Control proprioception for robust autonomous systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper show how neural networks, configured for regression, can be used to learn the relationships between Inertial Motion Unit (IMU) data collected on a robotic platform and the robot's commanded system state. By learning how the IMU data relates to commanded robot state we can use the neural network to predict what commands have been issued to the robot. By comparing the prediction to the actual commands we can determine if the perceived behavior of our robot matches the commanded behavior. This enables the vehicle to identify issues with control and potentially take corrective actions needed to enable long-duration autonomy.

Original languageEnglish (US)
Title of host publicationOCEANS 2017 � Anchorage
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
Volume2017-January
ISBN (Electronic)9780692946909
StatePublished - Dec 19 2017
EventOCEANS 2017 - Anchorage - Anchorage, United States
Duration: Sep 18 2017Sep 21 2017

Other

OtherOCEANS 2017 - Anchorage
CountryUnited States
CityAnchorage
Period9/18/179/21/17

Fingerprint

proprioception
robots
Robots
commands
robotics
autonomy
learning
Neural networks
prediction
regression analysis
vehicles
Robotics
platforms
predictions

All Science Journal Classification (ASJC) codes

  • Oceanography
  • Automotive Engineering
  • Water Science and Technology
  • Acoustics and Ultrasonics
  • Instrumentation
  • Ocean Engineering

Cite this

Homan, E., & Sustersic, Jr., J. P. (2017). Control proprioception for robust autonomous systems. In OCEANS 2017 � Anchorage (Vol. 2017-January, pp. 1-5). Institute of Electrical and Electronics Engineers Inc..
Homan, Eric ; Sustersic, Jr., John Phillip. / Control proprioception for robust autonomous systems. OCEANS 2017 � Anchorage. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-5
@inproceedings{b90bb54d0d194e609e8acfba0393f1c9,
title = "Control proprioception for robust autonomous systems",
abstract = "This paper show how neural networks, configured for regression, can be used to learn the relationships between Inertial Motion Unit (IMU) data collected on a robotic platform and the robot's commanded system state. By learning how the IMU data relates to commanded robot state we can use the neural network to predict what commands have been issued to the robot. By comparing the prediction to the actual commands we can determine if the perceived behavior of our robot matches the commanded behavior. This enables the vehicle to identify issues with control and potentially take corrective actions needed to enable long-duration autonomy.",
author = "Eric Homan and {Sustersic, Jr.}, {John Phillip}",
year = "2017",
month = "12",
day = "19",
language = "English (US)",
volume = "2017-January",
pages = "1--5",
booktitle = "OCEANS 2017 � Anchorage",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Homan, E & Sustersic, Jr., JP 2017, Control proprioception for robust autonomous systems. in OCEANS 2017 � Anchorage. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, OCEANS 2017 - Anchorage, Anchorage, United States, 9/18/17.

Control proprioception for robust autonomous systems. / Homan, Eric; Sustersic, Jr., John Phillip.

OCEANS 2017 � Anchorage. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-5.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Control proprioception for robust autonomous systems

AU - Homan, Eric

AU - Sustersic, Jr., John Phillip

PY - 2017/12/19

Y1 - 2017/12/19

N2 - This paper show how neural networks, configured for regression, can be used to learn the relationships between Inertial Motion Unit (IMU) data collected on a robotic platform and the robot's commanded system state. By learning how the IMU data relates to commanded robot state we can use the neural network to predict what commands have been issued to the robot. By comparing the prediction to the actual commands we can determine if the perceived behavior of our robot matches the commanded behavior. This enables the vehicle to identify issues with control and potentially take corrective actions needed to enable long-duration autonomy.

AB - This paper show how neural networks, configured for regression, can be used to learn the relationships between Inertial Motion Unit (IMU) data collected on a robotic platform and the robot's commanded system state. By learning how the IMU data relates to commanded robot state we can use the neural network to predict what commands have been issued to the robot. By comparing the prediction to the actual commands we can determine if the perceived behavior of our robot matches the commanded behavior. This enables the vehicle to identify issues with control and potentially take corrective actions needed to enable long-duration autonomy.

UR - http://www.scopus.com/inward/record.url?scp=85048202018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048202018&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2017-January

SP - 1

EP - 5

BT - OCEANS 2017 � Anchorage

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Homan E, Sustersic, Jr. JP. Control proprioception for robust autonomous systems. In OCEANS 2017 � Anchorage. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-5