A Behavior-Based Mission Planner for Cooperative Autonomous Underwater Vehicles^†

Abstract

Due to its applications in marine research, oceanographic, and undersea exploration, Autonomous Underwater Vehicles (AUVs) and the related control algorithms has been recently under intense investigation. In this work, we address target detection and tracking issues, proposing a control strategy which is able to benefit from the cooperation among robots within the fleet. In particular, we introduce a behavior-based planner for cooperative AUVs, proposing an algorithm able to search and recognize targets, in both static and dynamic scenarios. With no a priori information about the surrounding environment, robots cover an unknown area with the goal of finding objects of interest. When a target is found, the AUVs' goal become to classify it (fixed target) or track it (mobile target), with no information about target trajectory and with the constraint on maintaining the formation. Results demonstrate the good overall performance of the proposed algorithm in both scenarios.

Distributed Event-Triggered Adaptive Coordinated Trajectory Tracking Control of Multi-USVs Based on the Aggregate Tracking Error

“…The main contributions of this paper are as follows: 1) Compared with the coordinated control methods in [3], [6]- [9], [35], a distributed event-triggered method is proposed, in which the control instructions are updated based on the auxiliary state and distributed eventtriggered conditions, rather than updated at uniform time intervals based on the sampling time. By adopting the proposed control strategy, the energy consumption is greatly reduced.…”

Intelligent Navigation for a Solar Powered Unmanned Underwater Vehicle

“…In the field of neural networks research, it is often suggested that neural networks based on associative learning laws can model the mechanisms of classical conditioning, while neural networks based on reinforcement learning laws can model the mechanisms of operant conditioning [29,32]. The reinforcement learning is used to acquire navigation skills for autonomous vehicles and updates both the vehicle model and optimal behaviour at the same time [24,[33][34][35][36][37][38].…”

“…The SODMN is a kinematic adaptive neuro-controller and a real-time, unsupervised neural network that learns to control autonomous underwater and surface vehicles in a nonstationary environment. The SODMN combines associative learning and Vector Associative Map (VAM) learning [24,28,[36][37][38] to generate transformations between spatial and velocity coordinates. The transformations are learned in an unsupervised training phase, during which the vehicle moves as a result of randomly selected velocities of its actuators.…”

A topology control algorithm for autonomous underwater robots in three-dimensional space using PSO

“…This vehicle could independently create an intelligent choice about its next movement location using its neighbors' local information and on-board intelligence without human guidance [4]. The benefits of exploiting a group of AUVs as opposed to single application, become evident when considering performance, costs, fault tolerance and re-configurability [5]. It is prohibitive to use a central controller to guide AUVs' behavior due to ever changing, unknown environmental conditions, limited bandwidth and lossy communication mediums [6].…”