No abstract

The close integration of planning and execution is a challenging problem. Key questions are how to organize and explicitly represent the program flow to enable reasoning about it, how to dynamically create goals from run-time information and decide on-line which to pursue, and how to unify representations used during planning and execution.In this work, we present an integrated system that uses a goal reasoning model which represents this flow and supports dynamic goal generation. With an explicit world model representation, it enables reasoning about the current state of the world, the progress of the execution flow, and what goals should be pursued – or postponed or abandoned. Our executive implements a specific goal lifecycle with compound goal types that combine sub-goals by conjunctions, disjunctions, concurrency, or that impose temporal constraints.Goals also provide a frame of reference for execution monitoring. The current system can utilize PDDL as the underlying modeling language with extensions to aid execution, and it contains well-defined extension points for domain-specific code. It has been used successfully in several scenarios.

To solve ever more complex and longer tasks, mobile robots need to generate more elaborate plans and must handle dynamic environments and incomplete knowledge. We address this challenge by integrating two seemingly different approaches — PDDL-based planning for efficient plan generation and Golog for highly expressive behavior specification — in a coherent framework that supports continual planning. The latter allows to interleave plan generation and execution through assertions, which are placeholder actions that are dynamically expanded into conditional sub-plans (using classical planners) once a replanning condition is satisfied. We formalize and implement continual planning in Golog which was so far only supported in PDDL-based systems. This enables combining the execution of generated plans with regular Golog programs and execution monitoring. Experiments on autonomous mobile robots show that the approach supports expressive behavior specification combined with efficient sub-plan generation to handle dynamic environments and incomplete knowledge in a unified way.

Planning in an on-line robotics context has the specific requirement of a short planning duration. A property of typical contemporary scenarios is that (mobile) robots perform similar or even repeating tasks during operation. With these robot domains in mind, we propose database-driven macroplanning for STRIPS (DBMP/S) that learns macros – action sequences that frequently appear in plans – from experience for PDDL-based planners. Planning duration is improved over time by off-line processing of seed plans using a scalable database. The approach is indifferent about the specific planner by representing the resulting macros again as actions with preconditions and effects determined based on the actions contained in the macro. For some domains we have used separate planners for learning and execution exploiting their respective strengths. Initial results based on some IPC domains and a logistic robot scenario show significantly improved (over non-macro planners) or slightly better and comparable (to existing macro planners) performance.