Search Results (138)

Lithium–ion (Li–ion) batteries are fundamental for advancing intelligent and sustainable transportation, particularly in electric vehicles, due to their long lifespan, high energy density, and strong power efficiency. Ensuring the safety and reliability of EV batteries remains a critical challenge, as undetected faults can lead to hazardous failures or gradual performance degradation. While numerous studies have addressed battery fault detection, most existing reviews adopt isolated perspectives, often overlooking interdisciplinary and intelligent approaches. This paper presents a comprehensive review of advanced battery fault detection using modern machine learning, deep learning, and hybrid methods. It also discusses the pressing challenges in the field, including limited fault data, real-time processing constraints, model adaptability across battery types, and the need for explainable AI. Furthermore, emerging AI approaches such as transformers, graph neural networks, physics-informed models, edge computing, and large language models present new opportunities for intelligent and scalable battery fault detection. Looking ahead, these frameworks, combined with AI-driven strategies, can enhance diagnostic precision, extend battery life, and strengthen safety while enabling proactive fault prevention and building trust in EV systems. Full article

Underwater exploration is vital for advancing scientific understanding of marine ecosystems, biodiversity, and oceanic processes. Autonomous underwater vehicles and sensor platforms play a crucial role in continuous monitoring, but their operational endurance is often limited by energy constraints. Various control strategies have been proposed to enhance energy efficiency, including robust and optimal controllers, energy-optimal model predictive control, and disturbance-aware strategies. Recent work introduced a variable structure depth controller for a sensor platform with a variable buoyancy module, resulting in a 22% reduction in energy consumption. This paper extends that work by providing a formal stability proof for the proposed switching controller, ensuring safe and reliable operation in dynamic underwater environments. In contrast to the conventional approach used in controller stability proofs for switched systems—which typically relies on the existence of multiple Lyapunov functions—the method developed in this paper adopts a different strategy. Specifically, the stability proof is based on a novel analysis of the system’s trajectory in the net buoyancy force-versus-depth error plane. The findings were applied to a depth-controlled sensor platform previously developed by the authors, using a well-established system model and considering physical constraints. Despite adopting a conservative approach, the results demonstrate that the control law can be implemented while ensuring formal system stability. Moreover, the study highlights how stability regions are affected by different controller parameter choices and mission requirements, namely, by determining how these aspects affect the bounds of the switching control action. The results provide valuable guidance for selecting the appropriate controller parameters for specific mission scenarios. Full article

This study presents an adaptive integrated chassis control strategy for enhancing vehicle stability under different road conditions, specifically through the real-time estimation of tire cornering stiffness. A hierarchical control architecture is developed, combining active front steering (AFS) and direct yaw moment control (DYC). A recursive regularized weighted least squares algorithm is designed to estimate tire cornering stiffness from measurable vehicle states, eliminating the need for additional tire sensors. Leveraging this estimation, an adaptive sliding mode controller (ASMC) is proposed in the upper layer, where a novel self-tuning mechanism adjusts control parameters based on tire saturation levels and cornering stiffness variation trends. The lower-layer controller employs a weighted least squares allocation method to distribute control efforts while respecting physical and friction constraints. Co-simulations using MATLAB 2018a/Simulink and CarSim validate the effectiveness of the proposed framework under both high- and low-friction scenarios. Compared with conventional ASMC and DYC strategies, the proposed controller exhibits improved robustness, reduced sideslip, and enhanced trajectory tracking performance. The results demonstrate the significance of the real-time integration of tire dynamics into chassis control in improving vehicle handling and stability. Full article

As a fundamental technology in environmental perception, sound source localization (SSL) plays a critical role in public safety, marine exploration, and smart home systems. However, traditional methods such as beamforming and time-delay estimation rely on manually designed physical models and idealized assumptions, which struggle to meet practical demands in dynamic and complex scenarios. Recent advancements in deep learning have revolutionized SSL by leveraging its end-to-end feature adaptability, cross-scenario generalization capabilities, and data-driven modeling, significantly enhancing localization robustness and accuracy in challenging environments. This review systematically examines the progress of deep learning-based SSL across three critical domains: marine environments, indoor reverberant spaces, and unmanned aerial vehicle (UAV) monitoring. In marine scenarios, complex-valued convolutional networks combined with adversarial transfer learning mitigate environmental mismatch and multipath interference through phase information fusion and domain adaptation strategies. For indoor high-reverberation conditions, attention mechanisms and multimodal fusion architectures achieve precise localization under low signal-to-noise ratios by adaptively weighting critical acoustic features. In UAV surveillance, lightweight models integrated with spatiotemporal Transformers address dynamic modeling of non-stationary noise spectra and edge computing efficiency constraints. Despite these advancements, current approaches face three core challenges: the insufficient integration of physical principles, prohibitive data annotation costs, and the trade-off between real-time performance and accuracy. Future research should prioritize physics-informed modeling to embed acoustic propagation mechanisms, unsupervised domain adaptation to reduce reliance on labeled data, and sensor-algorithm co-design to optimize hardware-software synergy. These directions aim to propel SSL toward intelligent systems characterized by high precision, strong robustness, and low power consumption. This work provides both theoretical foundations and technical references for algorithm selection and practical implementation in complex real-world scenarios. Full article

