Human-guided Collaborative Problem Solving: A Natural Language based Framework

TL;DR

This paper introduces a natural language-based framework for human-machine collaborative problem solving, integrating language parsing, concept learning, and hierarchical planning, demonstrated through a Minecraft-based building task.

Contribution

It presents a novel integrated framework combining natural language processing, concept learning, and hierarchical task planning for collaborative problem solving.

Findings

Successfully demonstrated on a Minecraft building task

Framework effectively handles natural language communication

Addresses key challenges in collaborative problem solving

Abstract

We consider the problem of human-machine collaborative problem solving as a planning task coupled with natural language communication. Our framework consists of three components -- a natural language engine that parses the language utterances to a formal representation and vice-versa, a concept learner that induces generalized concepts for plans based on limited interactions with the user, and an HTN planner that solves the task based on human interaction. We illustrate the ability of this framework to address the key challenges of collaborative problem solving by demonstrating it on a collaborative building task in a Minecraft-based blocksworld domain. The accompanied demo video is available at https://youtu.be/q1pWe4aahF0.