Title :
Robotic agent control combining reactive and learning capabilities
Author :
Jacak, Witold ; Dreiseitl, Stephan
Author_Institution :
Res. Inst. for Symbolic Comput., Johannes Kepler Univ., Linz, Austria
Abstract :
This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of “lifelong learning” can be implemented by neural networks in a robotic action planner
Keywords :
intelligent control; learning by example; learning systems; neurocontrollers; planning (artificial intelligence); robots; state-space methods; action planner; autonomous robotic agent; conceptual world space; inductive learning; intelligent system; lifelong learning; machine learning; neural networks; reactive learning; robotic agent control; state space; Artificial intelligence; Control systems; Intelligent robots; Machine learning; Machine learning algorithms; Neural networks; Orbital robotics; Power system modeling; Robot control; State-space methods;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549153
