Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search

Yagiz E. Bayiz, Long Chen, Shih Jung Hsu, Pan Liu, Aaron N. Aguiles, Bo Cheng

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

2 Citations (Scopus)

Abstract

In this work, we present a successful application of a policy search algorithm to a real-time robotic learning problem, where the goal is to maximize the efficiency of lift generation on a dynamically scaled flapping robotic wing. The robotic wing has two degrees-of-freedom, i.e., stroke and pitch, and operates in a tank filled with mineral oil. For all experiments, the Reynolds number is maintained constant at 1000, where learning is performed for different prescribed stroke amplitudes to find the optimal wing pitching amplitude and the stroke-pitch phase difference that maximize the power loading (PL) of lift generation, a measure of aerodynamic efficiency. For the investigated stroke amplitude range (30°-90°), the efficiency is observed to increase with the stroke amplitude and the lift is mainly generated through the delayed stall, a quasi-steady aerodynamic mechanism. Furthermore, the wing rotation becomes more asymmetric with respect to stroke reversal as the stroke amplitude decreases, indicating an increased use of unsteady lift generation mechanisms at lower stroke amplitudes.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5519-5525
Number of pages7
ISBN (Electronic)9781538630815
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
Duration: May 21 2018May 25 2018

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
CountryAustralia
CityBrisbane
Period5/21/185/25/18

Fingerprint

Robotics
Aerodynamics
Mineral oils
Degrees of freedom (mechanics)
Reynolds number
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Bayiz, Y. E., Chen, L., Hsu, S. J., Liu, P., Aguiles, A. N., & Cheng, B. (2018). Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 5519-5525). [8460781] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8460781
Bayiz, Yagiz E. ; Chen, Long ; Hsu, Shih Jung ; Liu, Pan ; Aguiles, Aaron N. ; Cheng, Bo. / Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 5519-5525 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{01881093857e47c2b7abf4d805064495,
title = "Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search",
abstract = "In this work, we present a successful application of a policy search algorithm to a real-time robotic learning problem, where the goal is to maximize the efficiency of lift generation on a dynamically scaled flapping robotic wing. The robotic wing has two degrees-of-freedom, i.e., stroke and pitch, and operates in a tank filled with mineral oil. For all experiments, the Reynolds number is maintained constant at 1000, where learning is performed for different prescribed stroke amplitudes to find the optimal wing pitching amplitude and the stroke-pitch phase difference that maximize the power loading (PL) of lift generation, a measure of aerodynamic efficiency. For the investigated stroke amplitude range (30°-90°), the efficiency is observed to increase with the stroke amplitude and the lift is mainly generated through the delayed stall, a quasi-steady aerodynamic mechanism. Furthermore, the wing rotation becomes more asymmetric with respect to stroke reversal as the stroke amplitude decreases, indicating an increased use of unsteady lift generation mechanisms at lower stroke amplitudes.",
author = "Bayiz, {Yagiz E.} and Long Chen and Hsu, {Shih Jung} and Pan Liu and Aguiles, {Aaron N.} and Bo Cheng",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICRA.2018.8460781",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5519--5525",
booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",
address = "United States",

}

Bayiz, YE, Chen, L, Hsu, SJ, Liu, P, Aguiles, AN & Cheng, B 2018, Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8460781, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 5519-5525, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 5/21/18. https://doi.org/10.1109/ICRA.2018.8460781

Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search. / Bayiz, Yagiz E.; Chen, Long; Hsu, Shih Jung; Liu, Pan; Aguiles, Aaron N.; Cheng, Bo.

2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 5519-5525 8460781 (Proceedings - IEEE International Conference on Robotics and Automation).

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

TY - GEN

T1 - Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search

AU - Bayiz, Yagiz E.

AU - Chen, Long

AU - Hsu, Shih Jung

AU - Liu, Pan

AU - Aguiles, Aaron N.

AU - Cheng, Bo

PY - 2018/9/10

Y1 - 2018/9/10

N2 - In this work, we present a successful application of a policy search algorithm to a real-time robotic learning problem, where the goal is to maximize the efficiency of lift generation on a dynamically scaled flapping robotic wing. The robotic wing has two degrees-of-freedom, i.e., stroke and pitch, and operates in a tank filled with mineral oil. For all experiments, the Reynolds number is maintained constant at 1000, where learning is performed for different prescribed stroke amplitudes to find the optimal wing pitching amplitude and the stroke-pitch phase difference that maximize the power loading (PL) of lift generation, a measure of aerodynamic efficiency. For the investigated stroke amplitude range (30°-90°), the efficiency is observed to increase with the stroke amplitude and the lift is mainly generated through the delayed stall, a quasi-steady aerodynamic mechanism. Furthermore, the wing rotation becomes more asymmetric with respect to stroke reversal as the stroke amplitude decreases, indicating an increased use of unsteady lift generation mechanisms at lower stroke amplitudes.

AB - In this work, we present a successful application of a policy search algorithm to a real-time robotic learning problem, where the goal is to maximize the efficiency of lift generation on a dynamically scaled flapping robotic wing. The robotic wing has two degrees-of-freedom, i.e., stroke and pitch, and operates in a tank filled with mineral oil. For all experiments, the Reynolds number is maintained constant at 1000, where learning is performed for different prescribed stroke amplitudes to find the optimal wing pitching amplitude and the stroke-pitch phase difference that maximize the power loading (PL) of lift generation, a measure of aerodynamic efficiency. For the investigated stroke amplitude range (30°-90°), the efficiency is observed to increase with the stroke amplitude and the lift is mainly generated through the delayed stall, a quasi-steady aerodynamic mechanism. Furthermore, the wing rotation becomes more asymmetric with respect to stroke reversal as the stroke amplitude decreases, indicating an increased use of unsteady lift generation mechanisms at lower stroke amplitudes.

UR - http://www.scopus.com/inward/record.url?scp=85049839404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049839404&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2018.8460781

DO - 10.1109/ICRA.2018.8460781

M3 - Conference contribution

AN - SCOPUS:85049839404

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 5519

EP - 5525

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bayiz YE, Chen L, Hsu SJ, Liu P, Aguiles AN, Cheng B. Real-Time Learning of Efficient Lift Generation on a Dynamically Scaled Flapping Wing Using Policy Search. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 5519-5525. 8460781. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8460781