Autonomous race driving has emerged as a challenging domain for reinforcement learning (RL) applications, requiring high-speed control while adhering to strict safety constraints. Existing RL-based racing methods often struggle to balance performance and safety, with limited adaptability in dynamic racing scenarios with multiple opponent vehicles. The high-dimensional state space and strict safety constraints pose significant challenges for efficient learning. To address these challenges, this paper proposes an integrated RL framework that combines three novel components: (1) a state mapping mechanism that dynamically transforms raw track observations into a consistent representation space; (2) an action mapping technique that rigorously enforces physical traction constraints; and (3) a safe exploration guidance method that combines conservative controllers with RL policies, significantly reducing off-track incidents during training. Extensive experiments conducted in our simulation environment with four test tracks demonstrate the effectiveness of our approach. In time trial scenarios, our method improves lap times by 12–26% and increases the training completion rate from 33.1% to 78.7%. In competitive racing, it achieves a 46–51% higher average speed compared to baseline methods. These results validate the framework’s ability to achieve both high performance and safety in autonomous racing tasks. Full article

The large-scale integration of renewable energy and electric vehicles(EVs) into power distribution systems presents complex operational challenges, particularly in coordinating market mechanisms with grid stability requirements. This study proposes a new dispatching method based on dynamic electricity prices to coordinate the relationship between the market and the physical characteristics of the power grid. The proposed approach introduces a multi-agent transaction model incorporating voltage regulation metrics and network loss considerations into market bidding mechanisms. For EV integration, a differentiated scheduling strategy categorizes vehicles based on usage patterns and charging elasticity. The methodological innovations primarily include an enhanced scheduling algorithm for coordinated optimization of renewable energy and energy storage, and a dynamic coordinated optimization method for EV clusters. Implemented on a modified IEEE test system, the framework demonstrates improved voltage stability through price-guided energy storage dispatch, with coordinated strategies effectively balancing peak demand management and renewable energy utilization. Case studies verify the system’s capability to align economic incentives with technical objectives, where time-of-use pricing dynamically regulates storage operations to enhance reactive power support during critical periods. This research establishes a theoretical linkage between electricity market dynamics and grid security constraints, providing system operators with a holistic tool for managing high-renewable penetration networks. By bridging market participation with operational resilience, this work contributes actionable insights for developing interoperable electricity market architectures in energy transition scenarios. Full article

Integrated Sensing and Communication (ISAC) has been enhanced to serve as a pivotal enabler for next-generation communication systems. In the context of target area detection, a UAV-SAR (Unmanned Aerial Vehicle–Synthetic Aperture Radar) based ISAC system, which shares both physical infrastructure and spectrum, can enhance the utilization of spectrum and hardware resources. However, existing studies on UAV-SAR-based ISAC systems for target imaging remain limited. In this study, we first established an ISAC mechanism to enable SAR imaging and communication. Then, we analyzed the energy consumption model, which includes both UAV propulsion and ISAC energy consumption. To maximize system energy efficiency, we propose an optimization method based on sequential convex optimization with linear state-space approximation. Furthermore, we propose a plan with general constraints, including the initial and final positions, the signal-to-noise ratio (SNR) constraint for SAR imaging, the data transmission rate constraint, and the total power limitation of the UAV. To achieve maximum energy efficiency, we jointly optimized the UAV’s trajectory, velocity, communication beamforming, sensing beamforming, and power allocation. Numerical results demonstrate that compared to existing benchmarks and PSO algorithms, the proposed method significantly improves the energy efficiency of UAV-SAR-based ISAC systems through optimized trajectory design. Full article

