Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
arXiv:1606.05830 · doi:10.1109/TRO.2016.2624754
Abstract
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. 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?
References in corpus (2)
Cited by in corpus (203)
- ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
- Event-based Vision: A Survey
- DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
- SuMa++: Efficient LiDAR-based Semantic SLAM
- Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection
- Deep Drone Racing: From Simulation to Reality with Domain Randomization
- SegMap: Segment-based mapping and localization using data-driven descriptors
- Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment
- Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
- Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems
- The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection
- Keyframe-based monocular SLAM: design, survey, and future directions
- Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
- Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
- VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change
- Agilicious: Open-Source and Open-Hardware Agile Quadrotor for Vision-Based Flight
- A review of laser scanning for geological and geotechnical applications in underground mining
- Event-aided Direct Sparse Odometry
- AQUALOC: An Underwater Dataset for Visual-Inertial-Pressure Localization
- Visual SLAM: What are the Current Trends and What to Expect?
- The Hilti SLAM Challenge Dataset
- Human Intention Estimation based on Hidden Markov Model Motion Validation for Safe Flexible Robotized Warehouses
- A Survey of Robotic Harvesting Systems and Enabling Technologies
- Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas
- Dynamic Object Aware LiDAR SLAM based on Automatic Generation of Training Data
- Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
- Local Feature Matching Using Deep Learning: A Survey
- Gaussian Process Autonomous Mapping and Exploration for Range Sensing Mobile Robots
- Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps
- Autonomous Aerial Delivery Vehicles, a Survey of Techniques on how Aerial Package Delivery is Achieved
- Closed-form Preintegration Methods for Graph-based Visual-Inertial Navigation
- AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System
- DCL-SLAM: A Distributed Collaborative LiDAR SLAM Framework for a Robotic Swarm
- Active Learning in Robotics: A Review of Control Principles
- maplab 2.0 -- A Modular and Multi-Modal Mapping Framework
- AirDOS: Dynamic SLAM benefits from Articulated Objects
- From SLAM to Situational Awareness: Challenges and Survey
- Active SLAM: A Review On Last Decade
- Event-based Gesture Recognition with Dynamic Background Suppression using Smartphone Computational Capabilities
- Efficient LiDAR Odometry for Autonomous Driving
- AirVO: An Illumination-Robust Point-Line Visual Odometry
- BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments
- TwistSLAM: Constrained SLAM in Dynamic Environment
- DPC-Net: Deep Pose Correction for Visual Localization
- GenZ-ICP: Generalizable and Degeneracy-Robust LiDAR Odometry Using an Adaptive Weighting
- Edge SLAM: Edge Points Based Monocular Visual SLAM
- Navigating the Landscape for Real-time Localisation and Mapping for Robotics and Virtual and Augmented Reality
- MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
- Sensors, SLAM and Long-term Autonomy: A Review
- GICI-LIB: A GNSS/INS/Camera Integrated Navigation Library
- CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization
- Redesigning SLAM for Arbitrary Multi-Camera Systems
- Autonomous Navigation of MAVs in Unknown Cluttered Environments
- LiDAR-Based Place Recognition For Autonomous Driving: A Survey
- Globally-Optimal Contrast Maximisation for Event Cameras
- Brno Urban Dataset -- The New Data for Self-Driving Agents and Mapping Tasks
- Season-invariant GNSS-denied visual localization for UAVs
- 3D Multi-Robot Patrolling with a Two-Level Coordination Strategy
- IDOL: A Framework for IMU-DVS Odometry using Lines
- iRotate: Active Visual SLAM for Omnidirectional Robots
- A Geometric Nonlinear Stochastic Filter for Simultaneous Localization and Mapping
- Experimental Evaluation of Visual-Inertial Odometry Systems for Arable Farming
- LIDAR-based Stabilization, Navigation and Localization for UAVs Operating in Dark Indoor Environments
- OpenStreetMap-based Autonomous Navigation With LiDAR Naive-Valley-Path Obstacle Avoidance
- Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry
- Accurate Monocular Visual-inertial SLAM using a Map-assisted EKF Approach
- Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments
- Globally-Optimal Event Camera Motion Estimation
- LSVL: Large-scale season-invariant visual localization for UAVs
- Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results
- iSLAM: Imperative SLAM
- Efficient Decentralized Visual Place Recognition From Full-Image Descriptors
- ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization
- Joint Beam Management and SLAM for mmWave Communication Systems
- Minimization of GNSS-Denied Inertial Navigation Errors for Fixed Wing Autonomous Unmanned Air Vehicles
- How to Train a CAT: Learning Canonical Appearance Transformations for Direct Visual Localization Under Illumination Change
- Three dimensional unique identifier based automated georeferencing and coregistration of point clouds in underground environment
- Fast Autonomous Robotic Exploration Using the Underlying Graph Structure
- GNSS-denied geolocalization of UAVs by visual matching of onboard camera images with orthophotos
- Nonlinear Filter for Simultaneous Localization and Mapping on a Matrix Lie Group using IMU and Feature Measurements
- Active Rendezvous for Multi-Robot Pose Graph Optimization using Sensing over Wi-Fi
- Guaranteed Performance Nonlinear Observer for Simultaneous Localization and Mapping
- Distributed Consistent Multi-Robot Semantic Localization and Mapping
- Constructive Observer Design for Visual Simultaneous Localisation and Mapping
- Learning-Based Framework for Camera Calibration with Distortion Correction and High Precision Feature Detection
- Self-Supervised Deep Pose Corrections for Robust Visual Odometry
- Sparse Pose Graph Optimization in Cycle Space
- How to Evaluate Proving Grounds for Self-Driving? A Quantitative Approach
- GNSS-stereo-inertial SLAM for arable farming
- Sky-GVINS: a Sky-segmentation Aided GNSS-Visual-Inertial System for Robust Navigation in Urban Canyons
- Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
- SLAM for Visually Impaired People: a Survey
- Blind as a bat: audible echolocation on small robots
- HE-SLAM: a Stereo SLAM System Based on Histogram Equalization and ORB Features
- Robust Vehicle Positioning based on Multi-Epoch and Multi-Antenna TOAs in Harsh Environments
- On Incremental Structure-from-Motion using Lines
- Improving Self-Consistency in Underwater Mapping Through Laser-Based Loop Closure (Extended)
- Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference
- CAE-RLSM: Consistent and Efficient Redundant Line Segment Merging for Online Feature Map Building
- Factor Graph-Based Smoothing Without Matrix Inversion for Highly Precise Localization
- Applications of Spiking Neural Networks in Visual Place Recognition
- An Equivariant Observer Design for Visual Localisation and Mapping
- OROS: Online Operation and Orchestration of Collaborative Robots using 5G
- Online Object-Oriented Semantic Mapping and Map Updating
- Multiple Hypothesis Semantic Mapping for Robust Data Association
- Virtual Borders: Accurate Definition of a Mobile Robot's Workspace Using Augmented Reality
- Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review
- Certifiably Correct Range-Aided SLAM
- A 5-Point Minimal Solver for Event Camera Relative Motion Estimation
- A flexible framework for accurate LiDAR odometry, map manipulation, and localization
- ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality
- A Radio-Inertial Localization and Tracking System with BLE Beacons Prior Maps
- Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines
- AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning
- Autonomous adaptive noise characterization in quantum computers
- Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy
- Rao-Blackwellized Particle Smoothing for Simultaneous Localization and Mapping
- RGB-D Odometry and SLAM
- Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition
- Mapping While Following: 2D LiDAR SLAM in Indoor Dynamic Environments with a Person Tracker
- Image-Based Trajectory Tracking through Unknown Environments without Absolute Positioning
- An Addendum to NeBula: Towards Extending TEAM CoSTAR's Solution to Larger Scale Environments
- ORBBuf: A Robust Buffering Method for Remote Visual SLAM
- An N-Point Linear Solver for Line and Motion Estimation with Event Cameras
- ES-PTAM: Event-based Stereo Parallel Tracking and Mapping
- Marker-based Visual SLAM leveraging Hierarchical Representations
- A Framework for Interactive Teaching of Virtual Borders to Mobile Robots
- Localization and Mapping using Instance-specific Mesh Models
- A Deep Learning Approach to Identify Rock Bolts in Complex 3D Point Clouds of Underground Mines Captured Using Mobile Laser Scanners
- Modern Microscopy with the Web of Things: The OpenFlexure Microscope Software Stack
- Act, Perceive, and Plan in Belief Space for Robot Localization
- Enough is Enough: Towards Autonomous Uncertainty-driven Stopping Criteria
- Map Point Selection for Visual SLAM
- An Adaptive Graduated Nonconvexity Loss Function for Robust Nonlinear Least Squares Solutions
- G-Loc: Tightly-coupled Graph Localization with Prior Topo-metric Information
- Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
- Boosting Performance of a Baseline Visual Place Recognition Technique by Predicting the Maximally Complementary Technique
- 3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances
