Abstract

Event-based cameras (Figure 1) offer much potential to the fields of robotics and computer
vision, in part due to their large dynamic range and extremely high “frame rates”. These
attributes make them, at least in theory, particularly suitable for enabling tasks like
navigation and mapping on high speed robotic platforms under challenging lighting
conditions, a task which has been particularly challenging for traditional algorithms and
camera sensors. Before these tasks become feasible however, progress must be made
towards adapting and innovating current RGB-camera-based algorithms to work with eventbased
cameras. In this paper we present ongoing research investigating two distinct
approaches to incorporating event-based cameras for robotic navigation:
1. The investigation of suitable place recognition / loop closure techniques, and
2. The development of efficient neural implementations of place recognition
techniques that enable the possibility of place recognition using event-based
cameras at very high frame rates using neuromorphic computing hardware.
Figure 1: The first commercial event camera: (a) DVS128; (b) a stream of events (upward and
downward spikes: positive and negative events); (c) image-like visualisation of accumulated
events within a time interval (white and black: positive and negative events). From (H. Kim,
2014)].