BDI agents are a suitable approach for developing autonomous systems, including robots, capable of operating in dynamic and complex environments. The Robot Operating System (ROS), in turn, provides a collection of software libraries and tools that facilitate robot development. This tutorial introduces the programming of BDI agents for controlling ROS-based robots using the JaCaMo framework. It presents JaCaMo extensions that incorporate robot-specific elements, such as sensors and physical actuators, into the reasoning cycle of the agents. The theoretical foundations are complemented by hands-on activities in which participants develop ROS-based robots controlled by BDI agents.

JaCaMo-ROS Integration

We present programming techniques and supporting libraries for developing JaCaMo agents that control ROS-based robots. Participants learn how to integrate robot sensors into the perception process and how to map robot actuators to the actions of the agents. In the hands-on activities, participants implement and test agents capable of controlling ROS-based robots.

ROS-BDI Programming

We explore advanced aspects of controlling ROS-based robots with BDI agents. Topics include combining multiple sensor inputs to support complex decision making and designing goal-oriented behaviours to implement complex robotic tasks. The hands-on activities focus on implementing these capabilities in JaCaMo agents, integrating them with ROS-based robots, and running robotic applications.

About Maiquel

Maiquel de Brito is a Professor at the Federal University of Santa Catarina, Brazil. He received his PhD in Automation and Systems Engineering from the same university. His research interests include Agents and Multi-Agent Systems, particularly their social aspects and the application of agent technologies to cyber-physical systems. His main research projects include Embedded-MAS, a model and a set of development tools for cyber-physical BDI agents, and SAI, a model and a set of development tools for artificial institutions. Maiquel de Brito served as Chair of the Workshop-School of Agent Systems, their Environments and Applications (WESAAC) in 2022 and has been a member of the program committees of several conferences and workshops in the field of Artificial Intelligence.