- GNSS-Denied Semi Direct Visual Navigation for Autonomous UAVs Aided by PI-Inspired Inertial Priors
- Geo-Localization Based on Dynamically Weighted Factor-Graph
- Exploratory State Representation Learning
- Active Visual SLAM with Independently Rotating Camera
- HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
- Learning to Segment Dynamic Objects using SLAM Outliers
- Multi-Robot Decentralized Collaborative SLAM in Planetary Analogue Environments: Dataset, Challenges, and Lessons Learned
- Long Distance GNSS-Denied Visual Inertial Navigation for Autonomous Fixed Wing Unmanned Air Vehicles: SO(3) Manifold Filter based on Virtual Vision Sensor
- Robust Self-Tuning Data Association for Geo-Referencing Using Lane Markings
- Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios
- Occupancy-SLAM: An Efficient and Robust Algorithm for Simultaneously Optimizing Robot Poses and Occupancy Map
- DA-LMR: A Robust Lane Marking Representation for Data Association
- From Underground Mines to Offices: A Versatile and Robust Framework for Range-Inertial SLAM
- SUPER ODOMETRY 2.0: Resilient Odometry via Hierarchical Adaptation
- Efficient Computation of Map-scale Continuous Mutual Information on Chip in Real Time
- Guided Navigation from Multiple Viewpoints using Qualitative Spatial Reasoning
- Sparse 3D Point-cloud Map Upsampling and Noise Removal as a vSLAM Post-processing Step: Experimental Evaluation
- Adaptive filtering of projective quantum measurements using discrete stochastic methods
- Online Robust Sliding-Windowed LiDAR SLAM in Natural Environments
- KernelGPA: A Globally Optimal Solution to Deformable SLAM in Closed-form
- 3-D Relative Localization for Multi-Robot Systems with Angle and Self-Displacement Measurements
- AscDAMs: Advanced SLAM-based channel detection and mapping system
- Cluster on Wheels
- Guess the Drift with LOP-UKF: LiDAR Odometry and Pacejka Model for Real-Time Racecar Sideslip Estimation
- A New Tightly-Coupled Dual-VIO for a Mobile Manipulator With Dynamic Locomotion
- A bundle framework for observer design on smooth manifolds with symmetry
- Active Digital Twins via Active Inference
- Learning Camera Performance Models for Active Multi-Camera Visual Teach and Repeat
- Event-based Photometric Bundle Adjustment
- iKap: Kinematics-aware Planning with Imperative Learning
- Digital Twin based Automatic Reconfiguration of Robotic Systems in Smart Environments
- Characterizing Lidar Point-Cloud Adversities Using a Vector Field Visualization
- Landmark Stereo Dataset for Landmark Recognition and Moving Node Localization in a Non-GPS Battlefield Environment
- Loss Regularizing Robotic Terrain Classification
- Towards High-Definition Maps: a Framework Leveraging Semantic Segmentation to Improve NDT Map Compression and Descriptivity
- Towards Automated Key-Point Detection in Images with Partial Pool View
- Understanding why SLAM algorithms fail in modern indoor environments
- TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image
- TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning
- 3D Reconstruction by Looking: Instantaneous Blind Spot Detector for Indoor SLAM through Mixed Reality
- RSV-SLAM: Toward Real-Time Semantic Visual SLAM in Indoor Dynamic Environments
- Energy-Efficient SLAM via Joint Design of Sensing, Communication, and Exploration Speed
- TivNe-SLAM: Dynamic Mapping and Tracking via Time-Varying Neural Radiance Fields
- A Novel ViDAR Device With Visual Inertial Encoder Odometry and Reinforcement Learning-Based Active SLAM Method
- PODDP: Partially Observable Differential Dynamic Programming for Latent Belief Space Planning
- Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention
- Visual SLAM-based Localization and Navigation for Service Robots: The Pepper Case
- Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning
- InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation
- SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation
- Addressing the challenges of loop detection in agricultural environments
- UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM
- IPC: Incremental Probabilistic Consensus-based Consistent Set Maximization for SLAM Backends
- Event-based Mosaicing Bundle Adjustment
- Mobile Robot Exploration Without Maps via Out-of-Distribution Deep Reinforcement Learning
- Map as a By-product: Collective Landmark Mapping from IMU Data and User-provided Texts in Situated Tasks
- Guessing human intentions to avoid dangerous situations in caregiving robots
- Improved Bag-of-Words Image Retrieval with Geometric Constraints for Ground Texture Localization
- Robotic Template Library
- BIM-Loc: BIM-Integrated Discrepancy-Aware LiDAR-based Indoor Localization
- Concept-Guided Exploration: Building Persistent, Actionable Scene Graphs
- LAMP: Implicit Language Map for Robot Navigation
- The SLAM Confidence Trap
- MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization
- 3D Foundation Model-Based Loop Closing for Decentralized Collaborative SLAM