Accurate prediction of vehicle trajectories in complex traffic environments is essential for path planning and safety decisions in autonomous driving systems. However, purely data-driven models lack physical constraints, making it challenging to ensure reliability and consistency in dynamic traffic scenarios, while physics models face challenges in maintaining long-term prediction reliability under complex traffic conditions. To address these issues, a trajectory prediction method is proposed by combining a data-driven model based on graph neural networks and Informer with a physics model, fused through discriminative learning. Firstly, graph neural networks are utilized to extract spatial information, and the Informer is used for long-term trajectory encoding and decoding to capture the temporal dynamics of trajectories. Then, to improve the physical plausibility of trajectory predictions, a kinematic model with Cubature Kalman Filtering is employed to estimate the trajectory distribution. Furthermore, discriminative learning is designed to fuse a physics model into the decoder of the data-driven model using a generative adversarial approach. This paper conducts ablation experiments and comparative tests on real-world highway trajectory data from the NGSIM dataset. The evaluation confirms that the proposed method achieves consistent and high-quality prediction results across multiple scenarios.

Gear ratio optimization is essential for improving transmission efficiency and dynamic performance of four-wheel distributed drive electric heavy trucks. This study proposes a gear ratio optimization method that integrates battery health and shifting-induced energy losses and considers shift frequency. The method employs particle swarm optimization to optimize front and rear axle gear ratios under realistic truck operating conditions, followed by dynamic programming to determine the optimal gear-shifting sequence and real-time torque allocation. Through iterative refinement, the proposed method achieves optimal gear ratios of [32.17, 18.16] for the front axle and [35.53, 14.61] for the rear axle. Simulation results demonstrate that the optimized configuration reduces annual operational costs by 0.5%-1.9% compared to other optimization methods, yielding savings of 103,328 RMB per year while mitigating battery degradation and kinetic energy loss during gear shifts.

For distributed drive electric vehicles, energy consumption is affected by the power demand and energy management strategy. In this paper, an adaptive cruise control and energy management strategy cooperative framework for dual-motor electric vehicles is proposed based on the deep deterministic policy gradient algorithm. Firstly, the energy management problem in the car-following scenario is decomposed into two subproblems: the adaptive cruise control governs vehicle acceleration, while the energy management strategy allocates driving torque. Then, based on the cooperative architecture, the speed trajectory and torque allocation strategy are co-optimized to realize cooperation between the adaptive cruise control and the energy management strategy. Finally, the proposed cooperative strategy is compared with the traditional hierarchical strategy under the worldwide harmonized light vehicles test cycle. Results show that the proposed cooperative strategy can reduce the maximum acceleration and maximum deceleration by 10.8% and 10.4%, respectively, and improve energy consumption by 4.3% compared with the traditional hierarchical strategy.

Continuous sign language recognition seeks to identify unsegmented sign language from videos by means of a weakly supervised manner, providing only sentence-level labels. In sign language videos, the gestures are smooth and continuous, and the same word may also correspond to video clips of different scales. Therefore, this poses a challenge in accurately capturing complex temporal dependencies. For hearing-impaired service robots, continuous sign language recognition capability is particularly critical, as the robots need to understand the natural sign language expressions of hearing-impaired users in real time. Previous studies have shown that using methods with a time-invariant receptive field for temporal modeling can partially address this issue, but they are not well-suited to handle video clips of varying scales. In this study, we re-examined the temporal modeling schemes in recent CSLR works and proposed the Two-stage Temporal ConvTransformer (T2CT), which fully leverages the advantages of one-dimensional convolutional neural networks and Transformer encoders, adopting a two-stage structure to capture more comprehensive spatiotemporal features. In particular, each stage of the proposed T2CT consists of two parts: a Local Temporal Modeling Module to capture short-term temporal dependencies, and a Global Temporal Modeling Module for long-term temporal modeling. Experimental results on three challenging CSLR datasets demonstrate that the proposed T2CT achieves competitive performance.

