Demonstrating Social Error Recovery with AgentFactory

Exception handling is a well established method of error recovery through the alteration of plans in situ . This method relies on recovery routines existing in advance, which - we argue - is simply shorthand for more detailed plan descriptions. However, in practice, agents rarely act alone in their environment - other agents may exist, and potentially provide help in times of need. We argue that social error recovery is a particular class of exception handling that allows agents to resolve erroneous situations that are beyond their direct control. In our opinion, agent oriented programming languages must directly provide agents with abilities like social error recovery. Consequently, we introduce revisions to the AgentFactory framework, and more specifically, the programming language (AF-APL), which facilitate the rapid development of agents with in-built social error recovery. The use of these abilities are illustrated via an example of a social error recovery scenario for a mobile robot working as an office assistant.