Unmanned surface vehicle (USV) has witnessed a rapid growth in the recent decade and been applied various practical applications both military civilian domains. USVs can either be deployed as single unit or multiple vehicles fleet to conduct ocean missions. Central control of USV formations, path planning is key technology that ensures navigation safety by generating collision free trajectories. Compared with conventional algorithms, deep reinforcement learning (RL) based algorithms provides...

An effective anomaly detection system is critical for marine autonomous systems operating in complex and dynamic environments to reduce operational costs achieve concurrent large-scale fleet deployments. However, developing an automated fault remains challenging several reasons including limited data transmission via satellite services. Currently, most systems, such as underwater gliders, rely on intensive analysis by pilots. This study proposes unsupervised using bidirectional generative...

Purpose Autonomous obstacle avoidance is important in unmanned surface vehicle (USV) navigation. Although the result of detection often inaccurate because inherent errors LIDAR, conventional methods typically emphasize on a single obstacle-avoidance algorithm and neglect limitation sensors safety local region. Conventional also fail seamlessly integrating global algorithms. This paper aims to present cooperative manoeuvring approach including both avoidance. Design/methodology/approach The...

The autonomous obstacle avoidance planning of USV is the guarantee and precondition carrying out performance. Obstacle required to possess high accuracy instantaneity due a complex environment faster speed. algorithm Artificial Potential Field has advantage sample mathematical model, which easy understand implement, facilitate underlying control. However, application traditional problems local minimum, destination unreachable, poor algorithm. Aiming at these issues, method Unmanned Surface...

Purpose – This paper aims to propose a new method for combining global path planning with local planning, provide an efficient solution unmanned surface vehicle (USV) despite the changeable environment. Path is key issue of USV navigation. A lot research works were done on and planning. However, little attention was given Design/methodology/approach search shortcut Dijkstra algorithm used control in When encounters unknown obstacles, it switches our modified artificial potential field (APF)...

Recent advances in robotics and autonomous systems (RAS) have significantly improved the autonomy level of unmanned surface vehicles (USVs) made them capable undertaking demanding tasks various environments. During operation USVs, apart from normal situations, it is those unexpected scenes, such as busy waterways or navigation dust/nighttime, impose most dangers to USVs these scenes are rarely seen during training. Such a rare occurrence also makes manual collection recording into dataset...

People detection and tracking is an essential capability for mobile robots in order to achieve natural human–robot interaction. In this article, a human system designed validated using color data with depth information RGB-depth (RGB-D) cameras. The whole framework composed of detection, re-identification. Firstly, ground points ceiling planes are removed reduce computation effort. A prior-knowledge guided random sample consensus fitting algorithm used detect the plane points. All left...

Unmanned surface vehicles (USVs) are receiving increasing attention in recent years from both academia and industry. To make a high-level autonomy for USVs, the environment situational awareness is key capability. However, due to richness of features marine environments, as well complexity influenced by sun glare sea fog, development reliable system remains challenging problem that requires further studies. This paper, therefore, proposes new deep semantic segmentation model together with...

The paper introduces symbolic bisimulations for a simple probabilistic pi-calculus to overcome the infinite branching problem that still exists in checking ground between systems. Especially definition of weak (symbolic) bisimulation does not rely on random capability adversaries and suggests solution open axiomatization case unguarded recursion. Furthermore, we present an efficient characterization calculus, which allows "on-the-fly" instantiation bound names dynamic construction...

We present an implementation of model checking for probabilistic and stochastic extensions the -calculus, a process algebra which supports modeling concurrency mobility.Formal verification techniques such have clear applications in several domains, including mobile ad hoc network protocols, security biological pathways.Despite this, no automated exists.Building upon -calculus checker Mobility Model Checker (MMC), we first show procedure constructing underlying semantic or process.This can...

Autonomous obstacle-avoidance is an important problem of mobile robot (MR) navigation, which LIDAR a kind key equipment. A can implement behaviors with specific algorithm based on data. However, may encounter local minimum because unexpected environment, and the only gets suboptimal solution. Besides, it cannot avoid current obstacles accurately due to measuring errors LIDAR. To solve problem, novel integrated laser data proposed in this paper. The simulation experiment demonstrate that feasible.

Intention recognition is the ability to predict an opposing forcepsilas high level goals. Knowing attackerpsilas intention can support decision-making of network security administrators. Furthermore intent analysis plays import role in calculation inherent threat value. So how recognize attack has become a research hot domain recently.In this paper taxonomy characterized by consequences and targets introduced at first. Then graphical model based on state presented used intention. D-S...

To make full use of the temporal correlation video sequences, H.264/AVC adopts multiple reference frames to enhance coding quality. While performance being improved, complexity computation has been increased linearly, too. In this paper, we study motion characteristic sequences and spatial in first, then propose an adaptive fast selection algorithm. It can decrease number for compensation, reduce adaptively according features sequences. The results show that our algorithm achieves 45% time...

A symmetric Kullback-Leibler metric based tracking system, capable of moving targets, is presented for a bionic spherical parallel mechanism to minimize error function simulate smooth pursuit human eyes. More specifically, we propose real-time target algorithm which utilizes spatial histograms taking into account metric. In the proposed algorithm, key are extracted and taken particle filtering framework. Once identified, an image-based control scheme implemented drive such that identified be...

We present an implementation of model checking for the probabilistic pi-calculus-calculus, a process algebra which supports modelling concurrency, mobility and discrete behaviour. Formal verification techniques this calculus have clear applications in several domains, including mobile ad-hoc network protocols random security protocols. Despite this, no automated exists. Building upon (non-probabilistic) pi-calculus checker MMC, we first show procedure constructing Markov decision...