Abstract

Abstract

Abstract
In recent years, cognitive robots have started to find their way into manufacturing halls. However, the full potential of these robots can only be exploited through (a) an integration of the robots with the Manufacturing Execution System (MES), (b) a new and simpler way of programming based on robot skills, automated task planning, and knowledge modeling, and (c) enabling the robots to function in a shared human/robot workspace with the ability to handle unexpected situations. The STAMINA project has built a robotic system that meets these objectives for an automotive kitting application, which has also been tested, validated, and demonstrated in a relevant environment (TRL6). This paper describes the STAMINA robot system and the evaluation of this system on a series of realistic kitting tasks. The structure of the system, evaluation methodology, and experimental results, are presented along with the insights and experiences gained from this work.

Abstract
In this paper, we study the concept of Evolutionarily Stable Strategies (ESSs) for symmetric games with n >= 3 players. The main properties of these games and strategies are analyzed and several examples are provided. We relate the concept of ESS with previous literature and provide a proof of finiteness of ESS in the context of symmetric games with n >= 3 players. We show that unlike the case of n = 2, when there are more than two populations an ESS does not have a uniform invasion barrier, or equivalently, it is not equivalent to the strategy performing better against all strategies in a neighborhood. We also construct the extended replicator dynamics for these games and we study an application to a model of strategic planning of investment.

Abstract
Promotional tools such as cross-market discounts have been increasingly used as a means to increase customer satisfaction and sales. This paper aims to assess whether the implementation of a cross-market discount campaign by a retailing company encouraged customers to increase their purchases level. It contributes to the literature by using neural networks to detect novelties in a real context involving cross-market discounts. Besides the computation of point predictions, the methodology proposed involves the estimation of neural networks prediction intervals. Sales predictions are compared with the observed values in order to detect significant changes in customers' spending. The use of neural networks is validated through the comparison with the forecasting estimates of support vector regression, regression trees, and linear regression. The results reveal that the promotional campaign under analysis did not significantly impact the sales of the rewarded customers.

Abstract
Disruptive requirements that currently drive the so-called Industry 4.0 (I4.0) are increasingly present in today's industries, where factories are forced to innovate in search of improvement in the quality of manufacturing of products aligned with the reductions of: manufacturing time, environmental and cost impacts with the manufacturing process. For this, an Information Systems (IS) architecture is proposed to reduce the negative impacts on an industrial operation caused by manual configuration failures in manufacturing systems, machines that are worn out in the production process and unstable integrations between industrial subsystems. The suggested SI model uses the Viable Systems Model adapted to Maintenance 4.0 technologies (Cyber-physical Systems (CPS), Manufacturing Execution Systems (MES), Data Mining and Digital Manufacturing concepts/technologies) with the goal to create an automatic purchase flow to replace parts by mitigating impending failures in industrial equipment through data mining and predictive analysis.