Abstract
The emergence of multi-agent systems in the past years has led to the development of new methodologies to assist in the requirements and architectural analysis, as well as in the design phases of such systems. Consequently, several Agent Oriented Software Engineering (AOSE) methodologies have been proposed. In this paper, we analyze some AOSE methodologies, including Gaia, which supports the architectural design stage, and some proposed extensions. We then use an adapted version of this methodology to design an abstract generic system meta-model for a multi-robot application, which can be used as a basis for the design of these systems, avoiding or shortening repetitive tasks common to most systems. Based on the proposed Generic Robotic Agent Meta-Model (GRAMM), two distinct models for two different applications are derived, demonstrating the versatility and adaptability of the meta-model. By adapting the Gaia methodology to the design of open systems, this work makes the designers' job faster and easier, decreasing the time needed to complete several tasks, while at the same time maintaining a high-level overview of the system.

Abstract
In soccer, like in business, results are often the best indicator of a team's performance in a certain competition but insufficient to a coach to asses his team performance. As a consequence, measurement tools play an important role in this particular field. In this research work, a performance tool for soccer, based only in Cartesian coordinates is presented. Capable of calculating final game statistics, suisber of shots, the calculus methodology analyzes the game in a sequential manner, starting with the identification of the kick event (the basis for detecting all events), which is related with a positive variation in the ball's velocity vector. The achieved results were quite satisfactory, mainly due to the number of successfully detected events in the validation process (based on manual annotation). For the majority of the statistics, these values are above 92% and only in the case of shots do these values drop to numbers between 74 and 85%. In the future, this methodology could be improved, especially regarding the shot statistics, integrated with a real-time localization system, or expanded for other collective sports games, such as hockey or basketball.

Abstract
The Vehicle Scheduling Problem is a well-known combinatorial optimization problem that emerges in mobility and transportation sectors. The heterogeneous fleet with multiple depots extension arises in major urban public transportation companies due to different demands throughout the clay and some restrictions in the use of different vehicle types. This extension introduces complexity to the problem and makes the known deterministic methods unable to solve it efficiently. This paper describes an approach to create a comprehensive model to represent the Multiple Depot Vehicle Scheduling Problem as an Asymmetric Traveling Salesman Problem. To solve the A-TSP problem an Ant Colony based meta-heuristic was developed. The results achieved on solving problems from a Portuguese major public transportation planning database show the usefulness of the proposed approach.

Abstract
Expressiveness and naturalness in robotic motions and behaviors can be replicated with the usage of captured human movements. Considering dance as a complex and expressive type of motion, in this paper we propose a method for generating humanoid dance motions transferred from human motion capture (MoCap) data. Motion data of samba dance was synchronized to samba music, manually annotated by experts, in order to build a spatiotemporal representation of the dance movement with variability, in relation to the respective musical temporal structure (musical meter). This enabled the determination and generation of variable dance key-poses according to the captured human body model. In order to retarget these key-poses from the original human model into the considered humanoid morphology, we propose methods for resizing and adapting the original trajectories to the robot joints, overcoming its varied kinematic constraints. Finally, a method for generating the angles for each robot joint is presented, enabling the reproduction of the desired poses in a simulated humanoid robot NAO. The achieved results validated our approach, suggesting that our method can generate poses from motion capture and reproduce them on a humanoid robot with a good degree of similarity.

Abstract
This paper presents the modifications needed to adapt a humanoid agent architecture and behaviors from simulation to a real robot. The experiments were conducted using the Aldebaran Nao robot model. The agent architecture was adapted from the RoboCup 3D Simulation League to the Standard Platform League with as few changes as possible. The reasons for the modifications include small differences in the dimensions and dynamics of the simulated and the real robot and the fact that the simulator does not create an exact copy of a real environment. In addition, the real robot API is different from the simulated robot API and there are a few more restrictions on the allowed joint configurations. The general approach for using behaviors developed for simulation in the real robot was to: first, (if necessary) make the simulated behavior compliant with the real robot restrictions, second, apply the simulated behavior to the real robot reducing its velocity, and finally, increase the velocity, while adapting the behavior parameters, until the behavior gets unstable or inefficient. This paper also presents an algorithm to calculate the three angles of the hip that produce the desired vertical hip rotation, since the Nao robot does not have a vertical hip joint. All simulation behaviors described in this paper were successfully adapted to the real robot.

Abstract
Decision making in complex, multi agent and dynamic environments such as disaster spaces is a challenging problem in Artificial Intelligence. Uncertainty, noisy input data and stochastic behavior which are common characteristics of such environment makes real time decision making more complicated. In this paper an approach to solve the bottleneck of dynamicity and variety of conditions in such situations based on reinforcement learning is presented. This method is applied to RoboCup Rescue Simulation Fire brigade agent's decision making process and it learned a good strategy to save civilians and city from fire. The utilized method increases the speed of learning and it has very low memory usage. The effectiveness of the proposed method is shown through simulation results.