TY - CONF

T1 - Real-Time joint Landmark Recognition and Classifier Generation by an Evolving Fuzzy System.

AU - Zhou, Xiaowei

AU - Angelov, Plamen

N1 - "©2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE." "This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder."

PY - 2006/7/17

Y1 - 2006/7/17

N2 - A new approach to real-time joint classification and classifier design is proposed in this paper. It is based on the recently developed evolving fuzzy system (EFS) method and is applied to mobile robotics. The approach s t m from subtractive clustering method and its on-line evolving extension called eclustering. A new formula for data potential (spatial density) determination based on the participatory learning and data scatter concepts is introduced in the paper that is computationally simpler and more intuitive. An EFS-based self-organking classifier (eClass) is designed by automatic labding the landmarks that are detected in real-time The proposed approach makes possible fully autonomous and unsupervised joint landmark detection and recognition without the use of absolute coordinates, any communication link or any pr&raining. The proposed algorithm is recursive, nowiterative, one pass and thus cornputationally inexpensive and suitable for real-time applications. Extensive simulations as well as real-life tests has b m carried out in an indoor environment (an office located at InfoLab21, Lancmter University) using Pioneer3 DX mobile robotic platform equipped with sonar and motion sensors and on-board PC. The results indicate superior rates of recognition, flexibility, and computational demands of the proposed approach comparing with the previously published similar methods. Further investigations will be directed towards development of a cooperative scheme, tests in a realistic outdoor environment, and the presence of moving obstacles. (c) IEEE Press

AB - A new approach to real-time joint classification and classifier design is proposed in this paper. It is based on the recently developed evolving fuzzy system (EFS) method and is applied to mobile robotics. The approach s t m from subtractive clustering method and its on-line evolving extension called eclustering. A new formula for data potential (spatial density) determination based on the participatory learning and data scatter concepts is introduced in the paper that is computationally simpler and more intuitive. An EFS-based self-organking classifier (eClass) is designed by automatic labding the landmarks that are detected in real-time The proposed approach makes possible fully autonomous and unsupervised joint landmark detection and recognition without the use of absolute coordinates, any communication link or any pr&raining. The proposed algorithm is recursive, nowiterative, one pass and thus cornputationally inexpensive and suitable for real-time applications. Extensive simulations as well as real-life tests has b m carried out in an indoor environment (an office located at InfoLab21, Lancmter University) using Pioneer3 DX mobile robotic platform equipped with sonar and motion sensors and on-board PC. The results indicate superior rates of recognition, flexibility, and computational demands of the proposed approach comparing with the previously published similar methods. Further investigations will be directed towards development of a cooperative scheme, tests in a realistic outdoor environment, and the presence of moving obstacles. (c) IEEE Press

KW - DCS-publications-id

KW - inproc-457

KW - DCS-publications-credits

KW - dsp

KW - DCS-publications-personnel-id

KW - 102

KW - 82

M3 - Conference paper

T2 - World Congress on Computational Intelligence

Y2 - 16 July 2006 through 21 July 2006

ER -