This paper presents a heuristic approach combining constraint satisfaction, local search and a constructive optimization algorithm for a large-scale energy management and maintenance scheduling problem. The methodology shows how to successfully combine and orchestrate different types of algorithms and produce competitive results. The local search for production assignment is a simple yet optimal solution for the relaxed initial problem. We also propose an efficient way to scale the method for huge instances. A large part of the presented work is done to compete in the ROADEF/EURO Challenge 2010, organized jointly by the ROADEF, EURO and the Électricité de France. The numerical results obtained for the official competition instances testify about the quality of the approach. The method achieves 3 out of 15 possible best results.

This paper presents a visual/motor behavior learning approach, based on neural networks. We propose Behavior Chain Model (BCM) in order to create a way of behavior learning. Our behavior-based system evolution task is a mobile robot detecting a target and driving/acting towards it. First, the mapping relations between the image feature domain of the object and the robot action domain are derived. Second, a multilayer neural network for offline learning of the mapping relations is used. This learning structure through neural network training process represents a connection between the visual perceptions and motor sequence of actions in order to grip a target. Last, using behavior learning through a noticed action chain, we can predict mobile robot behavior for a variety of similar tasks in similar environment. Prediction results suggest that the methodology is adequate and could be recognized as an idea for designing different mobile robot behaviour assistance.