Accurate prediction of lithium-ion battery capacity degradation and remaining useful life (RUL) is crucial for battery health management and the safe operation of equipment. However, the diversity of battery types and variations in usage environments pose challenges to data-driven predictive models. Traditional machine learning models often exhibit poor performance in terms of prediction and generalization capabilities. This paper introduces a time-series large model: ANVMD-Llama. The model employs Adaptive Noise Variational Mode Decomposition (ANVMD) to process battery aging data for RUL prediction. Initially, the adaptive noise variational mode decomposition optimizes the tokenization scheme of Lag-Llama, decomposing battery degradation data into multiscale modal components with distinct features to characterize degradation trends and fluctuation properties, aiding the model in understanding fluctuation patterns. Subsequently, ANVMD-Llama is pre-trained on a large dataset of diverse lithium-ion battery degradation data to learn capacity degradation patterns. The model is then fine-tuned using a small amount of data to update the top-level modules, achieving more accurate predictions. Finally, the experimental results demonstrate that the proposed model achieves accurate RUL prediction and exhibits strong transfer capability.

Accurate and rapid state-of-health (SOH) estimation of retired lithium-ion batteries is critical for sustainable recycling and second-life applications. However, data-driven methods face challenges due to data scarcity and heterogeneity under random retirement conditions, such as varying states of charge (SOC). This study proposes a generative learning framework based on a vector quantized-variational autoencoder (VQ-VAE) to generate synthetic battery pulse voltage response data, enabling robust SOH estimation without exhaustive physical measurements. The VQ-VAE model leverages cross-attention mechanisms to capture dependencies between SOC conditions and voltage responses, generating high-fidelity data for unseen retirement scenarios. Experimental results demonstrate that the generated data achieve a mean absolute percentage error (MAPE) below 6% for SOH estimation across diverse battery types, including nickel manganese cobalt oxide (NMC), lithium iron phosphate (LFP), and lithium manganese oxide (LMO).

Microgrids based on distributed control are susceptible to cyber attacks during operation, which can result in system anomalies, crashes, and even equipment damage. To ensure a secure collaborative environment, this paper proposes an attack detection mechanism based on extended cell similarity. First, a DC microgrid model and a network attack model were established. Secondly, a microgrid state interval prediction mechanism based on QRLSTM is proposed. The output of the load prediction model is used as the input of the mechanism model, and the expected state range of the terminal equipment voltage and current is obtained through simulation. Then, the cell similarity algorithm is improved to relate the similarity between the actual measured data and the expected period to the probability of cyber attacks occurring. Finally, the effectiveness and feasibility of the detection method were verified through experiments.

In 5G and beyond, discontinuous reception (DRX) is a promising energy-saving technology for massive machine-type communications (mMTC) devices with intermittent connections. However, existing DRX solutions face challenges in effectively accommodating mMTC services with critical delay requirements, particularly in a dynamic wireless environment. To address this problem, this paper proposes an intelligent DRX scheme for critical mMTC. Firstly, we modify the conventional discontinuous reception model by introducing the critical delay flag. Then we optimize the DRX by Markov Decision Process and designe the energy-delay factor to achieve the simultaneous optimization. Finally, we extract the environmental features by convolutional neural network and solve the problem by deep Q-network. A communication simulation platform is established to verify the effectiveness of the proposed method. The simulation results show that the proposed method can effectively improve the energy efficiency in mMTC situations compared with state-of-the-art.

In truck platoons with a bidirectional-leader topology, variations in channel conditions result in unreliability and high latency in vehicle-to-vehicle (V2V) communications. This paper proposes an adaptive relay selection strategy based on Q-learning (QL). The strategy ensures that all vehicles in the platoon receive safety messages from the lead vehicle quickly and reliably. Firstly, relay selection is modeled as a Markov decision process (MDP). The lead vehicle and the relays act as intelligent agents. Agents make decisions adaptively based on real-time state observations in a dynamic communication environment. Secondly, a reward function is designed based on platoon topology and channel state information statistics (CSI). The purpose is to drive the proposed strategy to learn the optimal strategy for message transmission under different environments. Lastly, the simulation results demonstrate the effectiveness and robustness of the proposed algorithm. In various channel attenuation environments, the strategy has been demonstrated to enhance the packet delivery ratio (PDR) for the platoon tail and significantly increase the platoon’s throughput.

