Vision-based optimal landing on a moving platform

Takuma Nakamura, Stephen Haviland, Dmitry Bershadsky, Eric N. Johnson

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

4 Citations (Scopus)

Abstract

This paper describes a vision-based control architecture designed to enable autonomous landing on a moving platform. The landing trajectory is generated by using the receding-horizon differential dynamic programming (DDP), an optimal control method. The trajectory generation is aided by the output of a vision-based target tracking system. The vision system uses multiple extended Kalman filters which allows us to estimate the position and heading of the moving target via the observed locations. The combination of vision-based target tracking system and the receding-horizon DDP gives an unmanned aerial vehicle the capability to adaptively generate a landing trajectory against tracking errors and disturbances. Additionally, by adding the exterior penalty function to the cost of the DDP we can easily constrain the trajectory from collisions and physically infeasible solutions. We provide key mathematics needed for the implementation and share the results of the image-in-the-loop simulation and flight tests to validate the suggested methodology.

Original languageEnglish (US)
Title of host publication72nd American Helicopter Society International Annual Forum 2016
Subtitle of host publicationLeveraging Emerging Technologies for Future Capabilities
PublisherAmerican Helicopter Society
Pages3331-3341
Number of pages11
ISBN (Electronic)9781510825062
StatePublished - Jan 1 2016

Publication series

NameAnnual Forum Proceedings - AHS International
Volume4
ISSN (Print)1552-2938

Fingerprint

Landing
Dynamic programming
Trajectories
Target tracking
Extended Kalman filters
Unmanned aerial vehicles (UAV)
Costs

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Nakamura, T., Haviland, S., Bershadsky, D., & Johnson, E. N. (2016). Vision-based optimal landing on a moving platform. In 72nd American Helicopter Society International Annual Forum 2016: Leveraging Emerging Technologies for Future Capabilities (pp. 3331-3341). (Annual Forum Proceedings - AHS International; Vol. 4). American Helicopter Society.
Nakamura, Takuma ; Haviland, Stephen ; Bershadsky, Dmitry ; Johnson, Eric N. / Vision-based optimal landing on a moving platform. 72nd American Helicopter Society International Annual Forum 2016: Leveraging Emerging Technologies for Future Capabilities. American Helicopter Society, 2016. pp. 3331-3341 (Annual Forum Proceedings - AHS International).
@inproceedings{1908d71d94104c109e09e7881641e4b5,
title = "Vision-based optimal landing on a moving platform",
abstract = "This paper describes a vision-based control architecture designed to enable autonomous landing on a moving platform. The landing trajectory is generated by using the receding-horizon differential dynamic programming (DDP), an optimal control method. The trajectory generation is aided by the output of a vision-based target tracking system. The vision system uses multiple extended Kalman filters which allows us to estimate the position and heading of the moving target via the observed locations. The combination of vision-based target tracking system and the receding-horizon DDP gives an unmanned aerial vehicle the capability to adaptively generate a landing trajectory against tracking errors and disturbances. Additionally, by adding the exterior penalty function to the cost of the DDP we can easily constrain the trajectory from collisions and physically infeasible solutions. We provide key mathematics needed for the implementation and share the results of the image-in-the-loop simulation and flight tests to validate the suggested methodology.",
author = "Takuma Nakamura and Stephen Haviland and Dmitry Bershadsky and Johnson, {Eric N.}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
series = "Annual Forum Proceedings - AHS International",
publisher = "American Helicopter Society",
pages = "3331--3341",
booktitle = "72nd American Helicopter Society International Annual Forum 2016",
address = "United States",

}

Nakamura, T, Haviland, S, Bershadsky, D & Johnson, EN 2016, Vision-based optimal landing on a moving platform. in 72nd American Helicopter Society International Annual Forum 2016: Leveraging Emerging Technologies for Future Capabilities. Annual Forum Proceedings - AHS International, vol. 4, American Helicopter Society, pp. 3331-3341.

Vision-based optimal landing on a moving platform. / Nakamura, Takuma; Haviland, Stephen; Bershadsky, Dmitry; Johnson, Eric N.

72nd American Helicopter Society International Annual Forum 2016: Leveraging Emerging Technologies for Future Capabilities. American Helicopter Society, 2016. p. 3331-3341 (Annual Forum Proceedings - AHS International; Vol. 4).

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

TY - GEN

T1 - Vision-based optimal landing on a moving platform

AU - Nakamura, Takuma

AU - Haviland, Stephen

AU - Bershadsky, Dmitry

AU - Johnson, Eric N.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This paper describes a vision-based control architecture designed to enable autonomous landing on a moving platform. The landing trajectory is generated by using the receding-horizon differential dynamic programming (DDP), an optimal control method. The trajectory generation is aided by the output of a vision-based target tracking system. The vision system uses multiple extended Kalman filters which allows us to estimate the position and heading of the moving target via the observed locations. The combination of vision-based target tracking system and the receding-horizon DDP gives an unmanned aerial vehicle the capability to adaptively generate a landing trajectory against tracking errors and disturbances. Additionally, by adding the exterior penalty function to the cost of the DDP we can easily constrain the trajectory from collisions and physically infeasible solutions. We provide key mathematics needed for the implementation and share the results of the image-in-the-loop simulation and flight tests to validate the suggested methodology.

AB - This paper describes a vision-based control architecture designed to enable autonomous landing on a moving platform. The landing trajectory is generated by using the receding-horizon differential dynamic programming (DDP), an optimal control method. The trajectory generation is aided by the output of a vision-based target tracking system. The vision system uses multiple extended Kalman filters which allows us to estimate the position and heading of the moving target via the observed locations. The combination of vision-based target tracking system and the receding-horizon DDP gives an unmanned aerial vehicle the capability to adaptively generate a landing trajectory against tracking errors and disturbances. Additionally, by adding the exterior penalty function to the cost of the DDP we can easily constrain the trajectory from collisions and physically infeasible solutions. We provide key mathematics needed for the implementation and share the results of the image-in-the-loop simulation and flight tests to validate the suggested methodology.

UR - http://www.scopus.com/inward/record.url?scp=85001576990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85001576990&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85001576990

T3 - Annual Forum Proceedings - AHS International

SP - 3331

EP - 3341

BT - 72nd American Helicopter Society International Annual Forum 2016

PB - American Helicopter Society

ER -

Nakamura T, Haviland S, Bershadsky D, Johnson EN. Vision-based optimal landing on a moving platform. In 72nd American Helicopter Society International Annual Forum 2016: Leveraging Emerging Technologies for Future Capabilities. American Helicopter Society. 2016. p. 3331-3341. (Annual Forum Proceedings - AHS International).