PELEA: a Domain-Independent Architecture for Planning, Execution and Learning

摘要

One of the current limitations for large-scale use of planning technology in real world applications is the lack of software platforms to integrate the full spectrum of planning-related technologies: sensing, planning, executing, monitoring, re-planning and learning from past experiences. In this paper, we present PELEA, a domain-independent online planning architecture that includes state-of-the-art components for performing a wide range of (meta-)planning tasks, such as learning of control knowledge or low-level planning among many others. PELEA is conceived as a general-purpose architecture suitable for problems ranging from robotics to emergency management. PELEA is also intended to provide a rapid prototyping life-cycle for building planning applications and support planning practitioners with a highly-configurable tool.