Automatic landing on a moving platform using deep neural network estimation

Toshinobu Watanabe, Eric Johnson

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

Abstract

This paper describes a control architecture designed to enable autonomous landing on a moving vehicle. This architecture can be separated into two parts: prediction and trajectory generation. For the prediction method, we use a Deep Neural Network (DNN), which can estimate multiple future states of the landing target by using past measurement data. For trajectory generation, we employ differential dynamic programming (DDP), which involves the interior penalty function with time-varying weight in the cost function. As a result, we can predict the state for a future time by using the multi-point prediction technique using DNN and generate the trajectory with time-varying weight using DPP. We provide the architecture of DNN and DDP with implementation techniques and sample results.

Original languageEnglish (US)
Title of host publication7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy
PublisherAmerican Helicopter Society International
StatePublished - Jan 1 2017
Event7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy - Mesa, United States
Duration: Jan 24 2017Jan 26 2017

Other

Other7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy
CountryUnited States
CityMesa
Period1/24/171/26/17

Fingerprint

Landing
Trajectories
Dynamic programming
Cost functions
Deep neural networks

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering

Cite this

Watanabe, T., & Johnson, E. (2017). Automatic landing on a moving platform using deep neural network estimation. In 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy American Helicopter Society International.
Watanabe, Toshinobu ; Johnson, Eric. / Automatic landing on a moving platform using deep neural network estimation. 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy. American Helicopter Society International, 2017.
@inproceedings{67a5590fb12e42d58f69f820b9abfa65,
title = "Automatic landing on a moving platform using deep neural network estimation",
abstract = "This paper describes a control architecture designed to enable autonomous landing on a moving vehicle. This architecture can be separated into two parts: prediction and trajectory generation. For the prediction method, we use a Deep Neural Network (DNN), which can estimate multiple future states of the landing target by using past measurement data. For trajectory generation, we employ differential dynamic programming (DDP), which involves the interior penalty function with time-varying weight in the cost function. As a result, we can predict the state for a future time by using the multi-point prediction technique using DNN and generate the trajectory with time-varying weight using DPP. We provide the architecture of DNN and DDP with implementation techniques and sample results.",
author = "Toshinobu Watanabe and Eric Johnson",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
booktitle = "7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy",
publisher = "American Helicopter Society International",

}

Watanabe, T & Johnson, E 2017, Automatic landing on a moving platform using deep neural network estimation. in 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy. American Helicopter Society International, 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy, Mesa, United States, 1/24/17.

Automatic landing on a moving platform using deep neural network estimation. / Watanabe, Toshinobu; Johnson, Eric.

7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy. American Helicopter Society International, 2017.

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

TY - GEN

T1 - Automatic landing on a moving platform using deep neural network estimation

AU - Watanabe, Toshinobu

AU - Johnson, Eric

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper describes a control architecture designed to enable autonomous landing on a moving vehicle. This architecture can be separated into two parts: prediction and trajectory generation. For the prediction method, we use a Deep Neural Network (DNN), which can estimate multiple future states of the landing target by using past measurement data. For trajectory generation, we employ differential dynamic programming (DDP), which involves the interior penalty function with time-varying weight in the cost function. As a result, we can predict the state for a future time by using the multi-point prediction technique using DNN and generate the trajectory with time-varying weight using DPP. We provide the architecture of DNN and DDP with implementation techniques and sample results.

AB - This paper describes a control architecture designed to enable autonomous landing on a moving vehicle. This architecture can be separated into two parts: prediction and trajectory generation. For the prediction method, we use a Deep Neural Network (DNN), which can estimate multiple future states of the landing target by using past measurement data. For trajectory generation, we employ differential dynamic programming (DDP), which involves the interior penalty function with time-varying weight in the cost function. As a result, we can predict the state for a future time by using the multi-point prediction technique using DNN and generate the trajectory with time-varying weight using DPP. We provide the architecture of DNN and DDP with implementation techniques and sample results.

UR - http://www.scopus.com/inward/record.url?scp=85032922077&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032922077&partnerID=8YFLogxK

M3 - Conference contribution

BT - 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy

PB - American Helicopter Society International

ER -

Watanabe T, Johnson E. Automatic landing on a moving platform using deep neural network estimation. In 7th AHS Technical Meeting on VTOL Unmanned Aircraft Systems and Autonomy. American Helicopter Society International. 2017