THE DISTRIBUTED ARCHITECTURE FOR LARGE NEURAL NETWORKS (DISTAL) OF THE HUMANOID ROBOT MYON

Manfred Hild, Christian Thiele, Christian Benckendorff

Abstract

Humanoid robots are complex systems that require considerable processing power. This applies both for low-level sensorimotor loops, as well as for image processing and higher level deliberative algorithms. We present the distributed architecture DISTAL which is able to provide the processing power of large neural networks without relying on a central processor. The architecture successfully copes with runtime-metamorphoses of modular robots, such as the humanoid robot MYON, the body parts of which can be detached and reattached during runtime. We detail the implementation of DISTAL on 32-bit ARM RISC processors, describe the underlying neural byte-code (NBC) of neurons and synapses, and also depict the graphical application software BRAINDESIGNER which releases the user from program coding.

References

  1. Amoretti, M. and Reggiani, M. (2010). Architectural paradigms for robotics applications. Advanced Engineering Informatics, 24(1):4 - 13.
  2. Arkin, R. and Balch, T. (1997). AuRA: Principles and practice in review. Journal of Experimental & Theoretical Artificial Intelligence, 9(2):175-189.
  3. Baillie, J. (2005). Urbi: Towards a universal robotic lowlevel programming language. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2005.(IROS 2005), pages 820-825.
  4. Balkenius, C., Morén, J., Johansson, B., and Johnsson, M. (2010). Ikaros: Building cognitive models for robots. Advanced Engineering Informatics, 24(1):40 - 48.
  5. Hawes, N. and Wyatt, J. (2010). Engineering intelligent information-processing systems with cast. Advanced Engineering Informatics, 24(1):27 - 39.
  6. Heintz, F., Kvarnström, J., and Doherty, P. (2010). Bridging the sense-reasoning gap: DyKnow - Stream-based middleware for knowledge processing. Advanced Engineering Informatics, 24(1):14 - 26.
  7. Hild, M. (2007). Neurodynamische Module zur Bewegungsteuerung autonomer mobiler Roboter. PhD thesis, Institut für Informatik, Humboldt-Universität zu Berlin.
  8. Hild, M., Kubisch, M., and Höfer, S. (2011a). Using Quadric-Representing Neurons (QRENs) for RealTime Learning of an Implicit Body Model. In Proceedings of the 11th Conference on Mobile Robot and Competitions.
  9. Hild, M., Siedel, T., Benckendorff, C., Kubisch, M., and Thiele, C. (2011b). Myon: Concepts and Design of a Modular Humanoid Robot Which Can Be Reassembled During Runtime. In Proceedings of the 14th International Conference on Climbing and Walking Robots, Paris, France.
  10. Hülse, M. and Hild, M. (2010). Informatics for cognitive robots. Advanced Engineering Informatics, 24(1):2 - 3.
  11. Konolige, K. and Myers, K. (1998). The Saphira architecture for autonomous mobile robots. Artificial Intelligence and Mobile Robots: case studies of successful robot systems, pages 211-242.
  12. Laird, J., Newell, A., and Rosenbloom, P. (1987). Soar: An architecture for general intelligence. Artificial intelligence, 33(1):1-64.
  13. Lindstrom, M., Oreback, A., and Christensen, H. (2000). Berra: A research architecture for service robots. In IEEE International Conference on Robotics and Automation, 2000. Proceedings. ICRA'00, volume 4.
  14. Martínez-Barberá, H. and Herrero-Pérez, D. (2010). Programming multirobot applications using the thinkingcap-ii java framework. Advanced Engineering Informatics, 24(1):62 - 75.
  15. Mitchinson, B., Chan, T.-S., Chambers, J., Pearson, M., Humphries, M., Fox, C., Gurney, K., and Prescott, T. J. (2010). Brahms: Novel middleware for integrated systems computation. Advanced Engineering Informatics, 24(1):49 - 61.
  16. Orebäck, A. and Christensen, H. (2003). Evaluation of architectures for mobile robotics. Autonomous Robots, 14(1):33-49.
  17. Spranger, M., Thiele, C., and Hild, M. (2010). Integrating high-level cognitive systems with sensorimotor control. Advanced Engineering Informatics, 24(1):76 - 83.
Download


Paper Citation


in Harvard Style

Hild M., Thiele C. and Benckendorff C. (2011). THE DISTRIBUTED ARCHITECTURE FOR LARGE NEURAL NETWORKS (DISTAL) OF THE HUMANOID ROBOT MYON . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011) ISBN 978-989-8425-84-3, pages 260-266. DOI: 10.5220/0003683602600266


in Bibtex Style

@conference{ncta11,
author={Manfred Hild and Christian Thiele and Christian Benckendorff},
title={THE DISTRIBUTED ARCHITECTURE FOR LARGE NEURAL NETWORKS (DISTAL) OF THE HUMANOID ROBOT MYON},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)},
year={2011},
pages={260-266},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003683602600266},
isbn={978-989-8425-84-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)
TI - THE DISTRIBUTED ARCHITECTURE FOR LARGE NEURAL NETWORKS (DISTAL) OF THE HUMANOID ROBOT MYON
SN - 978-989-8425-84-3
AU - Hild M.
AU - Thiele C.
AU - Benckendorff C.
PY - 2011
SP - 260
EP - 266
DO - 10.5220/0003683602600266