Leveraging Virtual Reality to Identify Personalized Control Schemes for Teleoperating Non-Anthropomorphic Robots
Author(s)
Molnar, Jennifer
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Virtual reality (VR) has emerged as a popular teleoperation interface for robotic systems due to the immersive nature of VR interactions. In VR, users use their hands (or hand-held controllers) to interact with the environment. However, just as living animals have evolved
specialized embodiments that differ from those of a human (e.g. tentacles, wings, prehensile tails, etc.), specialized robotic systems are often designed with non-anthropomorphic embodiments (e.g. treads, wheels, arms with differing degrees of freedom, etc.). Such differences in embodiment between human hands and the robot introduce challenges for the design of intuitive user teleoperation interfaces.
This dissertation focuses on designing control schemes for teleoperating non-anthropomorphic robots and specifically investigates the hypothesis that users’ demonstrated preferences can provide a basis for functional, personalized control schemes. Specifically, my work will contribute:
• A comprehensive survey of control scheme designs for teleoperating both real and virtual non-anthropomorphic robots, to characterize common design principles and identify unexplored research areas.
• A VR “puppet-master” platform for identifying and validating user-generated mappings between a user’s hand and a simulated robot.
• An overview of users’ default control scheme preferences and rationales for an
example anthropomorphic and non-anthropomorphic robot arm, revealing features of a control scheme that are likely to benefit from personalization.
• An analysis of model prediction error for control schemes trained on single or
multiple participants and gestures, highlighting cases for which group-wise personalization is feasible and cases for which more data or more sophisticated processing methods are necessary.
Sponsor
Date
2024-04-24
Extent
Resource Type
Text
Resource Subtype
Dissertation