Exploring Variation of Natural Human Commands to a Robot in a Collaborative Navigation Task

Abstract

Robot-directed communication is variable, and may change based on human perception of robot capabilities. To collect training data for a dialogue system and to investigate possible communication changes over time, we developed a Wizard-of-Oz study that (a) simulates a robots limited understanding, and (b) collects dialogues where human participants build a progressively better mental model of the robots understanding. With ten participants, we collected ten hours of human-robot dialogue. We analyzed the structure of instructions that participants gave to a remote robot before it responded. Our findings show a general initial preference for including metric information (e.g., move forward 3 feet) over landmarks(e.g., move to the desk) in motion commands, but this decreased over time, suggesting changes in perception.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 30, 2017
Accession Number
AD1158541

Entities

People

  • Ashley Foots
  • Cassidy Henry
  • Claire Bonial
  • Clare R. Voss
  • Cory Hayes
  • David R Traum
  • Kimberly A. Pollard
  • Matthew Marge
  • Ron Artstein

Organizations

  • United States Army Research Laboratory
  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Autonomous Navigation
  • Computational Linguistics
  • Control Systems
  • Dialogue Systems
  • Human-Robot Interaction
  • Instructions
  • Language
  • Linguistics
  • Machine Translation
  • Motion Planning
  • Natural Language Processing
  • Natural Languages
  • Navigation
  • Navigators
  • Robot Navigation
  • Robotics
  • Robots

Fields of Study

  • Computer science

Readers

  • Robotics and Automation.
  • Speech Processing/Speech Recognition.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy