Learning failure recovery knowledge for mechanical assembly

L.S. Lopes, L.M. Camarinha-Matos
Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96  
A framework for planning and supervision of robotized assembly tasks is initially presented, with emphasis on failure recovery. The approach to the integration of services and the modeling of tasks, resources and environment is briefly described. A planning strategy and domain knowledge f o r nominal plan execution is presented. Through the use of machine learning techniques, the supervision architecture will be given capabilities for improving its peij5ormance over time. In particular, an
more » ... ach for memorizing failure recovery episodes, based on abstraction, deductive generalization and feature construction, is presented. Recovery planning consists of adapting plan skeletons from similar episodes previously occurred.
doi:10.1109/iros.1996.571041 dblp:conf/iros/LopesC96 fatcat:jga2rsupufazbagc7ifyrz7qtq