Autonomous Robots

, 27:327 | Cite as

A collection of outdoor robotic datasets with centimeter-accuracy ground truth

  • Jose-Luis Blanco
  • Francisco-Angel Moreno
  • Javier Gonzalez


The lack of publicly accessible datasets with a reliable ground truth has prevented in the past a fair and coherent comparison of different methods proposed in the mobile robot Simultaneous Localization and Mapping (SLAM) literature. Providing such a ground truth becomes specially challenging in the case of visual SLAM, where the world model is 3-dimensional and the robot path is 6-dimensional. This work addresses both the practical and theoretical issues found while building a collection of six outdoor datasets. It is discussed how to estimate the 6-d vehicle path from readings of a set of three Real Time Kinematics (RTK) GPS receivers, as well as the associated uncertainty bounds that can be employed to evaluate the performance of SLAM methods. The vehicle was also equipped with several laser scanners, from which reference point clouds are built as a testbed for other algorithms such as segmentation or surface fitting. All the datasets, calibration information and associated software tools are available for download


Dataset Least squares GPS localization Ground truth SLAM 


  1. Besl, P. J., & McKay, N. D. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256. CrossRefGoogle Scholar
  2. Blanco, J. L. (2008). The Mobile Robot Programming Toolkit (MRPT) website. Google Scholar
  3. Bonarini, A., Migliore, D., Fontana, G., & Matteucci, M. (2009). The Raw Seeds project website. Google Scholar
  4. Borkowski, K. M. (1987). Transformation of geocentric to geodetic coordinates without approximations. Astrophysics and Space Science, 139(1), 1–4. zbMATHCrossRefGoogle Scholar
  5. Campbell, J., Sukthankar, R., Nourbakhsh, I., & Pahwa, A. (2005). A robust visual odometry and precipice detection system using consumer-grade monocular vision. In IEEE international conference on robotics and automation (pp. 3421–3427). Google Scholar
  6. Civera, J., Davison, A. J. & Montiel, J. M. M. (2008). Inverse depth parametrization for monocular SLAM. IEEE Transactions on Robotics, 24(5). Google Scholar
  7. Davison, A. J., Reid, I., Molton, N., & Stasse, O. (2007). MonoSLAM: real-time single camera SLAM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6). Google Scholar
  8. De Boor, C. (2001). A practical guide to splines. Berlin: Springer. zbMATHGoogle Scholar
  9. Drake, S. P. (2000). Converting GPS coordinates λ φ h to local coordinates enu. Google Scholar
  10. Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: part I. IEEE Robotics and Automation Magazine, 13(2), 99–110. CrossRefGoogle Scholar
  11. Guivant, J. E., & Nebot, E. M. (2001). Optimization of the simultaneous localization and map-building algorithm for real-time implementation. IEEE Transactions on Robotics and Automation, 17(3), 242–257. CrossRefGoogle Scholar
  12. Guivant, J., Nebot, E., Nieto, J., & Masson, F. (2004). Navigation and mapping in large unstructured environments. International Journal of Robotics Research, 23(4), 449–472. CrossRefGoogle Scholar
  13. Horn, B. K. P. (1987). Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America A, 4(4), 629–642. CrossRefMathSciNetGoogle Scholar
  14. Howard, A., & Roy, N. (2003). The robotics data set repository (radish). Google Scholar
  15. Kaess, M., Ranganathan, A., & Dellaert, F. (2007). Fast incremental square root information smoothing. In International joint conferences on artificial intelligence (IJCAI) (pp. 2129–2134). Google Scholar
  16. Leick, A. (2004). GPS satellite surveying. New York: Wiley. Google Scholar
  17. Marquardt, D. (1963). An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal of Applied Mathematics, 11(2), 431–441. zbMATHCrossRefMathSciNetGoogle Scholar
  18. Montemerlo, M. (2003). FastSLAM: a factored solution to the simultaneous localization and mapping problem with unknown data association. PhD thesis, University of Washington. Google Scholar
  19. Mor, J. J. (1977). The Levenberg-Marquardt algorithm: implementation and theory. In Lecture notes in mathematics (Vol. 630, pp. 105–116). Berlin: Springer. Google Scholar
  20. Nieto, J., Guivant, J., Nebot, E., & Thrun, S. (2003). Real time data association for FastSLAM. In IEEE/RSJ international conference on intelligent robots and systems (Vol. 1). Google Scholar
  21. Paz, L.M., Guivant, J., Tardós, J. D., & Neira, J. (2007). Data association in O(n) for divide and conquer SLAM. In Robotics: science and systems, RSS, Atlanta, GA, USA, June 2007. Google Scholar
  22. Smith, R., Self, M., & Cheeseman, P. (1988). A stochastic map for uncertain spatial relationships. In The fourth international symposium on robotics research (pp. 467–474). Google Scholar
  23. Walter, M., Eustice, R., & Leonard, J. (2004). A provably consistent method for imposing sparsity in feature-based SLAM information filters. In International symposium of robotics research (ISRR). Berlin: Springer. Google Scholar
  24. Zhang, Z. (2000). A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(11), 1330–1334. CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Jose-Luis Blanco
    • 1
  • Francisco-Angel Moreno
    • 1
  • Javier Gonzalez
    • 2
  1. 1.E.T.S.I. Informática, Lab. 2.3.6University of MálagaMálagaSpain
  2. 2.E.T.S.I. Informática, Office 2.2.30University of MálagaMálagaSpain

Personalised recommendations