Abstract
This paper presents Neuro-Evolutionary Optimization SLAM (NeoSLAM) a novel approach to SLAM that uses a neural network (NN) to autonomously learn both a nonlinear motion model and the noise statistics of measurement data. The NN is trained using evolutionary optimization to learn the residual error of the motion model, which is then added to the odometry data to obtain the full motion model estimate. Stochastic optimization is used, to accommodate any kind of cost function. Prediction and correction are performed simultaneously within our neural framework, which implicitly integrates the motion and sensor models. An evolutionary programming (EP) algorithm is used to progressively refine the neural model until it generates a trajectory that is most consistent with the actual sensor measurements. During this learning process, NeoSLAM does not require any prior knowledge of motion or sensor models and shows consistently good performance regardless of the robot and the sensor noise type. Furthermore, NeoSLAM does not require the data association step at loop closing which is crucial in most other SLAM algorithms, but can still generate an accurate map. Experiments in various complex environments with widely-varying types of noise show that the learning capability of NeoSLAM ensures performance that is consistently less sensitive to noise and more accurate than that of other SLAM methods.
Similar content being viewed by others
References
Dissanayake G, Newman P, Clark S, Durrant-Whyte HF, Csorba M (2001) A solution to the simultaneous localization and map building (SLAM) problem. IEEE Trans Robot Autom 17(3):229–241
Smith R, Self M, Cheeseman P (1988) A stochastic map for uncertain spatial relationships. In: Proc 4th int sym on robot res, pp 467–474
Newman P, Leonard J, Tardòs JD, Neira J (2002) Explore and return: Experimental validation of real-time concurrent mapping and localization. In: IEEE int conf robot autom, pp 1802–1809
Choi YH, Lee TK, SY Oh (2008) A line feature based SLAM with low grade range sensors using geometric constraints and active exploration for mobile robot. Auton Robot 24:13–27
Kim SH, SY Oh (2008) SLAM in indoor environments using omni-directional vertical and horizontal line features. J Intell Robot Syst 51:31–43
Guivant J, Nebot E (2001) Optimization of the simultaneous localization and map-building algorithm for real-time implementation. IEEE Trans Robot Autom 17(3):242–257
Newman PM, Leonard JJ (2003) Pure range-only subsea SLAM. In: Proc IEEE int conf robot autom, pp 1921–1926
Davison AJ (2003) Real-time simultaneous localization and mapping with a single camera. In: Proc int conf comput vis, pp 1403–1410
Se S, Lowe D, Little J (2002) Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks. Int J Robot Res 21(8):735–758
Jeong WY, Lee KM (2005) CV-SLAM: a new ceiling vision-based SLAM technique. In: Int conf robot syst, pp 3195–3200
Dissanayake G, Newman P, Clark S, Durrant-Whyte HF, Csorba M (2001) A solution to the simultaneous localization and map building (SLAM) problem. IEEE Trans Robot Autom 17(3):229–241
Castellanos JA, Neira J, Tardòs JD (2004) Limits to the consistency of EKF-based SLAM. In: IFAC symp intell auton vehicles
Bailey T, Neito J, Guivant J, Stevens M, Nebot E (2006) Consistency of the EKF-SLAM algorithm. In: Int conf robot syst, pp 3562–3568
Choi M, Sakthivel R, Chung WK (2007) Neural network-aided extended Kalman filter for SLAM problem. In: IEEE int conf robot autom, pp 1686–1690
Murphy K (1999) Bayesian map learning in dynamic environments. In: Proc conf neural inf process syst, pp 1015–1021
Doucet A, Freitas J, Murphy K, Russel S (2000) Rao–Blackwellized particle filtering for dynamic Bayesian networks. In: Proc conf uncertain artif intell, pp 176–183
Montemerlo M, Thrun S, Koller D, Wegbreit B (2002) Fast-SLAM: A factored solution to the simultaneous localization and mapping problem. In: Proc AAAI nat conf artif intell, pp 593–598
Montemerlo M, Thrun S, Koller D, Wegbreit B (2003) Fast-SLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges. In: Proc int joint conf artif intell, pp 1151–1156
