Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
By César Cadena, Luca Carlone, Henry Carrillo, Yasir Latif, Davide Scaramuzza, José Neira, Ian David Reid, John J. Leonard. 2016
3,487 citations recorded by the source corpus.
Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors' take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?
Subfields: Aerospace Engineering, Computer Networks and Communications, Electrical and Electronic Engineering, 3D Vision & Pose, Robotics & Control
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Vladlen Koltun
- Davide Scaramuzza
- Abhinav Kumar Gupta
- Andrew J. Davison
- Jitendra Malik
- Luca Carlone
- Daniel Cremers
- Marc Pollefeys
In Computer Networks and Communications
- Khaled Ben Letaief
- Jun Zhang
- Yuanming Shi
- Luca Carlone
- Abhinav Kumar Gupta
- Lei Tai
- Jitendra Malik
- Jianmin Lu
In Electrical and Electronic Engineering
- Davide Scaramuzza
- Andrew J. Davison
- Michael Kaess
- Vladlen Koltun
- Guillermo Gallego
- René Ranftl
- Guoquan Huang
- Tobi Delbruck
In 3D Vision & Pose
- Jitendra Malik
- Vladlen Koltun
- Matthias Nießner
- Abhinav Kumar Gupta
- Leonidas J. Guibas
- Marc Pollefeys
- Andreas Geiger
- Manolis Savva
In Robotics & Control
- Vladlen Koltun
- Abhinav Kumar Gupta
- Roozbeh Mottaghi
- Jitendra Malik
- Saurabh Gupta
- Devendra Singh Chaplot
- Luca Weihs
- Davide Scaramuzza
Citations in the corpus
- A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “ision-making policy or control strategy should be realized effectively and efficiently. For example, the navigation for mobile robots with rational motion and coarse precision is considered as solved (Cadena et al., 2016). However, in challenging environments or with high expectation on the precision”
- A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “SLAM is very well-studied [75], but the purely geometric approach has room for improvements.”
- Deep Drone Racing: Learning Agile Flight in Dynamic Environments (2018, background): “Simultaneous Localization and Mapping (SLAM) systems [3] can provide accurate pose estimates against a previously-generated, globally-consistent map.”
- The limits and potentials of deep learning for robotics (2018, neutral): “As an extension of reasoning over individual objects, inference over the geometry of the whole scene is important for robotic vision, and closely related to the problems of object-based mapping or object-based SLAM [19], [86], [98], [114].”
- On Evaluation of Embodied Navigation Agents (2018, background): “There is also a rich and informative body of work on Si-The Si-The authors are listed in alphabetical order. multaneous Localization and Mapping (SLAM) [6], which focuses on building a map of the environment and localizing the agent within the map.”
- Semi-parametric Topological Memory for Navigation (2018, methodology): “Particularly relevant to our work are vision-based simultaneous localization and mapping (SLAM) methods (Cadena et al., 2016).”
- A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers (2022, methodology): “This problem has attracted significant attention from the robotics community in the last decades; see [3], [4], [5] and the references therein.”
- Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “Many classical robotics problems, like SLAM (Cadena et al., 2016) and visual place recognition (Lowry et al., 2016) begin to explore the possible breakthrough motivated by deep-learning.”
- Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, neutral): “in [8] where the SLAM topic is reviewed as a whole.”
- Navigation and planning in latent maps (2018, methodology): “We refer the interested reader to the survey of (Cadena et al., 2016), which contains a thorough review of the relevant publications and methods.”
- Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping (2019, methodology): “Contrary to related efforts targeting visual-inertial odometry (VIO) and SLAM, we combine visual-inertial SLAM, mesh reconstruction, and semantic understanding.”
- Factor Graphs for Robot Perception (2017, background): “A general overview of the area of SLAM can be found in [19, 59, 6, 187, 186].”
- Using Inertial Sensors for Position and Orientation Estimation (2017, neutral): “the tutorial papers [32, 5] or [20] for a more recent overview.”
- LDSO: Direct Sparse Odometry with Loop Closure (2018, background): “Simultaneous Localization and Mapping (SLAM) has been an active research area in computer vision and robotics for several decades since the 1980s [2], [3].”
- Deep Visual Teach and Repeat on Path Networks (2018, background): “A comprehensive overview of SLAM methods is outside the scope of this work, we direct the reader to an introductory text [34] or an overview of the state of the art [5].”
- Mobile Edge Intelligence and Computing for the Internet of Vehicles (2019, background): “the simultaneous estimation of the state of a vehicle and the construction of a map of the environment [65], [66], [67], [68].”