Self-Exploration of Autonomous Robots Using Attractor-Based Behavior Control and ABC-Learning

@inproceedings{Hild2011SelfExplorationOA,
  title={Self-Exploration of Autonomous Robots Using Attractor-Based Behavior Control and ABC-Learning},
  author={Manfred Hild and Matthias Kubisch},
  booktitle={SCAI},
  year={2011}
}
An autonomous robot which is equipped with sensorimotor loops and situated within a specific environment can be regarded as a dynamical system. By using Attractor-Based Behavior Control (ABC), the attractors of this dynamical system correspond to energy-efficient behavioral body postures, and the attractorconnecting heteroclinic orbits can be utilized to generate stable motion trajectories. We introduce ABC-Learning and demonstrate how it enables an autonomous robot to self-explore its… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 21 references

On Ashby’s Homeostat: A Formal Model of Adaptive Regulation

  • J. M. Herrmann, M. Holicki, R. Der
  • From Animals to Animates. MIT Press, 2004, pp…
  • 2004
Highly Influential
1 Excerpt

Behavior: The Control of Perception

  • W. Powers
  • Aldine Transaction,
  • 1973
Highly Influential
2 Excerpts

Design for a Brain

  • W. R. Ashby
  • J. Wiley,
  • 1960
Highly Influential
1 Excerpt

Proposal of an Intrinsically Motivated System for Exploration of Sensorimotor State Spaces

  • M. Kubisch, M. Hild, S. Höfer
  • Proceedings of the 10th International Conference…
  • 2010
1 Excerpt

Using Estimated State Sequences to Model Dynamical Systems

  • M. Gashler, T. Martinez
  • Journal of Machine Learning Research 1, 2010.
  • 2010
1 Excerpt

Using Slow Feature Analysis to Extract Behavioural Manifolds Representing Humanoid Robot Postures

  • S. Höfer, M. Hild, M. Kubisch
  • Proceedings of the 10th International Conference…
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…