Scalable co-evolution of soft robot properties and gaits
- 发表年份
- 2011
- 引用次数
- 2
- 访问权限
- 开放获取
摘要
One of the outstanding challenges in soft robotics is the chicken-and-egg problem of body/brain design: generation of locomotion is predicated on the existence of a locomotioncapable body, and generation of body plans is predicated upon the existence of effective locomotion.This problem is compounded by the high degree of coupling between the material properties of a soft body (such as stiffness or damping coefficients) and the effectiveness of a gait.In this work we describe a means by which the material properties of a simulated soft body co-evolve alongside locomotive gaits.Improvements in simulation time, with no loss of overall fitness, are obtained by incrementally increasing mesh density over the course of evolution.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002