Motivation and Objectives

Cooperative Robotics is a fast developing field, with applications to areas such as building surveillance, transportation of large objects, air and underwater pollution monitoring, forest fire detection, transportation systems, rescue after large-scale disasters. In a wide sense, a population of cooperative robots can be considered a distributed autonomous sensor network, where mobile robots and static sensors cooperate to provide a better understanding of ongoing activities in the area of concern, where they were deployed, a difficult, if not impossible, task for a single robot. Several lessons can be learned from emerging fields in Artificial Intelligence (e.g., Multi-Agent Systems) concerning topics such as Reinforcement Learning, Task Allocation, Logic-Based Planning, and Coordination Mechanisms, and in Systems Theory, concerning topics such as Discrete Event and Hybrid Systems, Decentralized (Partially Observable) Markov Decision Processes.

Our current case study - soccer robots - consists of a very challenging problem, where the robots must cooperate not only to shoot a ball towards the goal, but also to detect and avoid static (walls, stopped robots) and dynamic (moving robots) obstacles. Furthermore, they must cooperate to defeat an opposing team. Our research in soccer robotics includes image processing, visual servoing, navigation, cooperative perception, formation control, plan representation and task coordination by discrete event systems, multi-agent reinforcement learning, and multi-agent modeling and logic-based reasoning.

Topics

• Middleware and Functional Architecture
• Navigation
• Cooperative Perception
• Role Switching
• Discrete Event Plan Representation
• Color Segmentation