Natural Language for Human-Robot Collaboration: Problems Beyond Language Grounding

TL;DR

This paper explores complex language processing aspects like location, planning, and generation to improve human-robot collaboration, providing evaluation methods, baselines, and discussing future challenges.

Contribution

It highlights underexplored language tasks in human-robot collaboration and proposes evaluation frameworks and baselines for these challenges.

Findings

Proposes evaluation methods for language tasks in collaboration

Provides baseline models for location, planning, and generation

Discusses future research challenges and opportunities

Abstract

To enable robots to instruct humans in collaborations, we identify several aspects of language processing that are not commonly studied in this context. These include location, planning, and generation. We suggest evaluations for each task, offer baselines for simple methods, and close by discussing challenges and opportunities in studying language for collaboration.