Goal-Driven Autonomy with Semantically-Annotated Hierarchical Cases
نویسندگان
چکیده
We present LUiGi-H a goal-driven autonomy (GDA) agent. Like other GDA agents it introspectively reasons about its own expectations to formulate new goals. Unlike other GDA agents, LUiGi-H uses cases consisting of hierarchical plans and semantic annotations of the expectations of those plans. Expectations indicate conditions that must be true when parts of the plan are executed. Using an ontology, semantic annotations are defined via inferred facts enabling LUiGi-H to reason with GDA elements at different levels of abstraction. We compared LUiGi-H against an ablated version, LUiGi, that uses non-hierarchal cases. Both agents have access to the same base-level (i.e. non-hierarchical plans), while only LUiGi-H makes use of hierarchical plans. In our experiments, LUiGi-H outperforms LUiGi.
منابع مشابه
Bounded Expectations for Discrepancy Detection in Goal-Driven Autonomy
Goal-Driven Autonomy (GDA) is a model for online planning extended with dynamic goal selection. GDA has been investigated in the context of numerous abstract planning domains, and there has been recent interest in applying GDA to control unmanned vehicles. In robotic domains, certain continuous state features from sensor data must be modeled for reasoning. However, modeling these features preci...
متن کاملHierarchical Goal Networks and Goal-Driven Autonomy: Going where AI Planning Meets Goal Reasoning
Planning systems are typically told what goals to pursue and cannot modify them. Some methods (e.g., for contingency planning, dynamic replanning) can respond to execution failures, but usually ignore opportunities and do not reason about the goals themselves. Goal-Driven Autonomy (GDA) relaxes some common assumptions of classical planning (e.g., static environments, fixed goals, no unpredictab...
متن کاملGoal-Driven Autonomy in a Navy Strategy Simulation
Modern complex games and simulations pose many challenges for an intelligent agent, including partial observability, continuous time and effects, hostile opponents, and exogenous events. We present ARTUE (Autonomous Response to Unexpected Events), a domainindependent autonomous agent that dynamically reasons about what goals to pursue in response to unexpected circumstances in these types of en...
متن کاملApplying Goal Driven Autonomy to a Team Shooter Game
Dynamic changes in complex, real-time environments, such as modern video games, can violate an agent’s expectations. We describe a system that responds competently to such violations by changing its own goals, using an algorithm based on a conceptual model for goal driven autonomy. We describe this model, clarify when such behavior is beneficial, and describe our system (which employs an HTN pl...
متن کاملExtending a Verb-lexicon Using a Semantically Annotated Corpus
This paper describes the association of an hierarchical verb lexicon, VerbNet, with a semantically annotated corpus, the Proposition Bank. It focuses on comparisons of the syntactic coverage of the two resources as a method of evaluating their correspondence. Both VerbNet and PropBank have explicit syntactic frames associated with each verb, which allowed an automatic mapping between the two re...
متن کامل