Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Appearance-based approach to hybrid metric-topological simultaneous localisation and mapping

© The Institution of Engineering and Technology
Received 17/04/2013, Accepted 20/01/2014, Revised 05/12/2013, Published 06/03/2014

In this study a unified framework to carry out the simultaneous localisation and mapping of a mobile robot combining metric and topological techniques is presented. The robot moves in a real indoor environment and the algorithm makes use of the information provided by an omnidirectional camera mounted on the robot and its internal odometry. The hybrid approach consists in constructing simultaneously two maps of the environment, one metric and other topological with relationships between them which are updated in each step. The robot goes through the environment to build up a map while continuously captures images. To build the topological map the most relevant information from the scenes is extracted using a global appearance descriptor. A new node is added to the map when the appearance between two images is sufficiently different. Also, the authors check if there is a loop closure with a previous node. At the same time, a metrical map of the environment is computed. With this aim, the authors estimate the position of the robot when it captures a new image using a Monte–Carlo algorithm. The authors show how it is possible to obtain a reasonable performance both in time and accuracy in an indoor environment, when the involved parameters are properly tuned.

Inspec keywords: Monte Carlo methods; robot vision; feature extraction; SLAM (robots); mobile robots; cameras

Other keywords: hybrid metric-topological simultaneous localisation and mapping; position estimation; internal odometry; indoor environment; loop closure; global appearance descriptor; appearance-based approach; scene extraction; Monte-Carlo algorithm; mobile robot; omnidirectional camera

Subjects: Monte Carlo methods; Computer vision and image processing techniques; Monte Carlo methods; Image sensors; Image recognition; Mobile robots

