Towards Event-based SLAM
Event-based cameras are bio-inspired vision sensors whose pixels work independently from each other and respond asynchronously to brightness changes, with microsecond resolution. Their advantages make it possible to tackle challenging scenarios in robotics, such as high-speed and high dynamic range scenes. The main challenge in robot perception with these sensors is to design new algorithms that process the unfamiliar stream of intensity changes (“events”) and are able to unlock the sensor’s potential. In this talk, I will first describe the working principle of an event-based camera. Then a brief review is given on the recent progress of event-based localization and mapping. Afterwards, I will introduce our recent open-source project – ESVO and disclose more details of it. Finally, I conclude by discussing the limitations, challenges and open questions for event-based cameras.