Simultaneous localization and mapping: part I

By H. F. Durrant-Whyte, Tim Bailey. IEEE robotics & automation magazine, 2006

4,202 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/30f67b7275cec21a94be945dfe4beff08c7e004a

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

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments (2017, background): “Classical approaches, based on simultaneous localization and mapping (Durrant-Whyte and Bailey, 2006), are sensitive to noisy sensory input and changes in the environment.”
Benchmarking Classic and Learned Navigation in Complex 3D Environments (2019, methodology): “Most SLAM methods are based on metric maps [13, 8], although topological methods have been developed as well [15].”
Visual-Inertial Navigation: A Concise Review (2019, background): “…the location of the sensor platform and the features in the surrounding environment, SLAM estimators are able to easily incorporate loop closure constraints, thus enabling bounded localization errors, which has attracted signiﬁcant research efforts in the past three decades [16, 36, 93, 94].”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, background): “The location of ego-vehicle and landmarks are estimated online without any priori map information [331].”
Symbiotic human-robot collaborative assembly (2019, methodology): “Durrant-Whyte and Bailey [52] reported the SLAM solutions based on extended Kalman filter (EKF) and PF using vision system data.”
Unmanned Aircraft Capture and Control Via GPS Spoofing (2014, background): “…Meister, Schlaile, & Trommer, 2006), barometric altimeters (Kim and Sukkarieh, 2003), and electro-optical navigation systems based on exploratory simultaneous localization and mapping (SLAM) (Chowdhary et al., 2013; Durrant-Whyte and Bailey, 2006; Nuetzi, Weiss, Scaramuzza, & Siegwart, 2011).”
A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers (2022, methodology): “A similar approximation can be done for particle-filter SLAM, which represents the belief over robot trajectories as a set of particles [2], [3], [37].”
A Survey on 3D Gaussian Splatting (2024, critical): “…impressive real-time performance, it still suffers from the inherent limitations, including inefficient handling of highly-distorted cameras (crucial for robotics), secondary rays (for optical effects like reflections and shadows), and stochastic ray sampling (needed in various existing pipelines).”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, methodology): “To overcome those limitations, other localization strategies such using inertial measurement units (IMUs), GPS, LASER odometry and most recently Visual Odometry (VO) [88] and Simultaneous Localization and Mapping (SLAM) [36,38] methods have been proposed.”
Dense visual SLAM for RGB-D cameras (2013, methodology): “an extended Kalman filter [25], [26], and incrementally refine them.”
CENTRIST: A Visual Descriptor for Scene Categorization (2011, background): “Place recognition is an inherent part of a Simultaneous Localization and Map Building (SLAM) system [3], [4].”
Continuous 3D Perception Model with Persistent State (2025, neutral): “…traditional methods such as Structure from Motion (SfM) [1, 2, 28, 47, 65, 66, 70, 71, 80] and Simultaneous Localization and Mapping (SLAM) [11, 16, 19, 22, 37, 51, 53], as well as more recent approaches such as Neural Radiance Fields (NeRF) [12, 24, 49, 50, 84] and 3D Gaussian Splatting [36].”
A Random-Finite-Set Approach to Bayesian SLAM (2011, background): “In particular, it is argued that fundamentally, the map should be represented as a finite set, and thus, the concept of an RFS is required for a Bayesian SLAM formulation.”
Reset-free Trial-and-Error Learning for Robot Damage Recovery (2016, background): “The next step is to relax this assumption and let the robot discover its environment with a SLAM algorithm [68].”