Learning Perception for Indoor Robot Navigation with a Hybrid Hidden Markov Model/Recurrent Neural Networks Approach

This paper introduces a hybrid system for modeling, learning and recognition of sequences of 'states' in indoor robot navigation. States are broadly defined as local relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel recurrent neural networks trained to perform a posteriori state probability estimates of an underlying hidden Markov model (HMM) given a sequence of sensory (e.g. sonar) observations. Discriminative training is accomplished in a supervised manner, using gradient-descent. Recognition is carried out either in a dynamic programming framework, i.e. searching the maximum a posteriori probability of state-posteriors along paths of the HMM, or in real time. The approach is suitable for navigation and for map learning. Experiments of learning and recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presented.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  P. Freedman,et al.  Using uncertain sensing data to create reliable maps: an algorithm for exploring/mapping unknown graphlike worlds , 1993, Other Conferences.

[3]  Gianni A. Di Caro,et al.  Bridging the gap between planning and reactivity: a layered architecture for autonomous indoor navigation , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[4]  Sin-Horng Chen,et al.  A speech recognition method based on the sequential multi-layer perceptrons , 1996, Neural Networks.

[5]  John S. Bridle,et al.  Alpha-nets: A recurrent 'neural' network architecture with a hidden Markov model interpretation , 1990, Speech Commun..

[6]  P. Frasconi,et al.  Local Feedback Multi-Layered Networks , 1992 .

[7]  Yonghong Yan,et al.  Speech recognition using neural networks with forward-backward probability generated targets , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Wolfram Burgard,et al.  A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots , 1998, Auton. Robots.

[9]  Yoshua Bengio,et al.  Input-output HMMs for sequence processing , 1996, IEEE Trans. Neural Networks.

[10]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[11]  Yoshua Bengio.  A Connectionist Approach to Speech Recognition , 1993, Int. J. Pattern Recognit. Artif. Intell..

[12]  Reid G. Simmons,et al.  Probabilistic Robot Navigation in Partially Observable Environments , 1995, IJCAI.

[13]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[14]  Steve Renals,et al.  Large vocabulary continuous speech recognition using a hybrid connectionist-HMM system , 1994, ICSLP.

[15]  G. Ruske,et al.  A hybrid RBF-HMM system for continuous speech recognition , 1995 .

[16]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Yoshua Bengio,et al.  Global optimization of a neural network-hidden Markov model hybrid , 1992, IEEE Trans. Neural Networks.

[18]  Hervé Bourlard,et al.  Continuous speech recognition by connectionist statistical methods , 1993, IEEE Trans. Neural Networks.

[19]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[20]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[21]  Yoshua Bengio,et al.  Neural networks for speech and sequence recognition , 1996 .

[22]  Hervé Bourlard,et al.  Connectionist probability estimators in HMM speech recognition , 1994, IEEE Trans. Speech Audio Process..

[23]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[24]  Martial Hebert,et al.  Vision and navigation for the Carnegie-Mellon Navlab , 1988 .

[25]  George Zavaliagkos,et al.  A hybrid segmental neural net/hidden Markov model system for continuous speech recognition , 1994, IEEE Trans. Speech Audio Process..

[26]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[27]  Christoph Neukirchen,et al.  Advanced training methods and new network topologies for hybrid MMI-connectionist/HMM speech recognition systems , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[28]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[29]  Nils J. Nilsson,et al.  Shakey the Robot , 1984 .

[30]  Biing-Hwang Juang,et al.  Hidden Markov Models for Speech Recognition , 1991 .

[31]  Christoph Neukirchen,et al.  Large vocabulary speaker-independent continuous speech recognition with a new hybrid system based on MMI-neural networks , 1995, EUROSPEECH.

[32]  Andrea Fusiello,et al.  Synthesis of indoor maps in presence of uncertainty , 1997, Robotics Auton. Syst..

[33]  Edmondo Trentin,et al.  Networks with trainable amplitude of activation functions , 2001, Neural Networks.

[34]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[35]  Renato De Mori,et al.  A hybrid coder for hidden Markov models using a recurrent neural networks , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[36]  Tod S. Levitt,et al.  Qualitative Landmark-based Path Planning and Following , 1987, AAAI.

[37]  Yoshua Bengio,et al.  LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition , 1995, Neural Computation.

[38]  Marco Gori,et al.  Combining Neural Networks and Hidden Markov Models for Speech Recognition , 1999 .

[39]  Hsiao-Wuen Hon,et al.  Large-vocabulary speaker-independent continuous speech recognition using HMM , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[40]  John M. Evans,et al.  HelpMate: an autonomous mobile robot courier for hospitals , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[41]  Leslie Pack Kaelbling,et al.  An Architecture for Intelligent Reactive Systems , 1987 .

[42]  Tracy L. Anderson,et al.  Animal behavior as a paradigm for developing robot autonomy , 1990, Robotics Auton. Syst..

[43]  Gerhard Rigoll,et al.  Maximum mutual information neural networks for hybrid connectionist-HMM speech recognition systems , 1994, IEEE Trans. Speech Audio Process..

[44]  James L. Crowley,et al.  Coordinaton of Action and Perception in a Surveillance Robot , 1987, IEEE Expert.

[45]  Hervé Bourlard,et al.  Connectionist speech recognition , 1993 .

[46]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[47]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[48]  David E. Wilkins.  High-Level Planning in a Mobile Robot Domain (Preprint) , 1986 .

[49]  Hervé Bourlard,et al.  Connectionist Speech Recognition: A Hybrid Approach , 1993 .

[50]  Horacio Franco,et al.  Context-dependent connectionist probability estimation in a hybrid hidden Markov model-neural net speech recognition system , 1994, Comput. Speech Lang..

[51]  Renato De Mori,et al.  Spoken Dialogues with Computers , 1998 .

[52]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[53]  Alessandro Cimatti,et al.  The Mobile Robot of MAIA: Actions and Interactions in a Real Life Scenario , 1995 .

[54]  Anthony J. Robinson,et al.  An application of recurrent nets to phone probability estimation , 1994, IEEE Trans. Neural Networks.

[55]  Yann LeCun,et al.  Learning processes in an asymmetric threshold network , 1986 .

[56]  Benjamin Kuipers,et al.  A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations , 1991, Robotics Auton. Syst..

[57]  Yong Joo Chung,et al.  Multilayer perceptrons for state-dependent weightings of HMM likelihoods , 1996, Speech Commun..

[58]  Sung-Bae Cho,et al.  An HMM/MLP Architecture for Sequence Recognition , 1995, Neural Computation.

[59]  Reid G. Simmons,et al.  Passive Distance Learning for Robot Navigation , 1996, ICML.

[60]  Alain Hillion,et al.  Toward the border between neural and Markovian paradigms , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[61]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[62]  Fabrice R. Norelis,et al.  Control of mobile robot actions , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[63]  George Zavaliagkos,et al.  A Hybrid Continuous Speech Recognition System Using Segmental Neural Nets with Hidden Markov Models , 1993, Int. J. Pattern Recognit. Artif. Intell..

[64]  Elliot Singer,et al.  A speech recognizer using radial basis function neural networks in an HMM framework , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[65]  Steve Renals,et al.  Recent improvements to the ABBOT large vocabulary CSR system , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[66]  Edmondo Trentin.  Learning the Amplitude of Activation Functions in Layered Networks , 1999 .