Increasing Robot Autonomy via Motion Planning and an Augmented Reality Interface

J. D. Hernández, S. Sobti, A. Sciola, M. Moll, and L. E. Kavraki, “Increasing Robot Autonomy via Motion Planning and an Augmented Reality Interface,” IEEE Robotics and Automation Letters, 2020.

Abstract

Recently, there has been a growing interest in robotic systems that are able to share workspaces and collaborate with humans. Such collaborative scenarios require efficient mechanisms to communicate human requests to a robot, as well as to transmit robot interpretations and intents to humans. Recent advances in augmented reality (AR) technologies have provided an alternative for such communication. Nonetheless, most of the existing work in human-robot interaction with AR devices is still limited to robot motion programming or teleoperation. In this paper, we present an alternative approach to command and collaborate with robots. Our approach uses an AR interface that allows a user to specify high-level requests to a robot, to preview, approve or modify the computed robot motions. The proposed approach exploits the robot’s decisionmaking capabilities instead of requiring low-level motion specifications provided by the user. The latter is achieved by using a motion planner that can deal with high-level goals corresponding to regions in the robot configuration space. We present a proof of concept to validate our approach in different test scenarios, and we present a discussion of its applicability in collaborative environments.

PDF preprint: http://kavrakilab.org/publications/hernandez2020increasing-robot-autonomy-via-motion.pdf