Research Output

Commonsense-enhanced Natural Language Generation for Human-Robot Interaction

  Commonsense is vital for human communication, as it allows us to make inferences without explicitly mentioning the context. Equipping robots with commonsense knowledge would lead to better communication between humans and robots and will allow robots to be introduced in real-world environments. However, this is an extremely hard task due to the complex interdisciplinary nature of the problem, which spans across several fields including natural language generation, reasoning, computer vision and robotics. Addressing this challenge will unlock a plethora of opportunities for assistive and care robotics, service robotics and novel educational and training applications, to tackle immediate challenges such as caring for the elderly population, upscale skills, automate tasks and increase productivity. This paper proposes the Robot-Commonsense challenge that goes beyond traditional multi-modal interaction (vi-sion, deictic gestures, language, gaze) and focuses on incorporating commonsense knowledge to enhance human-robot interaction.

  • Date:

    21 February 2020

  • Publication Status:

    Accepted

  • Funders:

    Engineering and Physical Sciences Research Council

Citation

Gkatzia, D. (in press). Commonsense-enhanced Natural Language Generation for Human-Robot Interaction

Authors

Keywords

human-robot interaction; commonsense; communication; robotics

Monthly Views:

Available Documents