From SLAM to Spatial AI


Professor Andrew Davidson

“Robotics Today - A series of technical talks” is a new virtual robotics seminar series.

To enable the next generation of smart robots and devices which can truly interact with their environments, Simultaneous Localisation and Mapping (SLAM) algorithms are needed to develop general real-time geometric and semantic `Spatial AI' perception capability.

Andrew Davison, Professor of Robot Vision and Director of the Dyson Robotics Laboratory at Imperial College London was recently invited to take part in the virtual robotics seminar series “Robotics Today”. The series, which is open to members of the public and organised by researchers at Stanford and MIT, sees academics from across the world giving weekly talks on the latest research in robotics.

Professor Davison gave his seminar on SLAM (Simultaneous Localisation and Mapping) and its evolution towards general `Spatial AI': computer vision algorithms which enable robots and other artificial devices to map, localise within and ultimately understand and interact with the 3D spaces around them.

Within his talk, Professor Davison gave examples of the work he and his research group are working on, including ways in which they have gradually increased visual SLAM capability over the years. More research must still be done in this area to achieve true Spatial AI performance and a key issue is how estimation and machine learning components can be used and trained together in continuing to search for the best long-term scene representations to enable intelligent interaction.

Professor Davison’s research group and collaborators have consistently developed and demonstrated breakthrough systems, including MonoSLAM, KinectFusion, SLAM++ and CodeSLAM, and recent prizes include Best Paper at ECCV 2016 and Best Paper Honourable Mention at CVPR 2018.

"Robotics Today - A series of technical talks" is a virtual robotics seminar series. The goal of the series is to bring the robotics community together during these challenging times. 

Find out more about the seminar series []


Mr Ahmed Idle

Mr Ahmed Idle
Department of Computing