A Reliable Computational Model for BDI Agents

BDI (Belief, Desire, Intention) is a mature and commonly adopted architecture for intelligent agents. However, the current computational model adopted by BDI has a number of problems with concurrency control, recoverability and predictability. This has hindered the construction of agents having robust and predictable behaviour. To this end, we propose to integrate "distributed transactions", a well-established technology in distributed systems, into the computational model of multi-agent systems based on the BDI architecture. Differently from common approaches, where so-called ACID (Atomic, Consistent, Isolated, Durable) transactions are used simply to operate on external resources such as databases, in our model transactions are the foundation of the operational semantics of intentions and of collaborative tasks within team of agents. They provide a predictable, well understood behaviour in case of partial or total failure of intentions to achieve their goals or even crashes of agents. Furthermore, distributed transactions provide a simple and clear extension of the BDI semantics from the single-agent case to teams of agents. We discuss the development of an agent system having a computational model with well-defined correctness criteria. Instead of hardwiring robustness and fault-tolerant behaviour into agent plans, well defined notions of correctness exist at the semantic level. Verification can then be undertaken at the desired level of abstraction. Two BDI interpreter prototypes have been developed to demonstrate the feasibility of our approach. The first, TOMAS, is a Java environment that execute intentions as "nested transactions". The second is a re-implementation of TOMAS within a J2EE application server, which can be used to develop session beans (i.e., business logic); it demonstrates how the model we propose nicely fits into a state-of-the-art environment for mission critical systems in domains such as e-business and Web service