Search

This paper introduces a novel method for enhancing underground pipeline inspection, specifically addressing limitations associated with traditional closed-circuit television (CCTV) systems. These systems, commonly used for capturing visual data of sewer system deformations, heavily rely on subjective human expertise, leading to limited accuracy in detection. Furthermore, their inability to perform quantitative analyses of deformation extent hampers overall inspection effectiveness. Our proposed method leverages laser point cloud data and employs a 3D scanner for objective detection of geometric deformations in underground pipe corridors. By utilizing this approach, we enable a quantitative assessment of blockage levels, offering a significant improvement over traditional CCTV-based methods. The key advantages of our method lie in its objectivity and quantification capabilities, ultimately enhancing detection reliability, accuracy, and overall inspection efficiency.

Abstract Artificial intelligence is penetrating various fields. The demand for interdisciplinary talent is increasingly important, while interdisciplinary educational activities for high school students are lagging behind. Project‐based learning (PBL) in artificial intelligence (AI) and robotic education activities supported by a robotic sailboat platform, the sailboat test arena (STAr), has been shown to popularise AI and robotic knowledge in young students. In the implementation of the programme, PBL was provided for students, and gamification pedagogy was applied to increase participants' learning motivation and engagement. The results show that the proposed STAr‐based programme is capable of delivering the desired knowledge and skills to students at high school levels. The assessment results suggest that most students achieve learning outcomes on average. Students showed more interest in AI and marine disciplines and were willing to participate in more such educational programs. The findings fill the research gap that few existing education platforms have facilitated the teaching and learning of AI and marine disciplines for high school students.

Bridge cables are commonly used in bridge construction, and assessing their condition is crucial for ensuring bridge safety. However, current inspection methods often rely on large and heavy detection mechanical structures, which can be inconvenient during the inspection process. In light of these limitations, this paper proposes a portable non-destructive inspection method for bridge cables that detects the total magnetic flux variations utilizing an inductive search coil sensor. The occurrence of corrosion and cracks in bridge cables leads to changes in their original sectional area and permeability. These changes result in variations in the induced current that is excited by the coil, leading to distortions in both the magnetic field energy and the coil’s self-inductance. Thus, cable damage can be detected inversely by monitoring coil self-inductance variation. To assess the feasibility of this method, a numerical analysis is conducted, and an experimental structure is designed using a mock-up cable specimen with parallel steel wires that have varying degrees of damage. The experimental results demonstrate the effectiveness of the proposed method, which utilizes an inductive search coil sensor, intuitively identifies and quantifies internal flaws on the cable in real-time while maintaining a lightweight structure. The width and amplitude of the coil inductive response show a positive correlation with the flaw’s axial length and cross-sectional area, indicating that these parameters can be utilized to quantify the size of the flaw.

Autonomous sailing robots have attracted much attention, but challenges arise due to the sailing tests require an environment with both aerodynamic and hydrodynamic fields and a sufficient number of sailing robots in readiness. A remotely accessible platform with the advantages of low cost, easy operation and high efficiency is the preferred method to solve this dilemma. Consistent with this goal is the design of Sailboat Test Arena (STAr), a remotely accessible platform for sailing robot design verification, autonomous algorithms validation and sailing control practices. All three parts require extensive testing in real water environments. Hereby, for testers around the world, STAr can be accessed without time difference. A variety of local and remote tests have been conducted in the STAr platform at various location around the world. The results show that STAr is a remotely accessible and effective tool in data collection and skill transfer. With continuous adoption and optimization, STAr will continue to serve as a tool to further promote low-cost, high-efficiency and diverse sailing research, and provide opportunities for more people to experience sailing.

Sailing robots can contribute significantly to maritime surface exploration, due to its potential for long-range and long-duration motions in the environment with abundant wind. However, energy, the critical factor for their long-term missions, shall be carefully investigated, so as to achieve sustainability in distance and time. In this survey, we have conducted a comprehensive investigation on numerous sailing robots, developed in academia and industry. Some of them have achieved long-term operation, and some are motivated by, but still on the way to this ambitious goal. Prototypes are grouped in each team, so as to view the development path. We further investigate the existing design and control strategies for energy sufficiency from three perspectives: actuation, harvesting, and energy management. In propulsion and steering, i.e., two major actuations, researchers have accumulated effective sail and rudder designs. The motorized propeller and wave-glider–inspired mechanism also contribute as compliments for propulsion. Electricity harvesting based on solar or wind energies is also discussed to gather more power from nature. Pros and cons in strategies of energy management, which are valuable tools to enhance power utilization efficiency, are elaborated. This article is hoped to provide researchers in long-term robotic sailing with a comprehensive reference from the perspectives of energy.

Battery fast charging is one of the most significant and difficult techniques affecting the commercialization of electric vehicles (EVs). In this paper, we propose a fast charge framework based on model predictive control, with the aim of simultaneously reducing the charge duration, which represents the out-of-service time of vehicles, and the increase in temperature, which represents safety and energy efficiency during the charge process. The RC model is employed to predict the future State of Charge (SOC). A single mode lumped-parameter thermal model and a neural network trained by real experimental data are also applied to predict the future temperature in simulations and experiments respectively. A genetic algorithm is then applied to find the best charge sequence under a specified fitness function, which consists of two objectives: minimizing the charging duration and minimizing the increase in temperature. Both simulation and experiment demonstrate that the Pareto front of the proposed method dominates that of the most popular constant current constant voltage (CCCV) charge method.

