Estimating uncertain spatial relationships in robotics

By Randall Smith, Matthew Self, P. Cheeseman. 1986

In this paper, we describe a representation for spatial information, called the stochastic map, and associated procedures for building it, reading information from it, and revising it incrementally as new information is obtained. The map contains the estimates of relationships among objects in the map, and their uncertainties, given all the available information. The procedures provide a general solution to the problem of estimating uncertain relative spatial relationships. The estimates are probabilistic in nature, an advance over the previous, very conservative, worst-case approaches to the problem. Finally, the procedures are developed in the context of state-estimation and filtering theory, which provides a solid basis for numerous extensions.

Subfields: 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 Robotics & Control

Citations in the corpus

Simultaneous localization and mapping with unknown data association using FastSLAM (2003, methodology): “The dominant approach to the SLAM problem was introduced in a seminal paper by Smith, Self, and Cheeseman [13].”
Probabilistic Algorithms and the Interactive Museum Tour-Guide Robot Minerva (2000, methodology): “One popular family of approaches, known as SLAM algorithms [18, 19, 61, 62, 96], employs Kalman filters [54, 66] for concurrently estimating robot poses and maps.”
Probabilistic Algorithms in Robotics (2000, methodology): “Kalman filters have been applied with great success to a range of tracking and mapping problems in roboti cs [58, 83]; though they tend not to work well for global localization or the kidnapped robot problem.”
An Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics (2015, methodology): “SLAM approaches have been categorized into ﬁltering approaches (such as EKF-SLAM [106] and particle ﬁlter based SLAM [81]) and smoothing approaches (such as GraphSLAM [111], RGB-D SLAM [56], Smoothing and Mapping [30]).”
A Tutorial on Graph-Based SLAM (2010, background): “Frese et al. [8] propose a variant of Gauss-Seidel relaxation called multi-level relaxation (MLR).”
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks (2020, methodology): “Methods entailing structure-from-motion and SLAM [91,80,25,13,72,81] were used to build maps.”
Adapting the Sample Size in Particle Filters Through KLD-Sampling (2003, methodology): “Kalman filters are the most widely used variant of Bayes filters (Kalman 1960; Gelb 1974; Smith, Self, and Cheeseman 1990; Welch and Bishop 2001).”
Using laser range data for 3D SLAM in outdoor environments (2006, background): “Where the operator signifies the inverse transformation operator, as defined in [13], and xvi(k+1|k) and xvj(k+1|k) refer to the t = i and t = j vehicle poses in x(k + 1|k) respectively.”
Optimization of the simultaneous localization and map-building algorithm for real-time implementation (2001, background): “This problem is usually known as simultaneous localization and map building (SLAM) and was originally introduced in [7], [8].”
iSAM: Incremental Smoothing and Mapping (2008, methodology): “This is similar to the extended Kalman filter (EKF) approach to SLAM as pioneered by [12] but allows for iterating multiple”
Square Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing (2006, methodology): “As is standard in the SLAM literature (Smith et al. 1990; Leonard et al. 1992; Castellanos et al 1999; Dissanayake et al. 2001), we assume Gaussian process and measurement models (Maybeck 1979), defined by”
Simultaneous Localization and Mapping with Sparse Extended Information Filters (2004, methodology): “Today's most widely used on-line algorithms are based on the extended Kalman filter (EKF), whose application to SLAM problems was developed in a series of seminal papers (Smith and Cheeseman 1985; Moutarlier and Chatila 1989; Smith, Self, and Cheeseman 1990).”
A system for volumetric robotic mapping of abandoned mines (2003, background): “taneous localization and mapping , or SLAM, problem [10], [15], [20].”
EgoCom: A Multi-Person Multi-Modal Egocentric Communications Dataset (2020, background): “Instead, EgoCom is multi-disciplinary, combining synchronized multi-perspective, multi-modal communications data and egocentricity [19] with elements of conversational AI [20], natural language, audio, computer vision, and spatial AI [21].”
Unmanned aerial systems for photogrammetry and remote sensing: A review (2014, methodology): “…use of the corresponding images’ exterior orientation—we mention the related pioneering work in Grün (1985) on real-time bundle adjustment and the Simultaneous Localization and Mapping (SLAM) concept originated in the robotics community (Smith et al., 1986; Leonard and Durrant Whyte, 1991).”
Particle Filters in Robotics (2002, methodology): “This is achieved by modifying the importance factors As reported in [34], the Rao-Blackwellized particle ﬁl-ter large-scale SLAM problems, involving up to 100,000 dimensions.”
Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas Framework (2004, methodology): “The Kalman filter provides the optimal linear recursive solution to SLAM when certain assumptions hold, such as perfect data association, linear motion and measurement models, and Gaussian error models (Smith, Self, and Cheeseman 1990).”