Learning Task Knowledge and its Scope of Applicability in Experience-Based Planning Domains
This work addresses the challenge of long-term learning and planning in robotics by providing a method to bound the applicability of learned knowledge, though it appears incremental as it extends previous work on EBPDs.
The paper tackles the problem of determining when learned task knowledge (activity schemata) can be applied in experience-based planning domains by using Three-Valued Logic Analysis to generate a scope of applicability as a 3-valued logical structure, enabling automatic schema selection for solving tasks in simulated and real-world robot domains.
Experience-based planning domains (EBPDs) have been recently proposed to improve problem solving by learning from experience. EBPDs provide important concepts for long-term learning and planning in robotics. They rely on acquiring and using task knowledge, i.e., activity schemata, for generating concrete solutions to problem instances in a class of tasks. Using Three-Valued Logic Analysis (TVLA), we extend previous work to generate a set of conditions as the scope of applicability for an activity schema. The inferred scope is a bounded representation of a set of problems of potentially unbounded size, in the form of a 3-valued logical structure, which allows an EBPD system to automatically find an applicable activity schema for solving task problems. We demonstrate the utility of our approach in a set of classes of problems in a simulated domain and a class of real world tasks in a fully physically simulated PR2 robot in Gazebo.