Towards a theoretical foundation for morphological computation with compliant bodies
Towards a theoretical foundation for morphological computation with compliant bodies
复制标题
DOI：
10.1007/s00422-012-0471-0
复制
发表时间：
2011-12-01
影响因子：
1.9
通讯作者：
Maass, Wolfgang
中科院分区：
文献类型：
--
作者：
Hauser, Helmut;Ijspeert, Auke J.;Maass, Wolfgang
柔顺机器人的控制是，由于其往往是非线性和复杂的动力学，固有的困难。形态计算的愿景不仅将这些方面视为问题，而且还将其视为解决方案的一部分。非刚体部分不再被视为刚体部分的不完美实现，而是作为潜在的计算资源。这种观点的适用性已经被证明是各种复杂的机器人控制问题。然而，理解形态学计算的能力和局限性的理论基础一直缺失至今。我们提出了一个模型的形态计算与顺应机构，一个精确的数学表征的潜在的计算贡献的复杂的物理体是可行的。该理论表明，复杂性和非线性，通常是机器人不需要的特性，是提供计算能力所需的特征。我们证明了简单的通用模型的物理机构，质量弹簧系统的基础上，可以用来实现复杂的非线性算子。通过向形态学添加简单的读出（其是静态和线性的），这样的设备能够在连续时间内模拟输入到输出流的复杂映射。因此，通过将部分计算外包给物理身体，学习控制复杂身体的困难问题可以简化为一个简单而清晰的学习任务，它不会陷入误差函数的局部极小值。
The control of compliant robots is, due to their often nonlinear and complex dynamics, inherently difficult. The vision of morphological computation proposes to view these aspects not only as problems, but rather also as parts of the solution. Non-rigid body parts are not seen anymore as imperfect realizations of rigid body parts, but rather as potential computational resources. The applicability of this vision has already been demonstrated for a variety of complex robot control problems. Nevertheless, a theoretical basis for understanding the capabilities and limitations of morphological computation has been missing so far. We present a model for morphological computation with compliant bodies, where a precise mathematical characterization of the potential computational contribution of a complex physical body is feasible. The theory suggests that complexity and nonlinearity, typically unwanted properties of robots, are desired features in order to provide computational power. We demonstrate that simple generic models of physical bodies, based on mass-spring systems, can be used to implement complex nonlinear operators. By adding a simple readout (which is static and linear) to the morphology, such devices are able to emulate complex mappings of input to output streams in continuous time. Hence, by outsourcing parts of the computation to the physical body, the difficult problem of learning to control a complex body, could be reduced to a simple and perspicuous learning task, which can not get stuck in local minima of an error function.