Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Heecheol, Ohmura, Yoshiyuki, Nagakubo, Akihiko, Kuniyoshi, Yasuo
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913242021888000
author Kim, Heecheol
Ohmura, Yoshiyuki
Nagakubo, Akihiko
Kuniyoshi, Yasuo
author_facet Kim, Heecheol
Ohmura, Yoshiyuki
Nagakubo, Akihiko
Kuniyoshi, Yasuo
contents Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. In this study, deep imitation learning is applied to tasks that require force feedback. However, existing demonstration methods have deficiencies; bilateral teleoperation requires a complex control scheme and is expensive, and kinesthetic teaching suffers from visual distractions from human intervention. This research proposes a new master-to-robot (M2R) policy transfer system that does not require robots for teaching force feedback-based manipulation tasks. The human directly demonstrates a task using a controller. This controller resembles the kinematic parameters of the robot arm and uses the same end-effector with force/torque (F/T) sensors to measure the force feedback. Using this controller, the operator can feel force feedback without a bilateral system. The proposed method can overcome domain gaps between the master and robot using gaze-based imitation learning and a simple calibration method. Furthermore, a Transformer is applied to infer policy from F/T sensory input. The proposed system was evaluated on a bottle-cap-opening task that requires force feedback.
format Preprint
id arxiv_https___arxiv_org_abs_2202_09574
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer
Kim, Heecheol
Ohmura, Yoshiyuki
Nagakubo, Akihiko
Kuniyoshi, Yasuo
Robotics
Artificial Intelligence
Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. In this study, deep imitation learning is applied to tasks that require force feedback. However, existing demonstration methods have deficiencies; bilateral teleoperation requires a complex control scheme and is expensive, and kinesthetic teaching suffers from visual distractions from human intervention. This research proposes a new master-to-robot (M2R) policy transfer system that does not require robots for teaching force feedback-based manipulation tasks. The human directly demonstrates a task using a controller. This controller resembles the kinematic parameters of the robot arm and uses the same end-effector with force/torque (F/T) sensors to measure the force feedback. Using this controller, the operator can feel force feedback without a bilateral system. The proposed method can overcome domain gaps between the master and robot using gaze-based imitation learning and a simple calibration method. Furthermore, a Transformer is applied to infer policy from F/T sensory input. The proposed system was evaluated on a bottle-cap-opening task that requires force feedback.
title Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2202.09574