Utilizing Hidden Markov Models to Classify Maneuvers and Improve Estimates of an Unmanned Aerial Vehicle. Strong, A. K., Martin, S. M., & Bevly, D. M. In IFAC-PapersOnLine, volume 54, of Modeling, Estimation and Control Conference MECC 2021, pages 449–454, January, 2021.
![Utilizing Hidden Markov Models to Classify Maneuvers and Improve Estimates of an Unmanned Aerial Vehicle [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex
Paper doi abstract bibtex Estimating the states of a Unmanned Aerial Vehicle (UAV) without the use of onboard sensors can be difficult, particularly if the UAV is performing high dynamic maneuvers. This paper examines if data driven modelling can assist in estimating UAV states, as well as classification of UAV maneuvers. A standard Extended Kalman Filter (EKF) that uses radar measurements and a constant acceleration dynamic model is used as the baseline estimation technique for dynamic UAV maneuvers. The UAV maneuvers are then modelled as Hidden Markov Models (HMM), which classify maneuvers and generate additional state information in the form of acceleration and jerk estimates. These HMM estimates are incorporated into an EKF to create a fusion EKF+HMM. This paper evaluates the robustness of the HMM classification accuracy and compares the EKF+HMM to a standard EKF using both simulated and experimental data.
@inproceedings{strong_utilizing_2021,
series = {Modeling, {Estimation} and {Control} {Conference} {MECC} 2021},
title = {Utilizing {Hidden} {Markov} {Models} to {Classify} {Maneuvers} and {Improve} {Estimates} of an {Unmanned} {Aerial} {Vehicle}},
volume = {54},
url = {https://www.sciencedirect.com/science/article/pii/S2405896321022588},
doi = {10.1016/j.ifacol.2021.11.214},
abstract = {Estimating the states of a Unmanned Aerial Vehicle (UAV) without the use of onboard sensors can be difficult, particularly if the UAV is performing high dynamic maneuvers. This paper examines if data driven modelling can assist in estimating UAV states, as well as classification of UAV maneuvers. A standard Extended Kalman Filter (EKF) that uses radar measurements and a constant acceleration dynamic model is used as the baseline estimation technique for dynamic UAV maneuvers. The UAV maneuvers are then modelled as Hidden Markov Models (HMM), which classify maneuvers and generate additional state information in the form of acceleration and jerk estimates. These HMM estimates are incorporated into an EKF to create a fusion EKF+HMM. This paper evaluates the robustness of the HMM classification accuracy and compares the EKF+HMM to a standard EKF using both simulated and experimental data.},
urldate = {2024-06-20},
booktitle = {{IFAC}-{PapersOnLine}},
author = {Strong, Amy K. and Martin, Scott M. and Bevly, David M.},
month = jan,
year = {2021},
keywords = {Aerospace Estimation, Estimation, Filtering, Gaussian Mixture Model, Hidden Markov Model, Mechanical, Time Series Modelling},
pages = {449--454},
}Downloads: 0
{"_id":"6TuN34rpeuRprNYgy","bibbaseid":"strong-martin-bevly-utilizinghiddenmarkovmodelstoclassifymaneuversandimproveestimatesofanunmannedaerialvehicle-2021","author_short":["Strong, A. K.","Martin, S. M.","Bevly, D. M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","series":"Modeling, Estimation and Control Conference MECC 2021","title":"Utilizing Hidden Markov Models to Classify Maneuvers and Improve Estimates of an Unmanned Aerial Vehicle","volume":"54","url":"https://www.sciencedirect.com/science/article/pii/S2405896321022588","doi":"10.1016/j.ifacol.2021.11.214","abstract":"Estimating the states of a Unmanned Aerial Vehicle (UAV) without the use of onboard sensors can be difficult, particularly if the UAV is performing high dynamic maneuvers. This paper examines if data driven modelling can assist in estimating UAV states, as well as classification of UAV