Extracting task trees using knowledge retrieval search algorithms in functional object-oriented network

TL;DR

This paper compares iterative deepening search and greedy best-first search algorithms in extracting task trees from a functional object-oriented network for robotic task planning, analyzing their efficiency across various recipes.

Contribution

It evaluates and compares two search algorithms for task tree extraction in FOON, highlighting their performance differences based on recipe complexity.

Findings

IDS performs better on complex recipes

GBFS is more efficient on simpler recipes

Algorithm choice depends on recipe complexity

Abstract

The functional object-oriented network (FOON) has been developed as a knowledge representation method that can be used by robots in order to perform task planning. A FOON can be observed as a graph that can provide an ordered plan for robots to retrieve a task tree, through the knowledge retrieval process. We compare two search algorithms to evaluate their performance in extracting task trees: iterative deepening search (IDS) and greedy best-first search (GBFS) with two different heuristic functions. Then, we determine which algorithm is capable of obtaining a task tree for various cooking recipes using the least number of functional units. Preliminary results show that each algorithm can perform better than the other, depending on the recipe provided to the search algorithm.