Journal
ROBOTICS RESEARCH, ISRR 2022
Volume 27, Issue -, Pages 19-35Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-25555-7_3
Keywords
-
Categories
Ask authors/readers for more resources
In this work, we propose CL-SLAM, a novel task that extends the concept of lifelong SLAM from a single dynamically changing environment to sequential deployments in several drastically differing environments. To address this task, we introduce CL-SLAM, which leverages a dual-network architecture to adapt to new environments and retain knowledge from previously visited environments. We compare CL-SLAM to learning-based and classical SLAM methods, and demonstrate the advantages of leveraging online data.
Robots operating in the open world encounter various different environments that can substantially differ from each other. This domain gap also poses a challenge for Simultaneous Localization and Mapping (SLAM) being one of the fundamental tasks for navigation. In particular, learning-based SLAM methods are known to generalize poorly to unseen environments hindering their general adoption. In this work, we introduce the novel task of continual SLAM extending the concept of lifelong SLAM from a single dynamically changing environment to sequential deployments in several drastically differing environments. To address this task, we propose CL-SLAM leveraging a dual-network architecture to both adapt to new environments and retain knowledge with respect to previously visited environments. We compare CL-SLAM to learning-based as well as classical SLAMmethods and showthe advantages of leveraging online data. We extensively evaluate CL-SLAM on three different datasets and demonstrate that it outperforms several baselines inspired by existing continual learning-based visual odometry methods. We make the code of our work publicly available at http://continualslam.cs.uni-freiburg.de.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available