Advances in Inference and Representation for Simultaneous Localization and Mapping
arXiv:2103.05041
Abstract
Simultaneous localization and mapping (SLAM) is the process of constructing a global model of an environment from local observations of it; this is a foundational capability for mobile robots, supporting such core functions as planning, navigation, and control. This article reviews recent progress in SLAM, focusing on advances in the expressive capacity of the environmental models used in SLAM systems (representation) and the performance of the algorithms used to estimate these models from data (inference). A prominent theme of recent SLAM research is the pursuit of environmental representations (including learned representations) that go beyond the classical attributes of geometry and appearance to model properties such as hierarchical organization, affordance, dynamics, and semantics; these advances equip autonomous agents with a more comprehensive understanding of the world, enabling more versatile and intelligent operation. A second major theme is a revitalized interest in the mathematical properties of the SLAM estimation problem itself (including its computational and information-theoretic performance limits); this work has led to the development of novel classes of certifiable and robust inference methods that dramatically improve the reliability of SLAM systems in real-world operation. We survey these advances with an emphasis on their ramifications for achieving robust, long-duration autonomy, and conclude with a discussion of open challenges and a perspective on future research directions.
30 pages, 4 figures. To appear in Annual Review of Control, Robotics, and Autonomous Systems 2021
References in corpus (19)
- End to End Learning for Self-Driving Cars
- Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection
- Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
- Neural SLAM: Learning to Explore with External Memory
- VDO-SLAM: A Visual Dynamic Object-aware SLAM System
- Cramér-Rao bounds for synchronization of rotations
- Toward Geometric Deep SLAM
- Learning Physical Graph Representations from Visual Scenes
- FutureMapping: The Computational Structure of Spatial AI Systems
- Self-Improving Visual Odometry
- Predictive and adaptive maps for long-term visual navigation in changing environments
- Distributed Certifiably Correct Pose-Graph Optimization
- Dual Quadrics from Object Detection BoundingBoxes as Landmark Representations in SLAM
- FutureMapping 2: Gaussian Belief Propagation for Spatial AI
- Generalized Proximal Methods for Pose Graph Optimization
- Block-Coordinate Minimization for Large SDPs with Block-Diagonal Constraints
- Dynamic SLAM: The Need For Speed
- gradSLAM: Automagically differentiable SLAM
- An observable time series based SLAM algorithm for deforming environment