Evaluating BDI Agents in ROS: From Basic Integration to Fault Tolerant Multi-Robot Systems

The integration of Belief-Desire-Intention (BDI) agents with robotic systems offers a promising approach to programming autonomy
and decision-making in complex environments. This paper extends an interface to combine the Jason agent programming language with the Robot Operating System (ROS) to control multiple robots. We evaluate this implementation through two case studies—single-robot navigation and multi-robot auction-based task allocation—and benchmark it against a functionally equivalent Python-based implementation using qualitative and quantitative metrics. While the results of the first two case studies are informative, they are not sufficient to draw definitive conclusions about system fault tolerance. Therefore, we introduce a third fault-tolerance experiment: after adding additional robots and simulating a navigation agent failure, the system autonomously detects the failure, preempts the relevant tasks, and dynamically redistributes goals among the remaining agents. The outcomes are directly compared with those of the Python baseline. Our study outlines the experimental design and evaluation methodology, aiming to clarify the trade-offs between agent-oriented and imperative approaches in multi-robot systems and to identify scenarios in which BDI-based models provide advantages in responsiveness, robustness, and scalability.