Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition

Peng Yin, Lingyun Xu, Zhe Liu, Lu Li, Hadi Salman, Yuqing He, Weiliang Xu, Hesheng Wang, Howie ChosetIROS 2018 · OpenReview

Abstract

Place recognition is one of the major challenges for the LiDAR-based effective localization and mapping task. Traditional methods are usually relying on geometry matching to achieve place recognition, where a global geometry map need to be restored. In this paper, we accomplish the place recognition task based on an end-to-end feature learning framework with the LiDAR inputs. This method consists of two core modules, a dynamic octree mapping module that generates local 2D maps with the consideration of the robot's motion; and an unsupervised place feature learning module which is an improved adversarial feature learning network with additional assistance for the long-term place recognition requirement. More specially, in place feature learning, we present an additional Generative Adversarial Network with a designed Conditional Entropy Reduction module to stabilize the feature learning process in an unsupervised manner. We evaluate the proposed method on the Kitti dataset and North Campus Long-Term LiDAR dataset. Experimental results show that the proposed method outperforms state-of-the-art in place recognition tasks under long-term applications. What's more, the feature size and inference efficiency in the proposed method are applicable in real-time performance on practical robotic platforms.
BibTeX
@inproceedings{yin2018stabilize,
  author = {Peng Yin and Lingyun Xu and Zhe Liu and Lu Li and Hadi Salman and Yuqing He and Weiliang Xu and Hesheng Wang and Howie Choset},
  title = {{Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2018},
  url = {https://openreview.net/forum?id=dPR5XPQXDKV},
}

Loading related content...

Figure