UAV Behavior-Intention Estimation Method Based on 4-D Flight-Trajectory Prediction

Zhang, Honghai; Yan, Yongjie; Li, Shan; Hu, Yuxin; Líu, Hao

doi:10.3390/su132212528

Cited by 13 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning methods take drone trajectories as time-series data and mine the historical information to predict drone flight trajectories without considering other influencing factors. Zhang [33] proposed a 4D trajectory combination prediction model based on a genetic algorithm. Based on historical flight data and UAV motion equations, the genetic algorithm dynamically weights the model, which can predict the flight trajectory of UAV and the time to enter the protected area.…”

Section: Related Workmentioning

confidence: 99%

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

et al. 2022

Self Cite

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: Related Workmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The algorithm used historical ADS-B flight data and the UAV equation of motion. Their simulation could estimate UAV trajectory and the entering time to the protection zone accurate and instantly [25]. Since ADS-B data are heavily dependent on information from the GNSS system, another research proposed a method to construct a UAV trajectory when devoid of a GNSS signal.…”

Section: Ads-b Researchmentioning

confidence: 99%

UAS Traffic Management Communications: The Legacy of ADS-B, New Establishment of Remote ID, or Leverage of ADS-B-Like Systems?

Ruseno

Lin

Chang

2022

Drones

View full text Add to dashboard Cite

Unmanned aerial system (UAS) traffic management (UTM) requires each UAS to communicate with each other and to other stakeholders involved in the operation. In practice, there are two types of wireless communication systems established in the UAS community: automatic dependent surveillance broadcast (ADS-B) and remote identification (Remote ID). In between these two systems, there is ADS-B-like communication which leverages using other types of communications available in the market for the purpose of UTM. This review aims to provide an insight into those three systems, based on the published standard documents and latest research development. It also suggests how to construct a feasible communication architecture. The integrative approach is used in this literature review. The review categorization includes definition, data format, technology used, and research applications, and any remaining issues are discussed. The similarities and differences of each system are elaborated, covering practical findings. In addition, the SWOT analysis is conducted based on the findings. Lastly, multi-channel communication for UTM is proposed as a feasible solution in the UTM operation.

show abstract

“…Many efforts have been made to classify intention from observational data using experts-knowledge methods 4 . These methods define low-dimensional behavioural features 5 for relatively simple motion dynamics based on either geofence planning methods 6 , 7 and expert traffic rules 8 or drone’s flight constraints 9 . However, the challenge of predicting intention is exasperated by an inherent cognitive bias problem caused by the low scalability of these simplistic features to complex and diverse classification of drone intention.…”

Section: Introductionmentioning

confidence: 99%

Uncovering drone intentions using control physics informed machine learning

Perrusquía,

Guo,

Fraser

et al. 2024

Commun Eng

View full text Add to dashboard Cite

Unmanned Autonomous Vehicle (UAV) or drones are increasingly used across diverse application areas. Uncooperative drones do not announce their identity/flight plans and can pose a potential risk to critical infrastructures. Understanding drone’s intention is important to assigning risk and executing countermeasures. Intentions are often intangible and unobservable, and a variety of tangible intention classes are often inferred as a proxy. However, inference of drone intention classes using observational data alone is inherently unreliable due to observational and learning bias. Here, we developed a control-physics informed machine learning (CPhy-ML) that can robustly infer across intention classes. The CPhy-ML couples the representation power of deep learning with the conservation laws of aerospace models to reduce bias and instability. The CPhy-ML achieves a 48.28% performance improvement over traditional trajectory prediction methods. The reward inference results outperforms conventional inverse reinforcement learning approaches, decreasing the root mean squared spectral norm error from 3.3747 to 0.3229.

show abstract

UAV Behavior-Intention Estimation Method Based on 4-D Flight-Trajectory Prediction

Cited by 13 publications

References 5 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

UAS Traffic Management Communications: The Legacy of ADS-B, New Establishment of Remote ID, or Leverage of ADS-B-Like Systems?

Uncovering drone intentions using control physics informed machine learning

Contact Info

Product

Resources

About