Lithium-ion batteries are increasingly critical in portable and electrical technologies, making accurate estimations of their State of Health essential for extending battery life and ensuring safety. This study proposes a novel State of Health estimation model that integrates transfer learning with a Retentive Network architecture, addressing the limitations of traditional methods in data processing and feature extraction. By pre-training a model adaptable to various battery types, the approach leverages the Retentive Network’s powerful temporal data processing capabilities, enabling end-to-end application to raw data and reducing the need for complex preprocessing. The model utilizes a dual-stream parallel network architecture to extract valuable information from both charging and discharging data, significantly enhancing the accuracy of State of Health estimation. Furthermore, the model can quickly adapt to new or sparsely sampled battery types through pre-training and fine-tuning strategies, minimizing reliance on large labeled datasets. Compared with existing transfer learning approaches, the proposed model demonstrates superior performance in terms of accuracy and robustness, particularly in handling long-term degradation patterns. Extensive experiments on multiple public datasets show that the model consistently achieves a Mean Absolute Error below 0.90% and a Root Mean Square Error below 0.95%, confirming its effectiveness and precision. This research provides novel insights and methodologies for optimizing battery performance and improving management practices.

Battery degradation is a main hinder to extend the persistent lifespan of the portable heterogeneous computing device. Excessive energy consumption and prominent current fluctuations can lead to a sharp decline of battery endurance. To address this issue, a battery-aware workflow scheduling algorithm is proposed to maximize the battery lifetime and release the computing potential of the device fully. Firstly, a dynamic optimal budget strategy is developed to select the highest cost-effectiveness processors to meet the deadline of each task, accelerating the budget optimization by incorporating deep neural network. Second, an integer-programming greedy strategy is utilized to determine the start time of each task, minimizing the fluctuation of the battery supply current to mitigate the battery degradation. Finally, a long-term operation experiment and Monte Carlo experiments are performed on the battery simulator, SLIDE. The experimental results under real operating conditions for more than 1800 hours validate that the proposed scheduling algorithm can effectively extend the battery life by 7.31%-8.23%. The results on various parallel workflows illustrate that the proposed algorithm has comparable performance with speed improvement over the integer programming method.

High-reliability and low-latency communication is essential for timely information exchange in vehicle platooning. As a key enabler of this, the cellular vehicular-to-everything (C-V2X) network uses a sensing-based semi-persistent scheduling (SPS) protocol, where radio resources are reserved for a number of transmissions with reduced resource re-allocation and control overhead. However, consecutive access collisions may be caused by reservation conflict, which leads to long delay and threatens platoon’s stability and safety. In this paper, a coordinating resource reservation (CRR) protocol is proposed for vehicle platooning. By implementing error detection with coordination among platoon vehicles, the resource reservation is improved for reduced collisions and delay. Specifically, packet reception/loss information is sent out by platoon vehicles through their own packets. Such information is shared with transmitters and guides them to reserve new resources when access collision occurs. As a result, long delay is avoided while no extra feedback packet is introduced. Furthermore, Markov analysis is presented to evaluate the performance of SPS and the proposed CRR for vehicle platooning, providing the quantified performance gains. Finally, simulation results demonstrate the superiority of the proposed CRR in reducing packet loss and latency, compared with the legacy SPS and other state-of-the-art solutions.

The braking system is the key part of trains, and its full life-cycle of health status is essential to ensure the safety of trains. How to accurately assess real-time health status throughout the full life-cycle of the train braking system is a challenge. In this paper, a digital twin-driven hybrid estimate method for health status of the braking system is proposed. Firstly, an equivalent model of the braking system is built in the digital twin platform. Then, a hybrid method of fusing model and data is proposed to assess the health status. Finally, a cloud digital twin experimental platform for health status assessment of the braking system is built, and the health status is shown by visualization framework. The experiments verify the effectiveness and practicality of the proposed scheme.

Vehicle platooning utilizes automated driving and communication to let a group of vehicles travel closely, which improves road safety, traffic efficiency and fuel economy. In a platoon system, a critical task is to guarantee reliable communication among vehicles with efficient medium access control (MAC). This paper focuses on the feasibility of the distributed resource reservation MAC for communications among platoon vehicles using the cellular vehicle-to-everything (C-V2X) technology. For this purpose, a Markov chain-based model is proposed, which precisely estimates the network performance with different information flow topologies and system configurations. The state transition matrix is deduced and the stable state distribution is obtained. Given the information flow topology, we derive the probability that a platoon vehicle successfully delivers packets to all of the designated receivers. Finally, simulation results validate the analysis. To better implement the MAC protocol in practice, we also discuss the success probability for various information flow topologies in platoon communication.

