Evaluating Recipes Generated from Functional Object-Oriented Network
This addresses the need for reliable evaluation methods in robotic task planning, but it is incremental as it builds on existing knowledge representations and datasets.
The study tackled the problem of evaluating task trees from a functional object-oriented network (FOON) by converting them to recipes and comparing them to human-created ones in Recipe1M+. The result showed no significant difference in correctness, completeness, and clarity between the two.
The functional object-oriented network (FOON) has been introduced as a knowledge representation, which takes the form of a graph, for symbolic task planning. To get a sequential plan for a manipulation task, a robot can obtain a task tree through a knowledge retrieval process from the FOON. To evaluate the quality of an acquired task tree, we compare it with a conventional form of task knowledge, such as recipes or manuals. We first automatically convert task trees to recipes, and we then compare them with the human-created recipes in the Recipe1M+ dataset via a survey. Our preliminary study finds no significant difference between the recipes in Recipe1M+ and the recipes generated from FOON task trees in terms of correctness, completeness, and clarity.