Spatial Perception for Mobile Robots

Stefan Leutenegger (Imperial College, UK)

Abstract:

Robustness and accuracy of real-time localisation and mapping systems have dramatically improved recently, thanks to advances in processing hardware and commoditisation of sensors such as RGB-D cameras and inertial measurement units. I have been working on related algorithms and their software implementations, with a more recent focus on bringing together dense geometry and semantic, object-level scene understanding. The aim of these recent works is to bridge the sense-AI-gap and empower the next generation of mobile robots that need to plan and execute complex tasks in potentially cluttered, and dynamic environments, possibly in proximity of people. Example applications to be shown include inspection and autonomous construction with drones.