Skip to content

Datasets for Goal and Plan Recognition using Classical Planning Domains.

Notifications You must be signed in to change notification settings

pucrs-automated-planning/goal-plan-recognition-dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Goal and Plan Recognition Dataset

DOI

This repository contains datasets for goal and plan recognition as planning.

We created these datasets to evaluate goal/plan recognition approaches that use planning techniques.

We added 15 datasets with missing and full observations, and 4 datasets with missing and noisy observations.

Each .tar.bz2 file represents a goal/plan recognition problem, containing a domain description (domain.pddl), an initial state (template.pddl), a set of candidate goals (hyps.dat), a correct hidden goal in the set of candidate goals (real_hyp.dat), and an observation sequence (obs.dat). An observation sequence contains actions that represent an optimal plan or sub-optimal plan that achieves a correct hidden goal, and this observation sequence can be full or partial. A full observation sequence represents the whole plan for a hidden goal, i.e., 100% of the actions having been observed. A partial observation sequence contains missing observations and represents a plan for a correct hidden goal with 10%, 30%, 50%, or 70% of its actions having been observed. For goal/plan recognition problems with noisy observations, the observability of partial observations is quite different because every observation sequence always includes 2 noisy observations, so a partial observation sequence with noisy observations represents a plan with 25%, 50%, or 75% of its actions having been observed.

These datasets were used in the experiments described in Landmark-Based Heuristics for Goal Recognition.