Mind the map! Accounting for existing map information when estimating online HDMaps from sensor
arXiv:2311.10517
Abstract
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 We identify 3 reasonable types of useful existing maps (minimalist, noisy, and outdated).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.
arXiv comment23 pages, 4 figures, 6 tables
References in corpus (10)
- MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
- VectorMapNet: End-to-end Vectorized HD Map Learning
- OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
- Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
- HDMapNet: An Online HD Map Construction and Evaluation Framework
- MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
- LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints
- PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction
- Complementing Onboard Sensors with Satellite Map: A New Perspective for HD Map Construction
- Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?