Abstract
The implementation of a particle filter (PF) for vision-based bearing-only simultaneous localization and mapping (SLAM) of a mobile robot in an unstructured indoor environment is presented in this paper. Variations, using techniques from the genetic algorithm (GA), to standard PF procedures are proposed to alleviate the sample impoverishment problem. A monochrome CCD camera mounted on the robot is used as the measuring device and a measure on the image quality is incorporated into data association and PF update. Since the bearing-only measurement does not contain range information, we add a pseudo range to the measurement during landmark initialization as a hypothesised pair and the non-promising landmark is removed by a map management strategy. Simulation and experimental results from an implementation using real-life data acquired from a Pioneer robot are included to demonstrate the effectiveness of our approach.
Similar content being viewed by others
References
Arras, K.O., Tomatis, N., Siegwart, R.: Multisensor on-the-fly localisation using laser and vision. In: Proc. 2000 IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems, pp. 462–467, 2000
Bienvenue, A., Joannides, M., Berard, J., Fontenas, E., Francois, O.: Niching in Monte Carlo filtering algorithms. In: Proc. 5th Intl. Conf. on Artificial Evolution, Creusot, pp. 19–30, October 2001
Crowley, J.L.: Position estimation for a mobile robot using vision and odometry. In: Proc. 1992 IEEE Intl. Conf. on Robotics and Automation, Nice, pp. 2588–2593, May 1992
Davison, A.J.: SLAM with a single camera. In: SLAM/CML Workshop at ICRA 2002, pp. 11–15, May 2002
Deutscher, J., Davison, A., Reid, I.: Automatic partitioning of high dimensional search spaces associated with articulated body motion capture. In: Proc. 2001 IEEE Compt. Society Conf. on Comput. Vision and Pattern Recognition, pp. 669–676, December 2001
Dezert, J., Bar-Shalom, Y.: Joint probabilitic data association for autonomous navigation. IEEE Trans. Aerosp. Electron. Syst. 29(4), 1275–1285 (October 1993)
Dissanayake, G., Newman, P., Clark, S., Durrant-Whyte, H.F., Csorba, M.: A solution to the Simultaneous Localisation and Map Building (SLAM) problem. IEEE Trans. Robot. Autom. 17(3), 229–241 (June 2001)
Dissanayake, G., Williams, S.B., Durrant-Whyte, H.F., Bailey, T.: Map management for efficient Simultaneous Localisation and Mapping (SLAM). Auton. Robots 12, 267–286 (2002)
Fitzgibbons, T., Nobet, E.: Application of vision in simultaneous localization and mapping. In: Proc. 2001 Australian Conf. on Robotics and Automation, Sydney, pp. 121–127, November 2001
Ip, Y.L., Rad, A.B.: Incorporation of feature tracking into simultaneous localization and map building via sonar data. J. Intell. Robot. Syst. 39(2), 149–172 (February 2004)
Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc., F, Radar Signal Process. 140(2), 107–113 (April 1993)
Gordon, N.J.: Non-linear/non-Gaussian filtering and the bootstrap filter. In: IEE Colloquium on Non-linear Filters, 1–6 May 1994
Herrera, F., Lozano, M., Verdegay, J.L.: Tackling real-coded genetic algorithms: Operators and tools for behavioural analysis. Artif. Intell. Rev. 12(4), 265–319 (1998)
Higuchi, T.: Monte Carlo filter using the genetic algorithm operators. J. Stat. Comput. Simul. 59, 1–23 (1997)
Jeon, S.H., Kim, B.K.: Monocular-based position determination for indoor navigation of mobile robots. In: Proc. IASTED Intl. Conf. on Control and Applications, Banff, pp. 408–413, July 1999
Kwok, N.M., Fang, G., Zhou, W.: Evolutionary particle filter: Re-sampling from the genetic algorithm perspective. In: Proc. IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems, Edmonton, pp. 1053–1058, August 2005
Livatino, S., Madsen, C.B.: Optimization of robot self-localisation accuracy by automatic visual-landmark selection. In: Proc. SCIA99 11th Scandinavian Conf. on Image Analysis, Kangerlussnag, pp. 501–506, June 1999
Maksarov, D., Durrant-Whyte, H.: Mobile vehicle navigation in unknown environments: A multiple hypothesis approach. IEE Proc., Control Theory Appl. 142(4), (July 1995)
Meier, E.B., Ade, F.: Tracking cars in range images using the condensation algorithm. In: Proc. 1999 IEEE/IEEJ/JSAI Intl. Conf. on Intelligent Transportation Systems, pp. 129–134, October 1999
Mufioz, A.J., Gonzalez, J.: Two-dimensional landmark-based position estimation from a single image. In: Proc. 1998 IEEE Intl. Conf. on Robotics and Automation, Leuven, pp. 3709–3714, May 1998
Perez, J.A., Castellanos, J.A., Montiel, J.M.M., Neira, J., Tardos, J.D.: Continuous mobile robot localisation: Vision vs. laser. In: Proc. 1999 IEEE Intl. Conf. on Robotics and Automation, Detroit, pp. 2917–2923, May 1999
Wang, Z., Bovik, A.C.: A universal image quality index. IEEE Signal Process. Lett. 9(3), 81–84 (March 2002)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kwok, N.M., Rad, A.B. A Modified Particle Filter for Simultaneous Localization and Mapping. J Intell Robot Syst 46, 365–382 (2006). https://doi.org/10.1007/s10846-006-9066-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-006-9066-0