Traffic congestion in urban areas presents significant challenges to mobility, road safety, and the overall quality of the urban traffic network. This study presents a simulation-based modeling framework for dynamic lane assignment (DLA) systems designed to optimize traffic flow on Vukovar Street in Zagreb, Croatia, which is an urban corridor where the existing infrastructure fails to meet capacity demands during peak morning and afternoon hours. Using real-time traffic data and the PTV VISSIM environment, an adaptive DLA model responsive to current traffic conditions was developed and evaluated. The proposed model improves traffic flow efficiency with minimal physical infrastructure changes, focusing on maximizing capacity within existing corridor constraints. The results of this research indicate that the proposed model reduces average vehicle delay by 21.4% and shortens queue lengths by 19%. The effectiveness of the DLA approach is evaluated through comparative analysis with traditional static traffic configurations, demonstrating significant improvements in traffic efficiency, reduced travel times, and enhanced network performance. While this study is limited to a simulation environment, it provides a strong foundation for future real-world applications and offers a practical approach to improving traffic network efficiency. Full article

The proliferation of cyber–physical systems in modern vehicles, characterized by densely interconnected Electronic Control Units (ECUs) and heterogeneous communication networks, has significantly expanded the automotive attack surface. Traditional Threat Analysis and Risk Assessment (TARA) methodologies remain predominantly manual processes that exhibit limitations in scalability, and comprehensive threat identification. This research addresses these limitations by developing a formalized framework for automating attack path analysis within the automotive architecture. While attack graph methodologies have demonstrated efficacy in conventional information technology domains, their application within automotive cybersecurity contexts presents unique challenges stemming from domain-specific architectural constraints. We propose a novel Graph-based Attack Path Prioritization (GAPP) methodology that integrates Extended Finite State Machine (EFSM) modeling. Our implementation employs the Neo4j property graph database architecture to establish the mappings between architectural components, security states, and exploitation vectors. This research contributes a systematic approach to automotive security assessment, enhancing vulnerability identification capabilities while reducing analytical complexity. Full article

With the widespread adoption of electric vehicles (EVs), optimizing their charging and discharging strategies to improve energy efficiency and extend battery life has become a focal point of current research. Traditional charging and discharging strategies often fail to adequately consider the battery’s state of health (SOH), resulting in accelerated battery aging and decreased efficiency. In response, this paper proposes a safe reinforcement learning–based optimization method for EV charging and discharging strategies, aimed at minimizing charging and discharging costs while accounting for battery SOH. First, a novel battery health status prediction model based on physics-informed hybrid neural networks (PHNN) is designed. Then, the EV charging and discharging decision-making problem, considering battery health status, is formulated as a constrained Markov decision process, and an interior-point policy optimization (IPO) algorithm based on long short-term memory (LSTM) neural networks is proposed to solve it. The algorithm filters out strategies that violate constraints by introducing a logarithmic barrier function. Finally, the experimental results demonstrate that the proposed method significantly enhances battery life while maintaining maximum economic benefits during the EV charging and discharging process. This research provides a novel solution for intelligent and personalized charging strategies for EVs, which is of great significance for promoting the sustainable development of new energy vehicles. Full article

The reliable and uncertainty-aware prediction of surrounding vehicles remains a key challenge in autonomous driving. However, existing methods often struggle to quantify and incorporate uncertainty effectively. To address these challenges, we propose a hybrid architecture that combines a data-driven neural trajectory predictor with physically grounded constraints to forecast future vehicle occupancy. Specifically, the physical constraints are derived from vehicle kinematic principles and embedded into the network as additional loss terms during training. This integration ensures that predicted trajectories conform to feasible and physically realistic motion boundaries. Furthermore, a mixture density network (MDN) is employed to estimate predictive uncertainty, transforming deterministic trajectory predictions into spatial probability distributions. This enables a probabilistic occupancy representation, offering a richer and more informative description of the potential future positions of surrounding vehicles. The proposed model is trained and evaluated on the Aerial Dataset for China’s Congested Highways and Expressways (AD4CHE), which contains representative driving scenarios in China. Experimental results demonstrate that the model achieves strong fitting performance while maintaining high physical plausibility in its predictions. Full article

