• Corpus ID: 2092191

KLD-Sampling: Adaptive Particle Filters and Mobile Robot Localization

@inproceedings{Fox2001KLDSamplingAP,
  title={KLD-Sampling: Adaptive Particle Filters and Mobile Robot Localization},
  author={Dieter Fox},
  booktitle={NIPS 2001},
  year={2001}
}
  • D. Fox
  • Published in NIPS 2001
  • Computer Science
We present a statistical approach to adapting the sample set size of particle filters on-thefly. [] Key Result Extensive experiments using mobile robot localization as a test application show that our approach yields drastic imp rovements over particle filters with fixed sample set sizes and over a previously introduced adapt tion technique.

Figures and Tables from this paper

A Multi Swarm Particle Filter for Mobile Robot Localization
TLDR
A novel multi swarm particle filter moves the samples towards region of the state space where the likelihood is significant, without allowing them to go far away from the region of significant values for the proposed distribution.
Monte Carlo multi-robot localization based on grid cells and characteristic particles
TLDR
A Monte Carlo method based approach for multi-robot localization is described, where grid cells are used to describe the whole particle set which is used in MCL method to estimate the pose of robot.
Corrective Gradient Refinement for mobile robot localization
TLDR
This work develops an observation model for mobile robot localization using point cloud sensors (LIDAR and depth cameras) with vector maps and introduces the Corrective Gradient Refinement (CGR) algorithm that uses the state space gradients of the observation model to improve accuracy while maintaining low computational requirements.
Real-time particle filters
TLDR
This paper presents real-time particle filters, which make use of all sensor information even when the filter update rate is below the update rate of the sensors.
Real-time Particle Filters Using Mixtures of Samples Sets
TLDR
This paper presents a real time particle filter that makes use of all sensor information by partitioning sample sets into mixtures of smaller sample sets and determines the mixture weights so as to minimize the KL-divergence between the mixture density and the true posterior.
An experimental comparison of localization methods continued
TLDR
Experimental evidence is given that a combination of Markov localization and Kalman filtering as well as a variant of MCL outperform the other methods in terms of accuracy, robustness, and time needed for recovering from manual robot displacement, while requiring only few computational resources.
Vision-based extended Monte Carlo localization for mobile robot
TLDR
Vision-based extended MCL is realized that is applied to a networked robotic system, in which Bayesian networks are introduced to recognize polyhedron features in office environments for localization.
Localization and navigation of the CoBots over long-term deployments
TLDR
The Corrective Gradient Refinement (CGR) algorithm is presented, which refines the proposal distribution of the particle filter used for localization with sensor observations using analytically computed state space derivatives on a vector map.
A Biologically Inspired Global Localization System for Mobile Robots Using LiDAR Sensor
TLDR
A biologically-inspired global localization system using a LiDAR sensor that utilizes a hippocampal model and a landmark-based re-localization approach and demonstrates the high accuracy, applicability, and reliability of the proposed biologicallyinspired localization system in different localization scenarios.
Lightweight Particle Filters Based Localization Algorithm for Mobile Sensor Networks
  • Lian Li, Yan Liu, Limin Sun, Jian Ma
  • Computer Science
    2008 Second International Conference on Sensor Technologies and Applications (sensorcomm 2008)
  • 2008
TLDR
An improved and optimized particle filter algorithm was put forward in this paper, named as lightweight particle filters (LPF), which overcomes the limitations of the particle filters and provides high localization rate and precision.
...
...

References

SHOWING 1-10 OF 30 REFERENCES
Monte Carlo Localization: Efficient Position Estimation for Mobile Robots
TLDR
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.
Tracking multiple moving targets with a mobile robot using particle filters and statistical data association
TLDR
A sample-based variant of joint probabilistic data association filters is introduced to track features originating from individual objects and to solve the correspondence problem between the detected features and the filters.
Feature based CONDENSATION for mobile robot localization
  • P. Jensfelt, D. Austin, O. Wijk, M. Andersson
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
TLDR
This paper presents a comparison of four different feature types: sonar based triangulation points and point pairs, as well as lines and doors extracted using a laser scanner, and some general guidelines are drawn for determining good feature types.
Markov Localization for Mobile Robots in Dynamic Environments
TLDR
A version of Markov localization which provides accurate position estimates and which is tailored towards dynamic environments, and includes a filtering technique which allows a mobile robot to reliably estimate its position even in densely populated environments in which crowds of people block the robot's sensors for extended periods of time.
Using the CONDENSATION algorithm for robust, vision-based mobile robot localization
TLDR
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.
Sensor resetting localization for poorly modelled mobile robots
  • S. Lenser, M. Veloso
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
TLDR
A new localization algorithm, called sensor resetting localization, which is an extension of Monte Carlo localization, is presented, which has been successfully used on autonomous legged robots in the Sony legged league of the robotic soccer competition RoboCup'99.
Particle Filters for Mobile Robot Localization
This chapter investigates the utility of particle filters in the context of mobile robotics. In particular, we report results of applying particle filters to the problem of mobile robot localization,
Navigating Mobile Robots: Systems and Techniques
This is a survey of the state-of-the-art in sensors, systems, methods and technologies utilized by a mobile robot to determine its position in the environment. The many potential "solutions" are
Filtering via Simulation: Auxiliary Particle Filters
This article analyses the recently suggested particle approach to filtering time series. We suggest that the algorithm is not robust to outliers for two reasons: the design of the simulators and the
Particle methods for Bayesian modeling and enhancement of speech signals
TLDR
On-line estimation of the clean speech and model parameters and the adequacy of the chosen statistical models are performed and it is shown how model adequacy may be determined by combining the particle filter with frequentist methods.
...
...