bodin, P. H. J. Kelly and A. J. Davison. Comparative Design Space Exploration of Dense and Semi-Dense SLAM. In IEEE Intl. Conf. on Robotics and Automation (ICRA 2016), Stockholm, Sweden, May 2016. (arxiv)