Abstract
There is tremendous demand for marine environmental observation, which requires the development of a multi-agent cooperative observation algorithm to guide Unmanned Surface Vehicles (USVs) and Unmanned Aerial Vehicles (UAVs) to observe isotherm data of the mesoscale vortex. The task include two steps: firstly, USVs search out the isotherm, navigate independently along the isotherm, and collect marine data; secondly, a UAV takes off, and in its one round trip, the UAV and USVs jointly perform the task of the UAV reading the observation data from USVs. In this paper, aiming at the first problem of the USV following the isotherm in an unknown environment, a data-driven Deep Deterministic Policy Gradient (DDPG) control algorithm is designed that allows USVs to navigate independently along isotherms in unknown environments. In addition, a hybrid cooperative control algorithm based on a multi-agent DDPG is adopted to solve the second problem, which enables USVs and a UAV to complete data reading tasks with the shortest flight distance of the UAV. The experimental simulation results show that the trained system can complete this tas, with good stability and accuracy.
Highlights
A mesoscale eddy is a kind of marine phenomenon characterized by long-term closed circulation with a time scale from days to months and a spatial scale from tens of kilometers to hundreds of kilometers
The current means of object-oriented observation are insufficient, so it is necessary to develop an automatic sea–air cooperative observation system to promote the study of mesoscale eddy-related air–sea interactions and their weather and climate effects
The third layer neuron of the network input by the state–space matrix is merged with the second layer neuron node of the action matrix input network, and the output value is obtained through the ReLU activation function
Summary
A mesoscale eddy is a kind of marine phenomenon characterized by long-term closed circulation with a time scale from days to months and a spatial scale from tens of kilometers to hundreds of kilometers. It has a nonnegligible impact on weather prediction, marine chemistry, and the biological environment [1]. The observation of seawater isotherms will help us to understand the formation and propagation of mesoscale eddies The DQN training algorithm is improved to decouple the selection and evaluation of actions. A network is trained to output both an action and Q value simultaneously, but the algorithm is not mature
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