This article presents an alternative variant of motion planning techniques for autonomous vehicles (AVs) centered on an inverse approach that concurrently optimizes both trajectory and speed. This method emphasizes searching for a trajectory and distributing its speed within a single road segment, regarded as a final element. The references for the road lanes are represented by splines that interpolate the path length, derivative, and curvature using Cartesian coordinates. This approach enables the determination of parameters at the final node of the road segment while varying the reference length. Instead of directly modeling the trajectory and velocity, the second derivatives of curvature and speed are modeled to ensure the continuity of all kinematic parameters, including jerk, at the nodes. A specialized inverse numerical integration procedure based on Gaussian quadrature has been adapted to reproduce the trajectory, speed, and other key parameters, which can be referenced during the motion tracking phase. The method emphasizes incorporating kinematic, dynamic, and physical restrictions into a set of nonlinear constraints that are part of the optimization procedure based on sequential quadratic optimization. The objective function allows for variation in multiple parameters, such as speed, longitudinal and lateral jerks, final time, final angular position, final lateral offset, and distances to obstacles. Additionally, several motion planning variants are calculated simultaneously based on the current vehicle position and the number of lanes available. Graphs depicting trajectories, speeds, accelerations, jerks, and other relevant parameters are presented based on the simulation results. Finally, this article evaluates the efficiency, speed, and quality of the predictions generated by the proposed method. The main quantitative assessment of the results may be associated with computing performance, which corresponds to time costs of 0.5–2.4 s for an average power notebook, depending on optimization settings, desired accuracy, and initial conditions. Full article

Self-driving technology aims to minimize human error and improve safety, efficiency, and mobility through advanced autonomous driving algorithms. Among these, Model Predictive Control (MPC) is highly valued for its optimization capabilities and ability to manage constraints. However, its effectiveness depends on an accurate system model, as modeling errors and disturbances can degrade performance, making uncertainty management crucial. Learning-based MPC addresses this challenge by adapting the predictive model to changing and unmodeled conditions. However, existing approaches often involve trade-offs: robust methods tend to be overly conservative, stochastic methods struggle with real-time feasibility, and deep learning lacks interpretability. Sparse regression techniques provide an alternative by identifying compact models that retain essential dynamics while eliminating unnecessary complexity. In this context, the Sparse Identification of Nonlinear Dynamics (SINDy) algorithm is particularly appealing, as it derives governing equations directly from data, balancing accuracy and computational efficiency. This work investigates the use of SINDy for learning and adapting vehicle dynamics models within an MPC framework. The methodology consists of three key phases. First, in offline identification, SINDy estimates the parameters of a three-degree-of-freedom single-track model using simulation data, capturing tire nonlinearities to create a fully tunable vehicle model. This is then validated in a high-fidelity CarMaker simulation to assess its accuracy in complex scenarios. Finally, in the online phase, MPC starts with an incorrect predictive model, which SINDy continuously updates in real time, improving performance by reducing lap time and ensuring a smoother trajectory. Additionally, a constrained version of SINDy is implemented to avoid obtaining physically meaningless parameters while aiming for an accurate approximation of the effects of unmodeled states. Simulation results demonstrate that the proposed framework enables an adaptive and efficient representation of vehicle dynamics, with potential applications to other control strategies and dynamical systems. Full article

This paper summarizes the latest research progress in the field of motion control of autonomous underwater vehicles (AUVs), focusing on three core technologies: path following, trajectory tracking and multi-AUV formation control. Aiming at the external disturbances faced by AUVs performing tasks in complex marine environments as well as the system’s own inherent nonlinearities, model uncertainties, and physical constraints, it analyzes the advantages and shortcomings of the traditional control methods and intelligent control strategies in terms of improving the tracking accuracy, enhancing the robustness of the system, and realizing the cooperative operation. Recent advances in distributed control and multi-AUV cooperative operations, including leader–follower, consistency control, virtual structure and behavior control, and other formation control strategies, are also discussed. Finally, the future development trend of AUV control technology is outlooked, pointing out that intelligent control, multi-sensor fusion navigation, and distributed synergy will become an important direction to enhance the operational capability and adaptability of AUVs. This review aims to provide theoretical references and technical support for AUV applications in the fields of marine resource exploration and environmental monitoring. Full article

Addressing the limitations of restricted coding capacity and material dependency in acoustic identity tags for autonomous underwater vehicles (AUVs), this study introduces a novel passive acoustic identification tag (AID) design based on multilayered elastic cylindrical shells. By developing a Normal Mode Series (NMS) analytical model and validating it through finite element method (FEM) simulations, the work elucidates how material layering strategies regulate far-field target strength (TS) and establishes a time-domain multi-peak echo-based encoding framework. Results demonstrate that optimizing material impedance contrasts achieves 99% detection success at a 3 dB signal-to-noise ratio. Jaccard similarity analysis of 3570 material combinations reveals a system-wide average recognition error rate of 0.41%, confirming robust encoding reliability. The solution enables the combinatorial expansion of coding capacity with structural layers, yielding 210, 840, and 2520 unique codes for three-, four-, and five-layer configurations, respectively. These findings validate a scalable, hull-integrated acoustic identification system that overcomes material constraints while providing high-capacity encoding for compact AUVs, significantly advancing underwater acoustic tagging technologies through physics-driven design and systematic performance validation. Full article