Recurrent neural network learning with an application to the control of legged locomotion

Use of robots for real life applications has an increasing trend in today's industry and military. The robot platforms are capable of performing dangerous and difficult tasks, which are not efficient when carried out by human beings. Most of these tasks require high motion ability. There are various robotic platform and locomotion algorithms which may solve a given task. Among these, the biped robot platforms promise high performance in realizing difficult maneuver due to their morphological similarity to legged animals. Thus, legged locomotion is highly desirable in order to perform difficult maneuvers in rough terrain environments. However both modeling and control of such structures are quite difficult due to highly nonlinear structure of the resulting equations of motion and computational load of inverse kinematic equations. Central nervous systems and spinal cords of animals take role in control of locomotion of animals together. For controlling such biped robotic platforms frequently used control algorithms are based on so-called Central Pattern Generators (CPG). The controllers based on CPGs can be realized in different ways which includes the utilization of neural networks. However CPG is only capable of imitating spinal cord type of reflex-based motions in locomotion because of their restricted parameter space to sustain stable oscillation. Fully recurrent neural networks have capability of controlling locomotion with a higher conscious level such as central nervous system, hence motion space can be enlarged. Unfortunately, training of recurrent neural networks (RNN) takes long time. Moreover, their behaviors may be unpredictable against untrained inputs and training process may encounter with instability related problems easily. In order to solve these problems, various acceleration and regularization techniques are tested in the neural network training and their successes were compared with each other. Furthermore, time constant and error gradient limitation methods are employed to sustain stable training and their benefits are discussed. Finally leg angles of walking biped robot are taught to a group of RNNs with different configurations by benefiting from training stability enhancing methods. The resulting RNNs are then used in biped locomotion by using a classical PD controller. After that, performance of resulting RNNs and their stable locomotion generation capabilities are evaluated and effects of configuration parameters are discussed in detail.