Continuous Adaptation in Robotic Systems by Indirect Online Evolution

@article{Furuholmen2008ContinuousAI,
  title={Continuous Adaptation in Robotic Systems by Indirect Online Evolution},
  author={Marcus Furuholmen and Mats Hovin and J. Torresen and Kyrre Glette},
  journal={2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS)},
  year={2008},
  pages={71-76}
}
A conceptual framework for online evolution in robotic systems called indirect online evolution (IDOE) is presented. A model specie automatically infers models of a hidden physical system by the use of gene expression programming (GEP). A parameter specie simultaneously optimizes the parameters of the inferred models according to a specified target vector. Training vectors required for modelling are automatically provided online by the interplay between the two coevolving species and the… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-8 OF 8 REFERENCES

Evolutionary Robotics

D. Floreano, S. Nolfi
  • Springer Handbook of Robotics
  • 2008
VIEW 1 EXCERPT

and H

J. Bongard, V. Zykov
  • Lipson. Resilient Machines Through Continuous Self-Modeling
  • 2006
VIEW 1 EXCERPT

Nonlinear system identification using coevolution of models and tests

  • IEEE Transactions on Evolutionary Computation
  • 2004
VIEW 1 EXCERPT

Gene Expression Programming: a New Adaptive Algorithm for Solving Problems

C. Ferreira
  • Arxiv preprint cs.AI/0102027
  • 2001
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…