On Guiding Search in HTN Temporal Planning with non Temporal Heuristics
This work addresses a gap in temporal HTN planning, which is incremental as it adapts non-temporal techniques to a temporal context.
The paper tackles the lack of formal definitions and heuristics for temporal Hierarchical Task Network (HTN) planning by proposing a new Partial Order Causal Link (POCL) approach that uses existing non-temporal heuristics, showing experimentally that it is performant and can outperform existing methods.
The Hierarchical Task Network (HTN) formalism is used to express a wide variety of planning problems as task decompositions, and many techniques have been proposed to solve them. However, few works have been done on temporal HTN. This is partly due to the lack of a formal and consensual definition of what a temporal hierarchical planning problem is as well as the difficulty to develop heuristics in this context. In response to these inconveniences, we propose in this paper a new general POCL (Partial Order Causal Link) approach to represent and solve a temporal HTN problem by using existing heuristics developed to solve non temporal problems. We show experimentally that this approach is performant and can outperform the existing ones.