Rodreguez-Losada D, San Segundo P, Matia F, Pedraza L (2009) Dual FastSLAM: Dual factorization of the particle filter based solution of the simultaneous localization and mapping problem. J Intell Robot Syst 55:109–134
Eliazar A, Parr R (2003) DP-SLAM: Fast, robust simultaneous localization and mapping without predetermined landmarks. In: Proc int conf artif intell, pp 1135–1142
Hähnel D, Burgard W, Fox D, Thrun S (2003) An efficient FastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements. In: IEEE/RSJ int conf intell robot syst, pp 206–211
Grisetti G, Tipaldi GD, Stachniss C, Burgard W, Nardi D (2007) Fast and accurate SLAM with Rao-Blackwellized particle filters. Robot Auton Syst 55:30–38
Chatterjee A, Matsuno F (2007) A neuro-fuzzy assisted extended Kalman filter-based approach for simultaneous localization and mapping (SLAM) problems. IEEE Trans Fuzzy Syst 15(5):984–997
Begum M, Mann G, Gosine R (2008) Integrated fuzzy logic and genetic algorithmic approach for simultaneous localization and mapping of mobile robots. Appl Soft Comput 8:150–165
Duckett T (2003) A genetic algorithm for simultaneous localization and mapping. In: IEEE int conf robot autom, pp 434–439
Borenstein J, Feng L (1996) Gyrodometry: A new method for combining data from gyros and odometry in mobile robots. In: IEEE int conf robot autom, pp 423–428
Fogel D (1995) Evolutionary computation. IEEE Press, New York
Im KY, Oh SY, Han SJ (2002) Evolving a modular neural network-based behavioral fusion using extended VFF and environment classification for mobile robot navigation. IEEE Trans Evol Comput 6(4):413–419
Chohra A, Benmehrez C (1998) Neural navigation approach for intelligent autonomous vehicles (IAV) in partially structured environments. Appl Intell 8(3):219–233
Durand N, Alliot J-M, Médioni F (2000) Neural nets trained by genetic algorithm for collision avoidance. Appl Intell 13(3):205–213
Asiain JD Gomez-Allende DM (2001) Landmark recognition for autonomous navigation using odometric information and a network of perceptrons. In: Lect note in comput sci, vol 2085, pp 451–458
Choi WS, Oh SY (2007) Range sensor-based robot localization using neural network. In: Int conf control autom syst, pp 1092–1097
An SY, Kang JG, Choi WS, Oh SY (2010) A neural network based retrainable framework for robust object recognition with application to mobile robotics. Appl Intell. doi:10.1007/s10489-010-0212-9
Haykin S (2009) Neural networks. Macmillan, New York
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Jarvis RA, Patrick EA (1973) Clustering using a similarity measure based on shared nearest neighbors. IEEE Trans Comput 11
Borenstein J, Everett HR, Feng L (1996) Where am I? Sensors and methods for mobile robot positioning. University of Michigan, 119
Back T, Schwefel H (1993) An overview of evolutionary algorithms for parameter optimization. Evol Comput 1(1):1–23
Lucas GW (2009) A tutorial and elementary trajectory model for the differential steering system of robot wheel actuators. http://rossum.sourceforge.net/papers/DiffSteer/DiffSteer.html of subordinate document. Accessed 20 Jun 2009
Bishop CM (2002) Neural networks for pattern recognition. Oxford University Press, Oxford
Chan FHY, Lam FK, Zhu H (1998) Adaptive thresholding by a variational method. IEEE Trans Image Process 7(3):468–473
Yuen HK, Princen J, Illingworth J, Kittler J (1990) Comparative study of hough transform methods for circle finding. Image Vis Comput 1(1):71–77
http://www.hagisonic.com, 2006
Oh SS et al (2009) A system architecture for intelligent building guide robot PHOPE. In: 4th int conf auton robot agents
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kang, JG., Kim, S., An, SY. et al. A new approach to simultaneous localization and map building with implicit model learning using neuro evolutionary optimization. Appl Intell 36, 242–269 (2012). https://doi.org/10.1007/s10489-010-0257-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-010-0257-9