Learning to Localize Through Compressed Binary Maps
This work significantly reduces the storage requirements for localization maps, enabling the scaling of localization systems to larger environments for mobile robots and autonomous vehicles.
This paper addresses the challenge of large map storage in localization systems by learning a task-specific compression for map representations. This approach achieves a two orders of magnitude reduction in storage compared to general-purpose codecs like WebP, without compromising localization accuracy.
One of the main difficulties of scaling current localization systems to large environments is the on-board storage required for the maps. In this paper we propose to learn to compress the map representation such that it is optimal for the localization task. As a consequence, higher compression rates can be achieved without loss of localization accuracy when compared to standard coding schemes that optimize for reconstruction, thus ignoring the end task. Our experiments show that it is possible to learn a task-specific compression which reduces storage requirements by two orders of magnitude over general-purpose codecs such as WebP without sacrificing performance.