Abstract
An innovative neuro-evolutionary approach for mobile robot egomotion estimation with a 3D ToF camera is proposed. The system is composed of two main modules following a preprocessing step. The first module is a Neural Gas network that computes a Vector Quantization of the preprocessed camera 3D point cloud. The second module is an Evolution Strategy that estimates the robot motion parameters by performing a registration process, searching on the space of linear transformations, restricted to the translation and rotation, between the codebooks obtained for successive camera readings. The fitness function is the matching error between the predicted and the observed codebook corresponding to the next camera readings. In this paper, we report results of an implementation of this system tested on data from a real mobile robot, and provide several comparisons between our and other well-known registration algorithms.
Similar content being viewed by others
Notes
Those recorded datasets are available in our web site: http://www.ehu.es/ccwintco/index.php/Conjuntos_de_datos_3D.
References
Bentley JL (1975) Multidimensional binary search trees used for associative searching. Commun ACM 18(9):509–517
Besl PJ, McKay HD (1992) A method for registration of 3-D shapes. Pattern Anal Mach Intell IEEE Trans 14(2):239–256
Beyer H-G, Schwefel H-P (2002) Evolution strategies—a comprehensive introduction. Nat Comput 1(1):3–52
Chow CK, Tsui HT, Lee T (2004) Surface registration using a dynamic genetic algorithm. Pattern Recogn 37(1):105–117
Dissanayake G (2001) A solution to the simultaneous localization and map building (SLAM) problem. Robot Autom IEEE Trans 17(3):229–241
Guðmundsson SA, Larsen R, Ersbøll BK (2007) Robust pose estimation using the SwissRanger SR-3000 camera. In: Image analysis, volume 4522/2007 of lecture notes in computer science. Springer, pp 968–975
Kohonen T (2001) Self-organizing maps. Springer, Berlin
Lange R, Seitz P (2001) Solid-state time-of-flight range camera. IEEE J Quantum Electron 37(3):390–397
Martinetz TM, Berkovich SG, Schulten KJ (1993) ‘Neural-Gas’ network for vector quantization and its application to time-series prediction. Neural Netw IEEE Trans 4(4):558–569
Martinetz TM, Schulten KJ (1991) In: Proc international conference on artificial neural networks, chapter a neural-gas network learns topologies. North-Holland, Amsterdam, pp 397–402
Oggier T, Lehmann M, Kaufmannn R, Schweizer M, Richter M, Metzler P, Lang G, Lustenberger F, Blanc N (2003) An all-solid-state optical range camera for 3D-real-time imaging with sub-centimeter depth-resolution (SwissRanger). In: Proc SPIE, vol 5249. pp 634–545
Randy LH, Sue EH (2004) Practical genetic algorithms, 2nd edn. Wiley, Hoboken
Salvi J, Matabosch C, Fofi D, Forest J (2007) A review of recent range image registration methods with accuracy evaluation. Image Vis Comput 25(5):578–596
Thrun S (2002) Exploring artificial intelligence in the new millenium, chapter robotic mapping: a survey. Morgan Kaufmann, San Mateo
Vesanto J, Alhoniemi E, Himberg J, Kiviluoto K, Parviainen J (1999) Self-organizing map for data mining in matlab: the SOM toolbox. Simulation News Eur 25(54):54. http://www.cis.hut.fi/projects/somtoolbox/
Villaverde I, Echegoyen Z, Graña M (2009) Neuro-evolutive system for ego-motion estimation with a 3D camera. In: Köppen M (ed) Advances in neuro-information processing, vol 5506/2009 of lecture notes in computer sciences. Springer, pp 1021–1028
Villaverde I, Graña M (2008) A hybrid intelligent system for robot ego-motion estimation with a 3D camera. In: Corchado E, Abraham A, Pedrycz W (eds) Hybrid artificial intelligence systems, vol 5271 of lecture notes in artificial intelligence. Springer, pp 657–664
Ye C, Hegde G-PM (2009) Robust edge extraction for SwissRanger SR-3000 range images. In: Robotics and automation, 2009. ICRA ’09. IEEE international conference on, May, pp 2437–2442
Zinsser T, Schnidt H, Niermann J (2003) A refined ICP algorithm for robust 3-D correspondences estimation. In: International conference on image processing pp 695–698
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Villaverde, I., Graña, M. Neuro-evolutionary mobile robot egomotion estimation with a 3D ToF camera. Neural Comput & Applic 20, 345–354 (2011). https://doi.org/10.1007/s00521-010-0384-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-010-0384-6