T he simultaneous localization and mapping (SLAM) problem asks if it is possible for a mobile robot to be placed at an unknown location in an unknown environment and for the robot to incrementally build a consistent map of this environment while simultaneously determining its location within this map. A solution to the SLAM problem has been seen as a "holy grail" for the mobile robotics community as it would provide the means to make a robot truly autonomous.The "solution" of the SLAM problem has been one of the notable successes of the robotics community over the past decade. SLAM has been formulated and solved as a theoretical problem in a number of different forms. SLAM has also been implemented in a number of different domains from indoor robots to outdoor, underwater, and airborne systems. At a theoretical and conceptual level, SLAM can now be considered a solved problem. However, substantial issues remain in practically realizing more general SLAM solutions and notably in building and using perceptually rich maps as part of a SLAM algorithm.This two-part tutorial and survey of SLAM aims to provide a broad introduction to this rapidly growing field. Part I (this article) begins by providing a brief history of early developments in SLAM. The formulation section introduces the structure the SLAM problem in now standard Bayesian form, and explains the evolution of the SLAM process. The solution section describes the two key computational solutions to the SLAM problem through the use of the extended Kalman filter (EKF-SLAM) and through the use of Rao-Blackwellized particle filters (FastSLAM). Other recent solutions to the SLAM problem are discussed in Part II of this tutorial. The application section describes a number of important real-world implementations of SLAM and also highlights implementations where the sensor data and software are freely down-loadable for other researchers to study. Part II of this tutorial describes major issues in computation, convergence, and data association in SLAM. These are subjects that have been the main focus of the SLAM research community over the past five years. History of the SLAM ProblemThe genesis of the probabilistic SLAM problem occurred at the 1986 IEEE Robotics and Automation Conference held in San Francisco, California. This was a time when probabilistic methods were only just beginning to be introduced into both robotics and artificial intelligence (AI). A number of researchers had been looking at applying estimation-theoretic methods to mapping and localization problems; these included Peter Cheeseman, Jim Crowley, and Hugh DurrantWhyte. Over the course of the conference, many paper table cloths and napkins were filled with long discussions about consistent mapping. Along the way, Raja Chatila, Oliver Faugeras, Randal Smith, and others also made useful contributions to the conversation.The result of this conversation was a recognition that consistent probabilistic mapping was a fundamental problem in robotics with major conceptual and computational issues that ne...

This paper describes a new approach for generalizing the Kalman filter to nonlinear systems. A set of samples are used to parameterize the mean and covariance of a (not necessarily Gaussian) probability distribution. The method yields a filter that is more accurate than an extended Kalman filter (EKF) and easier to implement than an EKF or a Gauss second-order filter. Its effectiveness is demonstrated using an example.

The simultaneous localization and map building (SLAM) problem asks if it is possible for an autonomous vehicle to start in an unknown location in an unknown environment and then to incrementally build a map of this environment while simultaneously using this map to compute absolute vehicle location. Starting from the estimation-theoretic foundations of this problem developed in [1]-[3], this paper proves that a solution to the SLAM problem is indeed possible. The underlying structure of the SLAM problem is first elucidated. A proof that the estimated map converges monotonically to a relative map with zero uncertainty is then developed. It is then shown that the absolute accuracy of the map and the vehicle location reach a lower bound defined only by the initial vehicle uncertainty. Together, these results show that it is possible for an autonomous vehicle to start in an unknown location in an unknown environment and, using relative observations only, incrementally build a perfect map of the world and to compute simultaneously a bounded estimate of vehicle location. This paper also describes a substantial implementation of the SLAM algorithm on a vehicle operating in an outdoor environment using millimeter-wave (MMW) radar to provide relative map observations. This implementation is used to demonstrate how some key issues such as map management and data association can be handled in a practical environment. The results obtained are cross-compared with absolute locations of the map landmarks obtained by surveying. In conclusion, this paper discusses a number of key issues raised by the solution to the SLAM problem including suboptimal map-building algorithms and map management.