maneuvers. A standard Extended Kalman Filter (EKF) that uses radar measurements and a constant acceleration dynamic model is used as the baseline estimation technique for dynamic UAV maneuvers. The UAV maneuvers are then modelled as Hidden Markov Models (HMM), which classify maneuvers and generate additional state information in the form of acceleration and jerk estimates. These HMM estimates are incorporated into an EKF to create a fusion EKF+HMM. This paper evaluates the robustness of the HMM classification accuracy and compares the EKF+HMM to a standard EKF using both simulated and experimental data.","urldate":"2024-06-20","booktitle":"IFAC-PapersOnLine","author":[{"propositions":[],"lastnames":["Strong"],"firstnames":["Amy","K."],"suffixes":[]},{"propositions":[],"lastnames":["Martin"],"firstnames":["Scott","M."],"suffixes":[]},{"propositions":[],"lastnames":["Bevly"],"firstnames":["David","M."],"suffixes":[]}],"month":"January","year":"2021","keywords":"Aerospace Estimation, Estimation, Filtering, Gaussian Mixture Model, Hidden Markov Model, Mechanical, Time Series Modelling","pages":"449–454","bibtex":"@inproceedings{strong_utilizing_2021,\n\tseries = {Modeling, {Estimation} and {Control} {Conference} {MECC} 2021},\n\ttitle = {Utilizing {Hidden} {Markov} {Models} to {Classify} {Maneuvers} and {Improve} {Estimates} of an {Unmanned} {Aerial} {Vehicle}},\n\tvolume = {54},\n\turl = {https://www.sciencedirect.com/science/article/pii/S2405896321022588},\n\tdoi = {10.1016/j.ifacol.2021.11.214},\n\tabstract = {Estimating the states of a Unmanned Aerial Vehicle (UAV) without the use of onboard sensors can be difficult, particularly if the UAV is performing high dynamic maneuvers. This paper examines if data driven modelling can assist in estimating UAV states, as well as classification of UAV maneuvers. A standard Extended Kalman Filter (EKF) that uses radar measurements and a constant acceleration dynamic model is used as the baseline estimation technique for dynamic UAV maneuvers. The UAV maneuvers are then modelled as Hidden Markov Models (HMM), which classify maneuvers and generate additional state information in the form of acceleration and jerk estimates. These HMM estimates are incorporated into an EKF to create a fusion EKF+HMM. This paper evaluates the robustness of the HMM classification accuracy and compares the EKF+HMM to a standard EKF using both simulated and experimental data.},\n\turldate = {2024-06-20},\n\tbooktitle = {{IFAC}-{PapersOnLine}},\n\tauthor = {Strong, Amy K. and Martin, Scott M. and Bevly, David M.},\n\tmonth = jan,\n\tyear = {2021},\n\tkeywords = {Aerospace Estimation, Estimation, Filtering, Gaussian Mixture Model, Hidden Markov Model, Mechanical, Time Series Modelling},\n\tpages = {449--454},\n}\n\n\n\n","author_short":["Strong, A. K.","Martin, S. M.","Bevly, D. M."],"key":"strong_utilizing_2021-1","id":"strong_utilizing_2021-1","bibbaseid":"strong-martin-bevly-utilizinghiddenmarkovmodelstoclassifymaneuversandimproveestimatesofanunmannedaerialvehicle-2021","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S2405896321022588"},"keyword":["Aerospace Estimation","Estimation","Filtering","Gaussian Mixture Model","Hidden Markov Model","Mechanical","Time Series Modelling"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero-group/keb0115/5574615","dataSources":["oHndJaZA7ydhNbpvR","nuijajbxme96RAre3","cN69sC6vEx9NJkKJi","kDK6fZ4EDThxNKDCP"],"keywords":["aerospace estimation","estimation","filtering","gaussian mixture model","hidden markov model","mechanical","time series modelling"],"search_terms":["utilizing","hidden","markov","models","classify","maneuvers","improve","estimates","unmanned","aerial","vehicle","strong","martin","bevly"],"title":"Utilizing Hidden Markov Models to Classify Maneuvers and Improve Estimates of an Unmanned Aerial Vehicle","year":2021}