A model for vessel trajectory prediction based on long short-term memory neural network

Tang, Huang; Yin, Yixin; Shen, Helong

doi:10.1080/20464177.2019.1665258

Cited by 101 publications

(48 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A “sequence-to-sequence” recurrent neural network model has been developed to mesh and serialize a ship trajectory into a neural network model, in order to predict the main trajectory and arrival time [ 15 ]. A LSTM model has been introduced to predict ship’s position by evaluating the probability distribution and obtains relatively valid results [ 16 ]. To improve the accuracy of the prediction mechanisms, a multiple azimuth autonomous device sensor has been used as an additional data input, but the approach relies on a large amount of AIS data so computational performance is relatively low [ 17 ].…”

Section: Related Workmentioning

confidence: 99%

“…During the data preprocessing process, the wandering or anchoring trajectories in the original dataset are eliminated. We set the minimum time interval of the trajectory to 1200 s, because of the AIS information receiving interval is generally specified to be about 5–10 min, and the information interval higher than 20 min is used as the next stage of navigation status [ 16 ]. Each trajectory is optimized by a function Optimization (

) as shown in Algorithm 1.…”

Section: Modeling Approachmentioning

confidence: 99%

See 1 more Smart Citation

A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network

Suo

Chen

Claramunt

et al. 2020

Sensors

105

View full text Add to dashboard Cite

Ship trajectory prediction is a key requisite for maritime navigation early warning and safety, but accuracy and computation efficiency are major issues still to be resolved. The research presented in this paper introduces a deep learning framework and a Gate Recurrent Unit (GRU) model to predict vessel trajectories. First, series of trajectories are extracted from Automatic Identification System (AIS) ship data (i.e., longitude, latitude, speed, and course). Secondly, main trajectories are derived by applying the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. Next, a trajectory information correction algorithm is applied based on a symmetric segmented-path distance to eliminate the influence of a large number of redundant data and to optimize incoming trajectories. A recurrent neural network is applied to predict real-time ship trajectories and is successively trained. Ground truth data from AIS raw data in the port of Zhangzhou, China were used to train and verify the validity of the proposed model. Further comparison was made with the Long Short-Term Memory (LSTM) network. The experiments showed that the ship’s trajectory prediction method can improve computational time efficiency even though the prediction accuracy is similar to that of LSTM.

show abstract

Section: Related Workmentioning

confidence: 99%

) as shown in Algorithm 1.…”

Section: Modeling Approachmentioning

confidence: 99%

A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network

Suo

Chen

Claramunt

et al. 2020

Sensors

105

View full text Add to dashboard Cite

show abstract

“…Perera and Soares (2010) estimated ship position, velocity, and acceleration using an extended Kalman filter. Model-driven approaches require a mathematical model to be built for each trajectory, therefore they are not very suitable for dynamic environments (Tang et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

“…The results showed a 70% prediction accuracy. Tang et al (2019) constructed a neural network with two long short-term memory (LSTM) layers, which can observe the first 10 min of the vessel's state to predict the location of the vessel after 20 min. The experimental comparison revealed that the model performs better than the Kalman filter and backpropagation neural network.…”

Section: Related Workmentioning

confidence: 99%

Vessel Trajectory Prediction Using Historical Automatic Identification System Data

2020

View full text Add to dashboard Cite

For maritime safety and security, vessels should be able to predict the trajectories of nearby vessels to avoid collision. This research proposes three novel models based on similarity search of trajectories that predict vessels' trajectories in the short and long term. The first and second prediction models are, respectively, point-based and trajectory-based models that consider constant distances between target and sample trajectories. The third prediction model is a trajectory-based model that exploits a long short-term memory approach to measure the dynamic distance between target and sample trajectories. To evaluate the performance of the proposed models, they are applied to a real automatic identification system (AIS) vessel dataset in the Strait of Georgia, USA. The models' accuracies in terms of Haversine distance between the predicted and actual positions show relative prediction error reductions of 40·85% for the second model compared with the first model and 23% for the third model compared with the second model.

show abstract

“…They evaluated their method on a pig stomach dataset and their experimental results show that the framework can realize high translational and rotational accuracies for different types of endoscopic capsule robot trajectories. However, research on navigation with DL mainly focus on the visual navigation or visual-inertial navigation field for outdoor robots and aerial robots, and only very few of them were applied in the maritime engineering field [35], [36].…”

Section: Introductionmentioning

confidence: 99%

Navnet: AUV Navigation Through Deep Sequential Learning

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Achieving accurate navigation and localization is crucial for Autonomous Underwater Vehicle (AUV). Traditional navigation algorithms, such as Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF), require the system model and measurement model for state estimation to obtain the AUV position. However, this may introduce modeling errors and state estimation errors which will affect the final precision of AUV navigation system to a certain extent. To avoid these problems, in this paper, we proposed a deep framework-NavNet-by taking AUV navigation as a deep sequential learning problem. Firstly, the proposed NavNet can take raw sensor data at different frequencies as input, which benefits from the sequential learning capability of Recurrent Neural Network (RNN). Secondly, NavNet takes advantage of a simplified attention mechanism and Fully Connected (FC) layers to output AUV displacements per unit time, which accomplishes low-frequency AUV navigation by accumulation of it. More importantly, there is no need for the model building and state estimation with NavNet, which avoids the import of relevant errors. We compare the performance of NavNet to EKF and UKF using collected data by running Sailfish in the sea. Experimental results show that NavNet has an excellent performance in terms of both the navigation accuracy and fault tolerance. In addition, a reliable fusion strategy of NavNet and conventional method is applied to achieve high-frequency AUV navigation. The experimental results show that the proposed architecture can be a reliable supplement to limit the error growth of conventional algorithms. INDEX TERMS Autonomous underwater vehicle, navigation, extended Kalman filter, unscented Kalman filter, sequential learning.

show abstract

A model for vessel trajectory prediction based on long short-term memory neural network

Cited by 101 publications

References 12 publications

A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network

A Ship Trajectory Prediction Framework Based on a Recurrent Neural Network

Vessel Trajectory Prediction Using Historical Automatic Identification System Data

Navnet: AUV Navigation Through Deep Sequential Learning

Contact Info

Product

Resources

About