开发用于海洋任务的水下无人潜航器与空中平台自主编队

Faris A. Almalki1· Marios C. Angelides2 Received: 24 April 2025 / Revised: 21 August 2025 / Accepted: 24 August 2025© The Author(s) 2025 Abstract A new generation of Internet of Underwater Things (IoUT) has been facilitating the development of a new class of IoTapps, i.e. marine apps. Of interest in this research are Unmanned Underwater Vehicles (UUVs). Our experience withUnmanned Aerial Vehicles (UAVs) thus far suggests that UUVs have the potential to become effective and efficient whensupported with optimisation algorithms. To explore this, this work first puts together a school of UUVs by using acousticcommunications, and Deep Learning (DL). It then introduces an aerial platform as a source of renewable energy for theschool. The resulting fleet is then empowered to operate autonomously for the purpose of carrying out marine missions anddetecting underwater objects using a dual cognitive brain developed using a Dolphin Optimization Algorithm (DOA) anda Support Vector Machine (SVM). The results obtained indicate that the communication link budget parameters, reliabilityand localization, as well as the accuracy of coordination among the school of UUVs and the aerial platform as well as ini- KeywordsAutonomous school of UUVs· Acoustic communications· Wireless communications· DL· IoUT 1Introduction main 4IR technologies that are associated with UUVs. Astechnology continues to evolve, we should expect to see amore diverse and innovative range of solutions for morereliable and efficient underwater communications, whilstavoiding known exclusion zones like Nan Madol which Fourth Industrial Revolution (4IR) technologies are play-ing a crucial role in advancing underwater communication Since the 4IR is a fusion of technologies, this blurs thelines between the physical, digital, and biological spheres.This raises both immense opportunities and challengeswhen it comes to the autonomous fleet of UUVs [1–3]. The Marios C. Angelidesmarios.angelides@brunel.ac.ukFaris A. Almalkim.faris@tu.edu.sa1Department of Computer Engineering, College of Computers ●Accurate and reliable localization and navigation forUUVs which is hindered by poor hydroacoustic sensor Content courtesy of Springer Nature, terms of use apply. Rights reserved. ●Wireless communication, underwater, which is severelylimited by signal attenuation. This restricts real-time datatransmission and remote control, often requiring UUVsto operate with more autonomy and pre-programmedmissions, making dynamic adjustments difficult.●Energy supply to UUVs for extended missions which isdisrupted by battery depletion and will require frequent collected from past missions in complex and changingenvironments and choose, for example, a new path thatrecognizes and avoids obstacles or prioritizes targets. Inturn, this allows them to become more efficient and ef- ●Data analytics on the large amounts of data collected,such as images, videos, and sensory data, from which The rest of this paper is organized as follows: Sect.2pres-ents a review of related studies from which we draw ourmotivation for a framework we propose in Sect.3. Section4details a framework simulation and then discusses the initial In this work we propose to resolve some of the abovechallenges by endowing UUVs with IoUT and DL whichenables: 2Related studies review ●Autonomy that allows UUVs to make dynamic adjust-ments to their mission plan without any human inter-vention if, for example, they are affected by signal at-tenuation. In turn, this allows them to operate for longer This section reviews studies that relate to the advancementsof UUVs. To guarantee consistency within the scope, a set ofcriteria have been considered during review of the literature.The criteria include type of: UUV, network configuration, ●Intelligent real-time decision-making that allows UUVsto pursue continuous learning using data they have Content courtesy of Springer Nature, terms of use apply. Rights reserved. a reinforcement learning approach [14]. considers taskassignment and path planning using various AI approacheswhilst [15] proposes formation control and investigatesunderwater acoustic communication [16]. experiments withautonomous path planning in riverbanks using a 2D LiDARand PID controller [17]. presents an adaptive variablethreshold event-triggered control for trajectory tracking ofautonomous UUVs with actuator saturation [18]. proposes apredefined path for UUVs for data collection whereas [19]uses Cooperative coverage Path Planning (CPP) alongside aPac-Men mechanism for UUVs to explore deep oceans [20].proposes a fish-inspired robotic flocking algorithm that imi-tates behaviour and communication of schooling fish [21].considers dynamic trajectory planning for UUVs to remainclose to moving sensor nodes and exploit both short and that have emerged, namely, underwater communications,autonomous motion, object detection and computer vision,and underwater missions. We conclude with highlights ofour findin