Markov Localization for Mobile Robots in Dynamic Environments

  title={Markov Localization for Mobile Robots in Dynamic Environments},
  author={Wolfram Burgard and Dieter Fox and Sebastian Thrun},
Localization, that is the estimation of a robot's location from sensor data, is a fundamental problem in mobile robotics. This papers presents a version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments. The key idea of Markov localization is to maintain a probability density over the space of all locations of a robot in its environment. Our approach represents this space metrically, using a fine-grained grid to approximate… 
Markov Localization for Reliable Robot Navigation and People Detection
This paper presents Markov localization as a technique for estimating the position of a mobile robot based on a fine-grained, metric discretization of the state space, which is able to incorporate raw sensor readings and does not require predefined landmarks.
Probabilistic Localization Methods for a Mobile Robot Navigation
A Markov localization is introduced, which represents a posterior density – robot’s belief – by arbitrary density over the whole pose space (X, Y, θ) as a result of probability representation, and produced many successes.
Approaches to Mobile Robot Localization in Indoor Environments
An extensively tested low-complexity, robust and accurate pose tracking method is presented which utilizes the minimalistic model in combination with a laser sensor, based on the ideas of Multiple Hypothesis Tracking.
Indoor mobile robot localization in dynamic and cluttered environments using artificial landmarks
A novel probabilistic method equipped with function approximation techniques which is able to appropriately model the data distribution in Markov localization by using the maximum statistical power, thereby making a sensibly accurate estimation of robot’s pose in extremely dynamic, cluttered indoors environments.
This thesis proposes a multiple-model approach to solve the problems of egomotion estimation and moving object detection jointly in a random sample consensus (RANSAC) paradigm and proposes the use of discriminative models to reason about the joint association between measurements.
Dynamic Maps in Monte Carlo Localization
This article presents a method for updating the map dynamically during the process of localization, without requiring a severe increase in running time.
Cooperative Distributed Sensors for Mobile Robot Localization
A probabilistic algorithm to collaborate distributed sensors for mobile robot localization using a sample-based version of Markov localization—Monte Carlo localization (MCL), capable of localizing mobile robot in an any-time fashion.
Robot localization in symmetric environment
This work presents an extension to the MCL algorithm when localizing in highly symmetrical environments; a situation where MCL is often unable to correctly track equally probable poses for the robot.
Simultaneous localization and mapping for navigation in realistic environments
This thesis presents a method for achieving more accurate navigation by using the architectural properties of most domestic environments, when the stochastic mapping algorithm can not be used due to poor quality sensor data.
Dynamic motion models in Monte Carlo Localization
A technique to process these motions and corrections and dynamically determine revised motion parameters that more accurately reflect the robot's motion is demonstrated.


Position Estimation for Mobile Robots in Dynamic Environments
Extensions to Markov localization algorithms enabling them to localize mobile robots even in densely populated environments are proposed and implemented, demonstrating that this approach is able to accurately estimate the robot's position in more than 98% of the cases even in such highly dynamic environments.
Integrating global position estimation and position tracking for mobile robots: the dynamic Markov localization approach
  • W. Burgard, Andrcas Derr, D. Fox, A. Cremers
  • Computer Science
    Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190)
  • 1998
The dynamic Markov localization technique is presented as a uniform approach to position estimation, able to globally estimate the position of the robot, to efficiently track its position whenever the robot's certainty is high, and to detect and recover from localization failures.
Active Markov localization for mobile robots
Fast Grid-Based Position TRacking for Mobile Robots
An application of position probability grids to position tracking and, in contrast to many other approaches, is not restricted to a fixed set of predefined features such as doors, openings or corridor junction types.
An experimental comparison of localization methods
This experimental study compares two methods for localization of indoor mobile robots: Markov localization, which uses a probability distribution across a grid of robot poses; and scan matching, which using Kalman filtering techniques based on matching sensor scans.
Estimating the Absolute Position of a Mobile Robot Using Position Probability Grids
The position probability grid approach to estimating the robot's absolute position and orientation in a metric model of the environment is described, designed to work with standard sensors and is independent of any knowledge about the starting point.
Using the CONDENSATION algorithm for robust, vision-based mobile robot localization
This paper presents a novel, vision-based localization method based on the CONDENSATION algorithm, a Bayesian filtering method that uses a sampling-based density representation to track the position of the camera platform rather than tracking an object in the scene.
Monte Carlo Localization: Efficient Position Estimation for Mobile Robots
Monte Carlo Localization is a version of Markov localization, a family of probabilistic approaches that have recently been applied with great practical success and yields improved accuracy while requiring an order of magnitude less computation when compared to previous approaches.
A Mobile Robot That Learns Its Place
A neural network can be used to allow a mobile robot to derive an accurate estimate of its location from noisy sonar sensors and noisy motion information, and the robot can learn the relationship between location and sonar readings without requiring an external supervision signal.
Markov Localization using Correlation
CBML (correlation-based ML) permits video-rate localization using dense range scans, dynamic map updates, and a more precise error model than ML.