Title :
Evolving an adaptive controller for a quadruped-robot with dynamically-rearranging neural networks
Author :
Otsu, Kei ; Ishiguro, Akio ; Fujii, Akinobu ; Aoki, Takeshi ; Eggenberger, Peter
Author_Institution :
Dept. of Comput. Sci. & Eng., Nagoya Univ., Japan
Abstract :
As highly complicated interaction dynamics exist, it is therefore extremely difficult to design controllers for legged robots. Evolutionary robotics is one of the most promising approaches, but there still exist several problems that have to be solved. One of the critical problems is that evolved agents generally tend to over adapt to their given environments through the evolutionary process. In other words, they lack rich adaptability. Therefore, it is highly necessary to establish a method that enables one to efficiently construct adaptive controllers that can cope with different situations. For this purpose we introduce the concept of neuromodulators, allowing the evolvement of neural networks which can adjust not only the synaptic weights, but also the structure of the neural network by blocking and/or activating synapses or neurons. We apply this concept to create an adaptive controller for a quadruped robot which not only can walk forward but also regulate the torque output applied to each joint, according to the current situation
Keywords :
adaptive control; legged locomotion; motion control; neurocontrollers; robot dynamics; torque control; adaptability; adaptive control; dynamically rearranging neural networks; legged locomotion; mobile robots; neuromodulators; quadruped robot; synaptic weights; torque control; Adaptive control; Automatic control; Cognitive robotics; Feedback loop; Information science; Neural networks; Programmable control; Robotics and automation; Service robots;
Conference_Titel :
Intelligent Robots and Systems, 2001. Proceedings. 2001 IEEE/RSJ International Conference on
Conference_Location :
Maui, HI
Print_ISBN :
0-7803-6612-3
DOI :
10.1109/IROS.2001.976372