For autonomous vehicles and smart transportation services, information exchange and fusion with low latency and high reliability is critical. The 3rd Generation Partnership Project has released the cellular vehicle-to-everything (C-V2X) Mode 4 to enable direct vehicle-to-vehicle communications regardless of the cellular coverage. Mode 4 uses the sensing-based semi-persistent resource scheduling (SPS) to support autonomous resource selection by vehicles. However, channel access collisions lead to packet losses, especially in crowded scenarios. Thus, an accurate analytical model is essential to quantify the system performance, reveal how to mitigate collision and ensure system reliability and scalability. This paper focuses on the analytical modeling of the SPS and derives the access collision ratio considering both the sensed and hidden terminals in V2X. Extended simulations are conducted to verify the correctness of the analytical framework. In addition, we investigate the impact of system parameters on performance, which provides important guidelines for improving the system configuration.

Logistics distribution is an important link in logistics. Whether the logistics distribution path can be effectively optimized will directly affect the efficiency of the logistics distribution system. To plan the logistics distribution path reasonably, to reduce the cost of logistics management, for the multi-object path planning problem in logistics distribution, the fireworks differential evolution algorithm is used to design an optimization scheme. To achieve the overall goal of saving logistics and distribution costs, real number coding is used for each distribution point, and actual road information is obtained through the Gaode API. Aiming at the defects of the standard fireworks algorithm, the differential evolution algorithm is introduced based on the fireworks algorithm to plan the distribution route. The simulation results show that the firework differential evolution algorithm can effectively plan the optimal distribution path, and compared with the original firework algorithm, the ant colony algorithm and particle swarm optimization algorithm have a better improvement in the optimization accuracy.

Home energy management plays a key role in demand response for residential customers to reduce the total cost via scheduling household loads energy consumption. However, excessive energy consumption by customers will bring a great challenge to the stability of the grid. To address the challenge, a day-ahead multi-agent reinforcement learning method is proposed for home energy management under a peak power-limiting. We first formulate the total cost minimization problem as a Markov game, and then a novel household loads energy consumption scheduling algorithm is proposed based on Mutil-agent Deep Deterministic Policy Gradient (MADDPG). It is worth mentioning that the proposed algorithm can achieve cooperation between agents so that it can meet the peak power-limiting constraint. Simulation results are provided in this paper to show the effectiveness of the proposed method.

The high-speed solenoid valve is a crucial module in train braking system, which is an essential factor to ensure the safe operation of trains. How to estimate the health status of the high-speed solenoid valve accurately to improve the reliability of train braking system is a challenging issue. Most related work relies on accurate physical models or large amounts of historical data. To address this challenge, this paper proposes a hybrid data-fusion estimate method for the health status of train braking system. Firstly, the physical model of the high-speed solenoid valve is established, and physical indicators which represent the working performance are extracted. Then, the dynamic driving current is processed by ensemble empirical mode decomposition (EEMD) to calculate the information entropy. Physical indicators and information entropy indicators are combined into a feature vector, which can be reduced the dimension by the t-distributed stochastic neighbor embedding (T-SNE) algorithm. Finally, the feature vector is input into the probabilistic neural network (PNN) to estimate the health status of train braking system. The proposed method is implemented in the high-speed solenoid valve degradation dataset, which collected by the train brake system experiment platform. The result shows that it is better than other methods in the accuracy and calculation efficiency.

Different from previous data-driven methods for lithium-ion battery State-of-Charge (SoC) estimation, this paper aims to develop a hierarchical SoC estimation method to address the data dependency issue and measurement noise interferences. In the off-line training layer, aging-aware features are extracted to improve SoC estimation accuracy throughout the entire battery life cycle. Extreme gradient boosting (XGBoost) is introduced to map the relationship between the extracted features and SoC for its strong nonlinear fitting ability. In the on-line estimation layer, Ampere-hour integral method is utilized to provide SoC reference to guarantee the stability of the proposed method. Meanwhile, to suppress the measurement noise, we adopt Kalman filter to correct the SoC value estimated by XGBoost. The superiority of the proposed method is proved under the random walk discharging experiment by comparing with the results of XGBoost, i.e., without Kalman filter. The proposed method improved the accuracy of lithium-ion battery SoC by 4% to 10%.

