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