Dynamic model identification of unmanned surface vehicles using deep learning network

Woo, Joohyun; Park, Jong-young; Yu, Chan-Woo; Kim, Nakwan

doi:10.1016/j.apor.2018.06.011

Cited by 99 publications

(39 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2017) proposes a new course control based on the back‐propagation neural network to achieve more effective PID control for the USV. Furthermore, neural networks are often used in the control system of the USV to handle the environmental uncertainties caused by waves and currents (Peng et al., 2016; Shojaei, 2016; Woo et al., 2018). On the other hand, simulation is also a tool commonly used in operations research.…”

Section: Literature Reviewmentioning

confidence: 99%

Autonomous vessels: state of the art and potential opportunities in logistics

Góez

Guajardo

et al. 2020

Int Trans Operational Res

View full text Add to dashboard Cite

The growth in technology on autonomous transportation systems is currently motivating a number of research initiatives. This paper first presents a survey of the literature on autonomous marine vessels in general. By identifying the main research interests in this field, we define 10 thematic categories. The collected articles are then classified according to these categories. We show that research on autonomous vessels has increased dramatically in the past decade. However, most of the published articles have focused on navigation control and safety issues. Studies regarding other topics, such as transport and logistics, are very limited. Although our main interest is the literature on autonomous vessels, we contrast its development with respect to the literature on autonomous cars so as to have a better understanding about the future potentials in the research on autonomous vessels. The comparison shows that there are great opportunities for research about transportation and logistics with autonomous vessels. Finally, several potential research areas regarding logistics with autonomous vessels are proposed. As the technology behind remote‐controlled or autonomous ships is maturing rapidly, we believe that it is already time for researchers in the field to start looking into future water‐borne transport and logistics using autonomous vessels.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Autonomous vessels: state of the art and potential opportunities in logistics

Góez

Guajardo

et al. 2020

Int Trans Operational Res

View full text Add to dashboard Cite

show abstract

“…e deep learning methods have shown great potential in object detection and tracking field, which were pre-trained by the public-access benchmarks, and the models were then finetuned with customized data to obtain satisfactory ship behavior recognition performance. Woo et al developed a long short-term memory based recurrent neural network structure to detect and predict kinematic behaviors of unmanned surface vehicles [18]. Gao et al developed an online real-time ship behaviour prediction model by constructing a bidirectional long short-term memory recurrent deep learning neural network [19].…”

Section: Introductionmentioning

confidence: 99%

Video-Based Detection Infrastructure Enhancement for Automated Ship Recognition and Behavior Analysis

Chen

Yang

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

Video-based detection infrastructure is crucial for promoting connected and autonomous shipping (CAS) development, which provides critical on-site traffic data for maritime participants. Ship behavior analysis, one of the fundamental tasks for fulfilling smart video-based detection infrastructure, has become an active topic in the CAS community. Previous studies focused on ship behavior analysis by exploring spatial-temporal information from automatic identification system (AIS) data, and less attention was paid to maritime surveillance videos. To bridge the gap, we proposed an ensemble you only look once (YOLO) framework for ship behavior analysis. First, we employed the convolutional neural network in the YOLO model to extract multi-scaled ship features from the input ship images. Second, the proposed framework generated many bounding boxes (i.e., potential ship positions) based on the object confidence level. Third, we suppressed the background bounding box interferences, and determined ship detection results with intersection over union (IOU) criterion, and thus obtained ship positions in each ship image. Fourth, we analyzed spatial-temporal ship behavior in consecutive maritime images based on kinematic ship information. The experimental results have shown that ships are accurately detected (i.e., both of the average recall and precision rate were higher than 90%) and the historical ship behaviors are successfully recognized. The proposed framework can be adaptively deployed in the connected and autonomous vehicle detection system in the automated terminal for the purpose of exploring the coupled interactions between traffic flow variation and heterogeneous detection infrastructures, and thus enhance terminal traffic network capacity and safety.

show abstract

“…Ship's hydrodynamics as well as environmental influences such as wind and currents have been taken into consideration. A DRL based model identification method was proposed in [11]. By successfully capturing higher-order dynamic behaviours, the proposed deep learning algorithm is able to significantly reduce the motion prediction errors and greatly promote the robustness of the control of USVs.…”

Section: Introductionmentioning

confidence: 99%

Learn to Navigate: Cooperative Path Planning for Unmanned Surface Vehicles Using Deep Reinforcement Learning

et al. 2019

View full text Add to dashboard Cite

Unmanned surface vehicle (USV) has witnessed a rapid growth in the recent decade and has been applied in various practical applications in both military and civilian domains. USVs can either be deployed as a single unit or multiple vehicles in a fleet to conduct ocean missions. Central to the control of USV and USV formations, path planning is the key technology that ensures the navigation safety by generating collision free trajectories. Compared with conventional path planning algorithms, the deep reinforcement learning (RL) based planning algorithms provides a new resolution by integrating a high-level artificial intelligence. This work investigates the application of deep reinforcement learning algorithms for USV and USV formation path planning with specific focus on a reliable obstacle avoidance in constrained maritime environments. For single USV planning, with the primary aim being to calculate a shortest collision avoiding path, the designed RL path planning algorithm is able to solve other complex issues such as the compliance with vehicle motion constraints. The USV formation maintenance algorithm is capable of calculating suitable paths for the formation and retain the formation shape robustly or vary shapes where necessary, which is promising to assist with the navigation in environments with cluttered obstacles. The developed three sets of algorithms are validated and tested in computer-based simulations and practical maritime environments extracted from real harbour areas in the UK. INDEX TERMS Deep reinforcement learning, motion planning, multi-agent systems, unmanned surface vehicles (USVs), USV formations.

show abstract

Dynamic model identification of unmanned surface vehicles using deep learning network

Cited by 99 publications

References 18 publications

Autonomous vessels: state of the art and potential opportunities in logistics

Autonomous vessels: state of the art and potential opportunities in logistics

Video-Based Detection Infrastructure Enhancement for Automated Ship Recognition and Behavior Analysis

Learn to Navigate: Cooperative Path Planning for Unmanned Surface Vehicles Using Deep Reinforcement Learning

Contact Info

Product

Resources

About