Resumen de Context-aware plan repair in environments shared by multiple agents
Mohannad Babli
Execution Monitoring is crucial for the success of an autonomous agent executing a plan in a dynamic environment as it influences its ability to react to changes. While executing its plan in a dynamic world, it may suffer a failure and, in its endeavour to fix the problem, it may unknowingly disrupt other agents operating in the same environment. Additionally, being rational requires the agent to be context-aware, gather information and extend what is known from what is perceived to compensate for partial or incorrect prior knowledge and achieve the best possible outcome in various novel situations.
The work carried out in this PhD thesis allows the autonomous agents executing a plan in a dynamic environment to adapt to unexpected events and unfamiliar circumstances, utilise their perception of context and provide context-aware deliberative responses for seizing an opportunity or repairing a failure without disrupting other agents. This work is focused on developing a domain-independent architecture capable of handling the requirements of such autonomous behaviour. The architecture pillars are the intelligent system for execution simulation in a dynamic environment, the context-aware knowledge acquisition for planning applications and the plan commitment repair.
The intelligent system for execution simulation in a dynamic environment allows the agent to transform the plan into a timeline, periodically update its internal state with real-world information and create timed events. Events are processed in the context of the plan; if a failure occurs, the simulator reformulates the planning problem, reinvokes a planner and resumes the execution. The simulator is a console application and has a GUI designed specifically for smart tourism.
The context-aware knowledge acquisition module utilises semantic operations to dynamically augment the predefined list of object types of the planning task with relevant new object types. This allows the agent to be context-aware of the environment and the task and reason with incomplete knowledge, boosting the system's autonomy and context-awareness.
The novel plan commitment repair strategy among multiple agents sharing the same execution environment allows the agent to repair its plan responsibly when a failure is detected. The agent utilises a new metric, plan commitment, as a heuristic to guide the search for the most committed repair plan to the original plan from the perspective of commitments made to other agents whilst achieving the original goals. Consequently, the community of agents will suffer fewer failures due to the sudden changes or will have less lost time if the failure is inevitable.
All these developed modules were investigated and evaluated in several applications, such as a tourist assistant, a kitchen appliance repair agency and a living home assistant.
