Dynamical movement primitives: Learning attractor models for motor behaviors
Neural Computation
| Hi-index | 0.00 |
To generate coordinated periodic movements, robot locomotion demands mechanisms which are able to learn and produce stable rhythmic motion in a controllable way. Because systems based on biological central pattern generators (CPGs) can cope with these demands, these kind of systems are gaining in success. In this work we introduce a novel methodology that uses the dynamics of a randomly connected recurrent neural network for the design of CPGs. When a randomly connected recurrent neural network is excited with one or more useful signals, an output can be trained by learning an instantaneous linear mapping of the neuron states. This technique is known as reservoir computing (RC). We will show that RC has the necessary capabilities to be fruitful in designing a CPG that is able to learn human motion which is applicable for imitation learning in humanoid robots.