State of Charge (SoC) estimation is one of the most significant and difficult techniques to promote the commercialization of electric vehicles (EVs). Suffering from various interference in vehicle driving environment and model uncertainties due to the strong time-variant property and inconsistency of batteries, the existing typical SoC estimators such as coulomb counting and extended Kalman filter cannot perform their theoretically optimal efficacy in practical applications. Aiming at enhancing the robustness of SoC estimation and improving accuracy under the real driving conditions with noises and uncertainties, this paper proposes a framework consisting of (1) an adaptive-κ nonlinear diffusion filter to reduce the noise in current measurement, (2) a self-learning strategy to estimate and remove the zero-drift, (3) a coulomb counting algorithm to realize open-loop SoC estimation, (4) an H∞ filter to implement closed-loop robust estimation, and (5) a data fusion unite to achieve the final estimation by integrating the advantages of the two SoC estimators. The availability and efficacy of each component have been demonstrated based on comparative studiesin simulation with the conventional approaches respectively, under the testing conditions of noises with various signal-noise-ratios, varying zero-drifts, and different model errors. The overall framework has also been verified to rationally and efficiently combine these components and achieve robust estimation results in the presence of kinds of noises and uncertainties.

With the substantial increase of vehicles on road, driving safety and transportation efficiency have become increasingly concerned focus from drivers, passengers, and governments. Wireless networks constructed by vehicles and infrastructures provide abundant information to share for the sake of both enhanced safety and network efficiency. This paper presents the systematic research to enhance the vehicle safety by wireless communication, in the aspects of information acquisition through vehicle sensing, vehicle-to-vehicle (V2V) routing protocol for the highly dynamic vehicle network, vehicle-to-infrastructure (V2I) routing protocol for a tradeoff in real-time performance and load balance, and hardware implementation of V2V system with on-road test. Simulations and experimental result validate the feasibility of the algorithms and communication system.

We present an intelligent driver identification system to handle vehicle theft based on modeling dynamic human behaviors. We propose to recognize illegitimate drivers through their driving behaviors. Since human driving behaviors belong to a dynamic biometrical feature which is complex and difficult to imitate compared with static features such as passwords and fingerprints, we find that this novel idea of utilizing human dynamic features for enhanced security application is more effective. In this paper, we first describe our experimental platform for collecting and modeling human driving behaviors. Then we compare fast Fourier transform (FFT), principal component analysis (PCA), and independent component analysis (ICA) for data preprocessing. Using machine learning method of support vector machine (SVM), we derive the individual driving behavior model and we then demonstrate the procedure for recognizing different drivers by analyzing the corresponding models. The experimental results of learning algorithms and evaluation are described.

Battery fast charging is one of the most significant and difficult techniques affecting the commercialization of electric vehicles (EVs). In this paper, we propose a fast charge framework based on model predictive control, with the aim of simultaneously reducing the charge duration, which represents the out-of-service time of vehicles, and the increase in temperature, which represents safety and energy efficiency during the charge process. The RC model is employed to predict the future State of Charge (SOC). A single mode lumped-parameter thermal model and a neural network trained by real experimental data are also applied to predict the future temperature in simulations and experiments respectively. A genetic algorithm is then applied to find the best charge sequence under a specified fitness function, which consists of two objectives: minimizing the charging duration and minimizing the increase in temperature. Both simulation and experiment demonstrate that the Pareto front of the proposed method dominates that of the most popular constant current constant voltage (CCCV) charge method. [ABSTRACT FROM AUTHOR]

State of Charge (SoC) estimation is one of the most significant and difficult techniques to promote the commercialization of electric vehicles (EVs). Suffering from various interference in vehicle driving environment and model uncertainties due to the strong time-variant property and inconsistency of batteries, the existing typical SoC estimators such as coulomb counting and extended Kalman filter cannot perform their theoretically optimal efficacy in practical applications. Aiming at enhancing the robustness of SoC estimation and improving accuracy under the real driving conditions with noises and uncertainties, this paper proposes a framework consisting of (1) an adaptive-κ nonlinear diffusion filter to reduce the noise in current measurement, (2) a self-learning strategy to estimate and remove the zero-drift, (3) a coulomb counting algorithm to realize open-loop SoC estimation, (4) an H∞ filter to implement closed-loop robust estimation, and (5) a data fusion unite to achieve the final estimation by integrating the advantages of the two SoC estimators. The availability and efficacy of each component have been demonstrated based on comparative studies in simulation with the conventional approaches respectively, under the testing conditions of noises with various signal-noise-ratios, varying zero-drifts, and different model errors. The overall framework has also been verified to rationally and efficiently combine these components and achieve robust estimation results in the presence of kinds of noises and uncertainties. [ABSTRACT FROM AUTHOR]

Abstract  In this paper, we discuss the problem of how human control strategy can be represented as a parametric model using a support vector machine (SVM) and how an SVM-based controller can be used in controlling dynamically stable systems. The SVM approach has been implemented in the balance control of Gyrover, which is a dynamically stable, statically unstable, single-wheel mobile robot. The experimental results that compare SVM with general artificial neural network approaches clearly demonstrate the superiority of the SVM approach with regard to human control strategy learning. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel approach for video-anomaly detection in crowded and complicated scenes. The proposed approach detects anomalies based on a hierarchical activity-pattern discovery framework, comprehensively considering both global and local spatio-temporal contexts. The discovery is a coarse-to-fine learning process with unsupervised methods for automatically constructing normal activity patterns at different levels. A unified anomaly energy function is designed based on these discovered activity patterns to identify the abnormal level of an input motion pattern. We demonstrate the effectiveness of the proposed method on the UCSD anomaly-detection datasets and compare the performance with existing work. [ABSTRACT FROM AUTHOR]