Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)(2021)

引用 24|浏览24
暂无评分
摘要
We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any human annotation. The annotation process is automated with the combination of simultaneous localization and mapping (SLAM) and ray-tracing algorithms. By performing multiple navigation sessions in the same environment, we are able to identify permanent structures, such as walls, and disentangle short-term and long-term movable objects, such as people and tables, respectively. New sessions can then be performed using a network trained to predict these semantic labels. We demonstrate the ability of our approach to improve itself over time, from one session to the next. With semantically filtered point clouds, our robot can navigate through more complex scenarios, which, when added to the training pool, help to improve our network predictions. We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
更多
查看译文
关键词
training pool,network predictions,common localization techniques,lidar segmentation,autonomous indoor navigation,self-supervised learning approach,semantic segmentation,lidar frames,deep point cloud segmentation architecture,human annotation,annotation process,SLAM,ray-tracing algorithms,multiple navigation sessions,permanent structures,disentangle short-term,long-term movable objects,new sessions,semantic labels,session,semantically filtered point clouds
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要