摘要: This is the final report of a two-year, Laboratory Directed Research and Development (LDRD) project at the Los Alamos National Laboratory (LANL). A method was developed to incorporate learning and adaptive capabilities into tradit... 展开 This is the final report of a two-year, Laboratory Directed Research and Development (LDRD) project at the Los Alamos National Laboratory (LANL). A method was developed to incorporate learning and adaptive capabilities into traditional rule-based descriptions of environments. The learning and adapting capacity is critical to robot programming in highly unstructured and variable environments such as the operation of robots in gloveboxes. The technology is based on a hybrid expert system technology, called expert networks, and was developed with the associated knowledge capture techniques. 收起