Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimation

Robust localization in dense urban scenarios using a low-cost sensor setup and sparse HD maps is highly relevant for the current advances in autonomous driving, but remains a challenging topic in research. We present a novel monocular localization approach based on a sliding-window pose graph that leverages predicted uncertainties for increased precision and robustness against challenging scenarios and per-frame failures. To this end, we propose an efficient multi-task uncertainty-aware perception module, which covers semantic segmentation, as well as bounding box detection, to enable the localization of vehicles in sparse maps, containing only lane borders and traffic lights. Further, we design differentiable cost maps that are directly generated from the estimated uncertainties. This opens up the possibility to minimize the reprojection loss of amorphous map elements in an association-free and uncertainty-aware manner. Extensive evaluation on the Lyft 5 dataset shows that, despite the sparsity of the map, our approach enables robust and accurate 6D localization in challenging urban scenarios using only monocular camera images and vehicle odometry.

Authors

• Kürsat Petek
• Kshitij Sirohi
• Daniel Büscher
• Wolfram Burgard

Keywords

• Location awareness
• Uncertainty
• Costs
• Semantics
• Robot vision systems
• Estimation
• Multitasking
• Uncertainty Estimation
• Sparse Map
• Robust Localization
• Bounding Box
• Semantic Segmentation
• Traffic Light
• Prediction Uncertainty
• Challenging Scenarios
• Reprojection
• Urban Scenarios
• Perception Module
• Map Elements
• Root Mean Square Error
• Deep Learning
• Convolutional Neural Network
• Error Term
• Local System
• Object Detection
• Local Method
• Localizer
• Detection Head
• Aleatoric Uncertainty
• Bayesian Neural Network
• Single Pass
• Lane Markings
• Fisher Information
• Distance Map
• Matching Model
• Conjugate Prior