Mind the map! Accounting for existing map information when estimating online HDMaps from sensor
This work addresses the high cost of acquiring and maintaining HDMaps for autonomous driving, offering a domain-specific incremental improvement by leveraging existing maps.
The paper tackles the problem of estimating high-definition maps (HDMaps) for autonomous driving by incorporating existing map information, which is often overlooked, and introduces MapEX, a framework that improves map estimation by 38% over its base model and 8% over the state-of-the-art on the nuScenes dataset.
While HDMaps are a crucial component of autonomous driving, they are expensive to acquire and maintain. Estimating these maps from sensors therefore promises to significantly lighten costs. These estimations however overlook existing HDMaps, with current methods at most geolocalizing low quality maps or considering a general database of known maps. In this paper, we propose to account for existing maps of the precise situation studied when estimating HDMaps. We identify 3 reasonable types of useful existing maps (minimalist, noisy, and outdated). We also introduce MapEX, a novel online HDMap estimation framework that accounts for existing maps. MapEX achieves this by encoding map elements into query tokens and by refining the matching algorithm used to train classic query based map estimation models. We demonstrate that MapEX brings significant improvements on the nuScenes dataset. For instance, MapEX - given noisy maps - improves by 38% over the MapTRv2 detector it is based on and by 8% over the current SOTA.