Strategic planning for autonomous systems over long horizons

Planning plays a role in achieving long-term behaviour (persistent autonomy) without human intervention. Such behaviour engenders plans which are expected to last over many hours, or even days. Such a problem is too large for current planners to solve as a single planning problem, but is well-suited to decomposition and abstraction planning techniques. We present a novel approach to bottom-up decomposition into a two-layer hierarchical structure, which dynamically constructs planning problems at the abstract layer of the hierarchy using solution plans from the lower layer. We evaluate this approach in the context of persistent autonomy in autonomous underwater vehicles, showing that compared to strictly top-down approaches the bottom-up approach leads to more robust solution plans of higher quality.