Aircraft trajectory forecasting using local functional regression in Sobolev space

Tastambekov, Kairat; Puechmorel, Stéphane; Delahaye, Daniel; Rabut, Christophe

doi:10.1016/j.trc.2013.11.013

Cited by 72 publications

(34 citation statements)

References 9 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Almost two decades ago, Le Fablec (1999) has applied artificial neural network on this problem. It has also been investigated more recently using different Machine Learning techniques (Tastambekov et al (2014); Ghasemi Hamed (2014); Solina (2014, 2016)). With these approaches, the obtained model directly predicts the trajectory or a related metric.…”

Section: Literature Reviewmentioning

confidence: 99%

Learning aircraft operational factors to improve aircraft climb prediction: A large scale multi-airport study

Alligier

Gianazza

2018

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Ground-based aircraft trajectory prediction is a major concern in air traffic control and management. A safe and efficient prediction is a prerequisite to the implementation of new automated tools.In current operations, trajectory prediction is computed using a physical model. It models the forces acting on the aircraft to predict the successive points of the future trajectory. Using such a model requires knowledge of the aircraft state (mass) and aircraft intent (thrust law, speed intent). Most of this information is not available to ground-based systems.This paper focuses on the climb phase. We improve the trajectory prediction accuracy by predicting some of the unknown point-mass model parameters. These unknown parameters are the mass and the speed intent. This study relies on ADS-B data coming from The OpenSky Network. It contains the climbing segments of the year 2017 detected by this sensor network. The 11 most frequent aircraft types are studied. The obtained data set contains millions of climbing segments from all over the world. The climbing segments are not filtered according to their altitude. Predictive models returning the missing parameters are learned from this data set, using a Machine Learning method. The trained models are tested on the two last months of the year and compared with a baseline method (BADA used with the mean parameters computed on the first ten months). Compared with this baseline, the Machine Learning approach reduce the RMSE on the altitude by 48 % on average on a 10 minutes horizon prediction. The RMSE on the speed is reduced by 25 % on average. The trajectory prediction is also improved for small climbing segments. Using only information available before the considered aircraft take-off, the Machine Learning method can predict the unknown parameters, reducing the RMSE on the altitude by 25 % on average.The data set and the Machine Learning code are publicly available.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Learning aircraft operational factors to improve aircraft climb prediction: A large scale multi-airport study

Alligier

Gianazza

2018

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…For example, the forward-looking IR (FLIR) systems and ground moving target indicator (GMTI) radar systems have been developed to search and track ground vehicles [1,2]. In a civilian air traffic control (ATC) area, the radar MTT systems [3,4] are used to check the standard separation between pairs of targets for maintenance of safety conditions and regularity of traffic flow. The visible and IR camera MTT systems have been used in the applications of ballistic missile guidance [5] and space-based early warning [6], which are required to identify and track several hundred targets in real time [7].…”

Section: Introductionmentioning

confidence: 99%

A Survey of Motion-Based Multitarget Tracking Methods

Qiu¹,

Zhang²,

Lü³

et al. 2015

PIER B

View full text Add to dashboard Cite

Abstract-Multitarget tracking (MTT) in surveillance system is extremely challenging, due to uncertain data association, maneuverable target motion, dense clutter disturbance, and real-time processing requirements. A good many methods have been proposed to cope with these challenges. However, no up-to-date survey is available in the literature that can help to select suitable tracking algorithm for practical problem. This paper provides a comprehensive review of the state-of-the-art motion-based MTT techniques, classifies existing methods into two groups, i.e., the detect-beforetrack (DBT) scheme and the track-before-detect (TBD) scheme. The DBT scheme is employed to achieve robust and tractable tracking performance when the signal-noise-ratio (SNR) is strong. The TBD scheme is used in the scenarios of low SNR, and it aims to cumulate target energy by multiple sensor frames. Furthermore, depending on the data association mechanism, the DBT methods can be classified into two categories, data association based approaches and finite set statistics (FISST) based approaches. And the TBD methods can be classified into non-Bayesian approaches and Bayesian approaches depending on the basis theory used for tracking. For each category, this paper provides the detailed descriptions of the representative algorithms, and examines their pros and cons. Finally, new trends for future research directions are offered.

show abstract

“…(intent)를 추론하여 이를 궤적예측에 반영하는 연 구가 이루어졌으며 [8,9] 시 필요한 항공기간 분리 간격을 계산한 연구 [10] 가 있으며, 다른 연구에서는 회귀분석(regression analysis)을 통해 항공기 궤적을 예측하였다 [11,12]. 회귀 분석을 통한 궤적 예측의 정확도를 향 상시키고자 가중선형회귀(Weighted Linear Regression) 를 사용하여 궤적 예측을 수행한 연구가 있었으 며 [13,14], 또 다른 연구에서는 가우시안 혼합 모형을 사용하여 공항지역 내 항공기 궤적을 예 측하는 방법을 제안하였다 [15].…”

unclassified

En-route Ground Speed Prediction and Posterior Inference Using Generative Model

백¹,

이²

2019

J. Korean Soc. Aviat. Aeronaut.

View full text Add to dashboard Cite

한국항공운항학회 27 생성 모형을 사용한 순항 항공기 향후 속도 예측 및 추론 Ⅰ. 서 론 지속적으로 증가하는 국내 및 국제 항공교통수요 에 대응하기 위해 출발관리기법(DMAN, Departure Manager)과 같은 의사결정지원도구가 개발되고 있다. 출발관리기법은 항공기의 출발시간과 출 발순서를 최적화한 후 이를 관제사들에게 제공 함으로써 항공기가 공항 이동지역 및 공역에서 불필요하게 지연되는 것을 막아준다. 항공기의 출발 스케줄을 최적화하기 위해서는 보다 정확 한 궤적 예측이 필요하며, 그동안 궤적 예측의 정확도를 향상시키기 위한 다양한 연구가 이루 어져 왔다. 기존에는 PMM(Point Mass Model)과 Eurocontrol 에서 개발한 BADA(Base of Aircraft Data) 등 항 공기 성능 모형(Aircraft Performance Model)을 기반으로 하는 궤적 예측 연구가 주로 수행되었 다[1-6]. 하지만 항공기 성능 모형 기반의 궤적 예측은 벡터링(vectoring)과 같이 실제 항공기가 비행할 때 발생하는 다양한 요인들을 고려하지 못하며, 입력 변수로 사용되는 데이터의 정확도 및 접근성이 좋지 않기 때문에 예측 정확도가 떨어진다[7]. 이와 같은 문제를 보완하고 예측 정확도를 향상시키기 위해서 항공기의 의도 ABSTRACTAn accurate trajectory prediction is a key to the safe and efficient operations of aircraft. One way to improve trajectory prediction accuracy is to develop a model for aircraft ground speed prediction. This paper proposes a generative model for posterior aircraft ground speed prediction. The proposed method fits the Gaussian Mixture Model(GMM) to historical data of aircraft speed, and then the model is used to generates probabilistic speed profile of the aircraft. The performances of the proposed method are demonstrated with real traffic data in Incheon Flight Information Region(FIR).

show abstract

Aircraft trajectory forecasting using local functional regression in Sobolev space

Cited by 72 publications

References 9 publications

Learning aircraft operational factors to improve aircraft climb prediction: A large scale multi-airport study

Learning aircraft operational factors to improve aircraft climb prediction: A large scale multi-airport study

A Survey of Motion-Based Multitarget Tracking Methods

En-route Ground Speed Prediction and Posterior Inference Using Generative Model

Contact Info

Product

Resources

About