The vehicular service support with adaptability, real-time, and low delay is crucial for connected vehicles. However, due to limited coverage of mobile edge computing servers and data processing capability of connected vehicles, vehicular services need to be offloaded to the edge server and adaptively migrate as the connected vehicle moves. Aiming at the adaptive migration service, a deep Q-learning service migration decision algorithm is proposed in this paper. The proposed algorithm can dynamically adjust the vehicular service migration decision according to traffic information. Furthermore, a service migration framework consisting of neural networks is proposed in this paper to improve the adaptability and real-time performance of the algorithm. By using this framework, training and decision-making can be carried out simultaneously in different places. Finally, compared with the two existing algorithms, extensive simulations are conducted to verify the effectiveness of the proposed algorithm.

Currently, the robot is playing an increasingly significant role in managing a warehouse. This paper proposes an optimal method to help a warehouse robot make task decisions, which aims at minimizing the whole cost of completing multiple tasks. Firstly, Abstract Transition System (ATS) is used to model the warehouse environment, and Linear Temporal Logic (LTL) formula is used to formulate the tasks of warehouse robot. Then based on the ATS and the Büchi automaton translated from the LTL formula, a Min-cost Task Decision Algorithm is proposed to obtain the task decision for the warehouse robot. The decision points out the optimal order and path for the robot to do its tasks. The effectiveness of the proposed method is validated through case studies with two kinds of tasks.

With the rapid development of inspection techniques, more emphases should be placed on the improvement of the reliability, safety and intelligence of the robot system. In this paper, a framework for the patrol robot that automatically finishes complex task and motion planning in the indoor substation is proposed. To realize real-time response to the environmental changes, the proposed framework keeps an ongoing interaction with the environment as a Reactive System (RS). The RS employs the Transition System (TS) and Nondeterministic Biichi Automaton (NBA) to create a discrete controller that bounds the acts of the patrol robot in the safe and reasonable specifications. What's more, the environment signals are treated as the trigger condition of task switching. If a new environment information is detected, our approach can automatically give a feasible plan. Then, the sensor-based mechanism of continuous controllers is guided by the discrete controller, which results in a hybrid system satisfying the high-level specification. The experiment within the LTLMoP toolkit verifies the proposed framework.

This paper presents a novel vision servoing approach using depth maps to perform robotic motion task with field of view (FOV) constraint. The vision servoing scheme relies on the depth information available from an Red Green Blue-Depth (RGB-D) camera. With respect to the previous approaches, the proposed vision servoing approach has the advantage as follow: First, it does not require the estimation of 3D pose, which only relies on the error of depth maps, without feature matching. Moreover, this method addresses the problem of field of view constraint in the motion process by the frame pose estimation. This visual servoing system is computation efficiency, because it does not need the descriptor and estimation of the pose parameters. We drive the robot towards the target position by the depth map error minimizing. Both simulation and experimental results are provided to demonstrate the effectiveness of the proposed depth map-based vision servoing method.

Recently, mobile cloud offloading is a promising technique to deal with the increasingly complex applications on mobile devices, meeting the ever- increasing energy requirements. However, cloud offloading with multiple mobile devices may cause considerable mutual interference, which may result in intolerable time delay and more energy consumption. In this paper, a novel offloading decision method is investigated to minimize the total energy consumption of mobile devices over cellular networks. Generally, mobile devices can execute a sequence of tasks in parallel with different characteristics, i.e., communication- intensive and computation-intensive. And recent advances show that only computation-intensive tasks are applicable to be offloaded for energy saving. The offloading decision issue is formulated as a NP- hard combinatorial optimization problem with the time deadline and communication quality constraints. Combining the problem linearization method and decision variables mapping from integer to the real domain, a rapid and efficient iterative approximation method is proposed, helping the cloud controller to select the best tasks for offloading aiming at minimizing the total energy consumption. Numerical simulation demonstrates that considerable energy can be saved with the proposed task offloading method in mobile cloud scenarios.

Effective handoff scheme is an important issue in heterogeneous wireless networks. In this paper, we propose a context-aware-based vertical handoff decision scheme for heterogeneous wireless networks. A linear fuzzy membership function is employed to normalize dynamic environmental information, such as terminal's position, speed and link quality. In this scheme, energy consumption is introduced to judge whether to handoff or not, and the candidate handoff networks are determined by the network speed threshold. We also present a comprehensive utility evaluation function to evaluate networks quality, and the weights of decision factors are calculated by analytic hierarchy process(AHP). Then, the target handoff network is selected adaptively according to the comprehensive utility of candidate networks. Specifically, we consider a knowledge base to match the environmental state with target handoff network. Simulation results show that the proposed handoff decision scheme could effectively avoid unnecessary handoff.