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.
@article{arxiv.2207.09566,
title = {Human-guided Collaborative Problem Solving: A Natural Language based Framework},
author = {Harsha Kokel and Mayukh Das and Rakibul Islam and Julia Bonn and Jon Cai and Soham Dan and Anjali Narayan-Chen and Prashant Jayannavar and Janardhan Rao Doppa and Julia Hockenmaier and Sriraam Natarajan and Martha Palmer and Dan Roth},
journal= {arXiv preprint arXiv:2207.09566},
year = {2022}
}