VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry
share
Visual localization is one of the fundamental enablers of robot autonomy which has been mostly tackled using local feature-based pipelines that efficiently encode knowledge about the environment and the underlying geometrical constraints. Although deep learning based approaches have shown considerable robustness in the context of significant perceptual changes, repeating structures and textureless regions, their performance has been subpar in comparison to local feature-based pipelines. In this paper, we propose the novel VLocNet++ architecture that attempts to overcome this limitation by simultaneously embedding geometric and semantic knowledge of the world into the pose regression network. We adopt a multitask learning approach that exploits the inter-task relationship between learning semantics, regressing 6-DoF global pose and odometry, for the mutual benefit of each of these tasks. VLocNet++ incorporates the Geometric Consistency Loss function that utilizes the predicted motion from the odometry stream to enforce global consistency during pose regression. Furthermore, we propose a self-supervised warping technique that uses the relative motion to warp intermediate network representations in the segmentation stream for learning consistent semantics. In addition, we propose a novel adaptive weighted fusion layer to leverage inter and intra task dependencies based on region activations. Finally, we introduce a first-of-a-kind urban outdoor localization dataset with pixel-level semantic labels and multiple loops for training deep networks. Extensive experiments on the challenging indoor Microsoft 7-Scenes benchmark and our outdoor DeepLoc dataset demonstrate that our approach exceeds the state-of-the-art, outperforming local feature-based methods while exhibiting substantial robustness in challenging scenarios.
READ FULL TEXT