HUMAN INTENTION-DRIVEN ROBOT MOTION CONTROL IN COLLABORATIVE TASKS BASED ON THE THEORY OF COOPERATION, DA

Abstract

We propose an adaptive robot motion-control for safe Human-Robot collaborative tasks. We focus our research in active reasoning in the object-manipulation and human-robot interaction processes to solve a given task. We start with the object transportation task where a human and a robot jointly move an object to a target destination; the robot generates its trajectory using standard path planning techniques and actively modifies its behavior given the different user signals (e.g. a force input in its hand and the human motion s direction and velocity) as a measure of user intention. Furthermore, we plan to introduce the user-intention in the robot s reasoning system for collaborative tasks; to do this, we intend to evaluate different user signals and metrics to infer the human intention and apply probabilistic models based on game theory to successfully perform the task. Finally, we will introduce new and more complex collaborative tasks for domestic service robots, such as cleaning or cooking, and we will explore further human-intention signals (e.g. vision) and its interpretation from the robot perspective to be useful to solve such tasks.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 04, 2023
Source ID
FA23862214029

Entities

People

  • Hiroyuki Okada

Organizations

  • Air Force Office of Scientific Research
  • Tamagawa University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Industrial Economics
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Autonomy - Human-Robot Interaction