References

    1. 1)
      • 14. Montemerlo, M., Thrun, S.: ‘Simultaneous localization and mapping with unknown data association using FastSLAM’. Proc. of IEEE International Conference on Robotics and Automation, Taipei, Taiwan, 2003, vol. 2, pp. 1985–1991.
    2. 2)
    3. 3)
      • 29. Harris, C.G., Stephens, M.: ‘A combined corner and edge detector’. Proc. of Alvey Vision Conference, 1998, pp. 147–151.
    4. 4)
      • 49. Smith, A.F.M., Gelfand, A.E.: ‘Bayesian statistics without tears: a sampling-resampling perspective’, Am. Stat., 1992, 46, (2), pp. 84–88.
    5. 5)
      • 32. Pretto, A., Menegatti, E., Pagello, E., Jitsukawa, Y., Ueda, R., Arai, T.: ‘Toward image-based localization for AIBO using wavelet transform’. Proc. Artificial Intelligence and Human-Oriented Computing, Berlin, Heidelberg, 2007, pp. 831–838.
    6. 6)
      • 34. Rossi, F., Ranganathan, A., Dellaert, F., Menegatti, E.: ‘Toward topological localization with spherical Fourier transform and uncalibrated camera’. Proc. Int. Conf. on Simulation, Modeling and Programming for Autonomous Robots, Venice, Italy, 2008, pp. 319–330.
    7. 7)
    8. 8)
      • 24. Valgren, C., Lilienthal, A.: ‘SIFT, SURF and seasons: long-term outdoor localization using local features’. Proc. European Conf. on Mobile Robots, Freiburg, Germany, 2007, pp. 253–258.
    9. 9)
      • 36. Amorós, F., Payá, L., Reinoso, Ó., Fernández, L., Marín, J.M.: ‘Visual map building and localization with an appearance-based approach. Comparisons of techniques to extract information of panoramic images’. Proc. Int. Conf. on Informatics in Control, Automation and Robotics, Madeira, Portugal, 2010, pp. 423–426.
    10. 10)
      • 17. Gil, A., Reinoso, O., Pay, L., Ballesta, M., Pedrero, J.: ‘Managing data association in visual SLAM using SIFT features’, International Journal of Factory Automation, Robotics and Soft Computing, 2007, 1, pp. 179–184.
    11. 11)
      • 27. Barfoot, T.D.: ‘Online Visual Motion Estimation using FastSLAM with SIFT Features’. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems. Edmonton, s, 2005, pp. 579–585.
    12. 12)
      • 30. Jogan, M., Leonardis, A.: ‘Robust localization using eigenspace of spinning-images’. Proc. IEEE Workshop on Omnidirectional Vision. Hilton Head Island, USA, 2000, pp. 37–44.
    13. 13)
      • 43. Gonzalez, R., Wintz, P.: ‘Digital image processing’ (Addison, 1987).
    14. 14)
      • 45. Fernandez, L., Paya, L., Reinoso, O., Gil, A., Julia, M., Ballesta, M.: ‘Robust methods for robot localization under changing illumination conditions. Comparison of different filtering techniques’. Proc. Int. Conf. on Agents and Artificial Intelligence, Valencia, Spain, 2010, vol. 1, pp. 223–228.
    15. 15)
      • 5. Diosi, A., Kleeman, L.: ‘Advanced sonar and laser range finder fusion for simultaneous localization and mapping’. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 2, Sendai, Japan, 2004, pp. 1854–1859.
    16. 16)
      • 6. Angeli, A., Doncieux, S., Meyer, J., Filliat, D.: ‘Visual topological SLAM and global localization’. Proc. of IEEE International Conference on Robotics and Automation, Piscataway, NJ, USA, 2009, pp. 2029–2034.
    17. 17)
      • 52. Seber, G.: ‘Multivariate observations’ (Wiley Interscience, 1984).
    18. 18)
      • 1. Smith, R., Self, M., Cheeseman, P.: ‘A stochastic map for uncertain spatial relationships’. Proc. Fourth Int. Symp.. Cambridge, MA, USA, 1988, pp. 467–474..
    19. 19)
      • 18. Lui, W., Jarvis, R.: ‘A pure vision-based approach to topological SLAM’. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Taipei, Taiwan, 2010, pp. 3784–3791.
    20. 20)
    21. 21)
      • 9. Motard, E., Raducanu, B., Cadenat, V., Vitrià, J.: ‘Incremental on-line topological map learning for a visual homing application’. Proc. of IEEE International Conference on Robotics and Automation, 2007, pp. 2049–2054.
    22. 22)
      • 12. Blanco, J.L., Fernandez, J.A., Gonzalez, J.: ‘A new approach for large-scale localization and mapping: hybrid metric-topological SLAM’. Proc. of the IEEE International Conference on Robotics and Automation, 2007, pp. 2061–2067.
    23. 23)
      • 2. Tully, S., Moon, H., Kantor, G., Choset, H.: ‘Iterated filters for bearing-only SLAM’. Proc. IEEE Int. Conf. on Robotics and Automation (ICRA). Pasadena, California, USA, 2008, pp. 1442–1448.
    24. 24)
      • 11. Tully, S., Moon, H., Morales, D., Kantor, G., Choset, H.: ‘Hybrid localization using the hierarchical atlas’. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007, pp. 2857–2864.
    25. 25)
      • 37. Amorós, F., Payá, L., Reinoso, Ó., Jiménez, L.M.: ‘Comparison of global-appearance techniques applied to visual map building and localization’. Proc. Int. Conf. on Computer Vision Theory and Applications, Rome, Italy, 2012, vol. 2, pp. 395–398.
    26. 26)
    27. 27)
    28. 28)
      • 46. Valiente, D., Fernandez, L., Aparicio, A.G., Castello, L.P., Garcia, O.R.: ‘Visual Odometry through appearance and feature-based method with omnidirectional images’, J. Robot., 2012, 2012, pp. 13–0.
    29. 29)
    30. 30)
      • 47. Fox, D., Burgard, W., Thrun, S.: ‘Markov localization for mobile robots in dynamic environments’, J. Artif. Intell. Res., 1999, 11, pp. 391–427.
    31. 31)
      • 23. Murillo, A.C., Guerrero, J.J., Sagüés, C.: ‘SURF features for efficient robot localization with omnidirectional images’. Proc. IEEE Int. Conf. on Robotics and Automation, San Diego, CA, USA, 2007, pp. 3901–3907.
    32. 32)
      • 50. ROS. http://www.ros.org, 2012.
    33. 33)
    34. 34)
    35. 35)
    36. 36)
      • 20. Tully, S., Kantor, G., Choset, H., Werner, F.: ‘A multi-hypothesis topological SLAM approach for loop closing on edge-ordered graphs’. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Piscataway, NJ, USA, 2009, pp. 4943–4948.
    37. 37)
    38. 38)
      • 31. Paya, L., Fernandez, L., Reinoso, O., Gil, A., Ubeda, D.: ‘Appearance-based dense maps creation. Comparison of compression techniques with panoramic images’. Proc. Int. Conf. on Informatics in Control, Automation and Robotics, Milan, Italy, 2009, pp. 238–246.
    39. 39)
      • 28. Gil, A., Reinoso, O., Vicente, A., Fernández, C., Payá, L.: ‘Monte Carlo localization using SIFT features’. Pattern Recognition and Image Analysis, (3522> LCNS), 2005, pp. 623–630.
    40. 40)
      • 15. Hähnel, D., Burgard, W., Fox, D., Thrun, S.: ‘An efficient FastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements’. Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, NV, USA, 2003, pp. 206–211.
    41. 41)
      • 41. Wu, J., Christensen, H.I., Rehg, J.M.: ‘Visual place categorization: problem, dataset, and algorithm’. Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, St. Louis, USA, 2009, pp. 4763–4770.
    42. 42)
      • 51. Stachniss, C., Grisetti, G., Hähnel, D., Burgard, W.: ‘Improved Rao-Blackwellized mapping by adaptive sampling and active loop-closure’. Proc. Workshop on Self-Organization of Adaptive Behavior. Ilmenau, Germany, 2004, pp. 1–15.
    43. 43)
      • 42. Folkesson, J., Christensen, H.: ‘Outdoor exploration and SLAM using a compressed filter’. Proc. IEEE Int. Conf. on Robotics and Automation, Taipei, Taiwan, 2003, vol. 1, pp. 419–426.
    44. 44)
    45. 45)
    46. 46)
      • 8. Romero, A., Cazorla, M.: ‘Topological SLAM using omnidirectional images: merging feature detectors and graph-matching’, in: Blanc-Talon, J., Bone, D., Philips, W., Popescu, D., Scheunders, P., (Eds.), ‘Advanced concepts for intelligent vision systems’, (6474LNCS). Springer, Berlin, Heidelberg, 2010, pp. 464–475.
    47. 47)
    48. 48)
    49. 49)
    50. 50)
    51. 51)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2013.0086
Loading

Related content

content/journals/10.1049/iet-its.2013.0086
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address