Long-term 4D trajectory prediction using generative adversarial networks

Wu, Xinzhou; Yang, Hongyu; Hu, Chen; Hu, Qinzhi; Hu, Haoliang

doi:10.1016/j.trc.2022.103554

Cited by 35 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to further analyze the prediction performance of the trajectory prediction method (BESTCC-CNN-LSTM), LSTM, GRU (gate recurrence unit) and velocity trend extrapolation (VTE) is used for trajectory prediction comparison [41], [42]. In this paper, MSE and MAE are used as prediction performance evaluation indexes.…”

Section: Comparative Analysis Of 4d Trajectory Prediction Performancementioning

confidence: 99%

Short-Term 4D Trajectory Prediction for UAV Based on Spatio-Temporal Trajectory Clustering

et al. 2022

View full text Add to dashboard Cite

To improve the trajectory prediction accuracy of unmanned aerial vehicles (UAVs) with random behavior intentions, this paper presents a short-term four-dimensional (4D) trajectory prediction method based on spatio-temporal trajectory clustering. A spatio-temporal trajectory clustering algorithm is first designed to cluster the UAV trajectory segments divided by a fixed time window. Each trajectory segment is given a category label that represents some certain type of behavior characteristics, such as climbing, turning, descending, etc. The convolutional neural network (CNN) is used to identify the category label of a given trajectory segment by learning the behavior characteristics of different trajectory segments. Based on the long-short-term memory network (LSTM), a short-term trajectory prediction model for different categories of label trajectory segments is established. The global trajectory prediction includes several steps adopting the corresponding prediction models. Historical trajectory data of UAVs are used to validate the proposed prediction method. Experiment results indicate that the method can obtain obviously better prediction accuracy in a short prediction time range (0-3s) with acceptable efficiency compared to LSTM, GRU and velocity trend extrapolation.

show abstract

Section: Comparative Analysis Of 4d Trajectory Prediction Performancementioning

confidence: 99%

Short-Term 4D Trajectory Prediction for UAV Based on Spatio-Temporal Trajectory Clustering

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Its structure is shown in Figure 7. The output sequence ht of the upstream layer is computed using the input sequence from time y-t to time y-1, and the output sequence ht of the downstream layer is computed using the input sequence from time y+t to time y+1, as shown in equations ( 16) to (20) [24] [25]. Similar to the LSTM layer, the final output of the Bi-LSTM layer can be represented as a vector.…”

Section: Figure 6 Uas Trajectory Reconstructionmentioning

confidence: 99%

“…In equation (24), ∆𝑃 ̅ = 𝑃 𝑆 ̅ -𝑃 𝑅 ̅̅̅̅ , if the position errors of the two UASs are independent of each other, the relative positions is:…”

Section: ) Collision Probability For Uas Pairsmentioning

confidence: 99%

Multivariate Combined Collision Detection for Multi-Unmanned Aircraft Systems

Zhang

Zhong

et al. 2022

IEEE Access

View full text Add to dashboard Cite

To mitigate the problem of multiple unmanned aircraft systems (MUAS) conflicts at low altitude and ensure the operational safety, this paper proposes a Multivariate Combined Conflict Detection (MCCD) method for MUAS by combining the characteristics of nominal and probabilistic trajectory method. Firstly, the structural framework of the MCCD method is established based on the concept of potential conflict pool, and a detection pattern is derived for MUAS. Secondly, a three-dimensional conflict fast detection model is constructed by velocity obstacle methods, which can rapidly detect potential conflict risks. Thirdly, a trajectory prediction model is constructed by using bidirectional long-short term memory (Bi-LSTM) network, and then a probabilitybased conflict detection model can be obtained by the expected value and error distribution of trajectory prediction, which can accurately calculate the collision probability of UAS pair. By fully integrating the above models, the fast and accurate detection of MUAS conflicts is achieved. Finally, multiple conflicting trajectories are constructed to analyze the effectiveness of MCCD method, the tests indicate that the average detection time of the proposed method is less than 15ms, the false positive rate is less than 0.01 and the false negative rate is less than 0.0035. The results show that the MCCD has the accuracy advantage and better real-time performance for MUAS conflict detection compared to the method of velocity trend extrapolation, single probabilistic conflict detection and probabilistic neural network.INDEX TERMS conflict detection, multi-unmanned aircraft systems, potential conflict, probability estimation.

show abstract

“…Shi et al [28] proposed a trajectory prediction model based on LSTM that considers the correlation between adjacent trajectory points for longtime trajectory prediction. Wu et al [29] used generative adversarial networks to predict the long-term 4D trajectory of aircraft, which shows the great prospect of deep learning in the field of trajectory prediction. The airspace congestion prediction model in this paper is also based on the framework of deep learning.…”

Section: Introductionmentioning

confidence: 99%

Multiobjective Four-Dimensional Trajectory Synergetic Optimization Based on Congestion Prediction and NSGA3-SA

et al. 2022

View full text Add to dashboard Cite

Synergetic trajectory planning of flights is one of the important goals of trajectory-based operation (TBO), and it is also a method to further improve the utilization of airspace resources with the increasing number of flights in recent years. In order to plan the four-dimensional trajectory (4DT) pretactically and comprehensively, match the flight traffic with airspace capacity, reduce congestion, potential conflicts, and fuel consumption thus improving the efficiency of flights, this paper conducts a method for synergetic trajectory planning in the en-route phase from the perspective of airlines. Firstly, the aircraft performance model, aircraft fuel consumption model, and atmospheric model are constructed according to the base of aircraft data (BADA3.11), and an airspace congestion prediction model is constructed based on the historical flow data of airspace. Secondly, a multi-objective synergetic trajectory planning model is established, and a solution method based on the non-dominated sorting genetic algorithm and simulated annealing algorithm (NSGA3-SA) for the problem of synergetic trajectory planning is designed. The simulation shows that the optimization model and the solution algorithm of NSGA3-SA can reduce fuel consumption by about 4.5% compared to the original flight plans and has a good effect on reducing congestion and avoiding conflicts. The running time of the NSGA3-SA can meet the operational requirements of the pre-tactical trajectory planning. The multi-objective optimization model and the solution algorithm proposed in this paper have great value for the research of flight plan optimization.

show abstract

Long-term 4D trajectory prediction using generative adversarial networks

Cited by 35 publications

References 16 publications

Short-Term 4D Trajectory Prediction for UAV Based on Spatio-Temporal Trajectory Clustering

Short-Term 4D Trajectory Prediction for UAV Based on Spatio-Temporal Trajectory Clustering

Multivariate Combined Collision Detection for Multi-Unmanned Aircraft Systems

Multiobjective Four-Dimensional Trajectory Synergetic Optimization Based on Congestion Prediction and NSGA3-SA

Contact Info

Product

Resources

About