Mixed platoons, consisting of connected autonomous vehicles (CAVs) and human-driven vehicles (HDVs), are expected to dominate future roadways. However, achieving substantial improvements in fuel economy and safety under time-varying, mixed traffic conditions in real-world scenarios remains challenging. To this aim, this paper proposes a deep reinforcement learning (DRL) based decentralized control strategy, which consists of two levels: 1) At the methodology level, the hierarchical platoon formation algorithm systematically organizes the mixed platoons into local platoons with uniform car-following patterns and sub-platoons within a generic HDV-CAVs structure, enabling adaptation to time-varying traffic volume and mixed traffic heterogeneity. 2) At the operation level, the HDV-CAVs unit is embedded in the learning environment to capture uncertain HDV behaviors through state and reward propagation channels. Multiple objectives are explicitly integrated into the reward function. A safety-supervised decentralized proximal policy optimization algorithm is developed to enhance safety and training efficiency. Extensive validations demonstrate the effectiveness of the proposed strategy in improving fuel economy and safety under different traffic demand levels and penetration rates.

Deep neural networks are highly effective at transforming sparse and unstructured data into dense and semantic representations, demonstrating strong capabilities in object detection tasks. However, their performance often diminishes when detecting small-sized objects due to the loss or corruption of critical information during feature extraction. To address this challenge, DPAKS is introduced, a reliable DETR- like detector for small objects enhanced with directional prior auxiliary knowledge to guide the model's focus on small objects. In the decoder of DPAKS, a small denoising training strategy is employed that reduces the interference of noisy queries generated from real small objects. This approach effectively learns the features of small objects during the denoising process, sharpening the model's attention to small-sized objects. Additionally, to enhance the reliability of DPAKS's backbone, an auxiliary branch is introduced that provides supervision via shorter paths, improving the optimization of low-level feature parameters. This branch facilitates the transmission of gradient information suited for small objects without interfering with the detection of other sized objects. Furthermore, a new supervision head is proposed and added to the detection head of DPAKS, which categorizes object sizes based on artificial prior knowledge. This guides the model to effectively learn size categories and become more sensitive to small objects. Remarkably, DPAKS achieves competitive performance in small object detection without imposing additional computational burdens at the inference stage. The code is available athttps://github.com/XUhaozhi88/DPAKS.

Despite the crucial role of driving behaviour research in shaping autonomous vehicle interaction design, the current state of their deep integration remains unexplored, constraining the design innovative of autonomous vehicle. This study conducted a systematic review by analysing 320 publications from 2003 to 2023 following PRISMA guidelines. Initially, the research evolution trajectory was depicted through performance analysis, followed by exploring dynamic research themes using scientific mapping. The results reveal the pivotal role of driving behaviour research in fostering innovative practices within autonomous vehicle interaction design and the evolution of thematic content. Three future directions are identified: behaviour insights of diverse interactive entities, all-in-one design solutions, and mixed-reality design evaluation tools. These findings provide practical guidance for utilizing driving behaviour research to foster innovation in AV interaction design, thereby accelerating the socialization of AVs and the transformation towards intelligent mobility.

The vehicle trajectory prediction is crucial for autonomous driving. The vast majority of existing trajectory prediction schemes depend on high definition (HD) maps. However, the HD knowledge is not invariably valid under many actual traffic scenarios. When map information is unreliable, vehicle trajectory prediction is a fundamental challenge that must be overcome in autonomous driving areas. Over the vehicle–road cooperation, this work has developed a spatiotemporal-attentional-mechanism-based prediction model (STAM-P) for vehicle trajectories under map-free scenarios to precisely forecast future trajectories in the case of unreliable map information. First, a temporal transformer encoder was used to capture and encode the state information of the vehicle at different time steps for extracting the vehicle temporal features of the trajectories. Second, a spatial encoder layer consisting of the static map convolutional layer and the dynamic spatial transformer in the spatial feature extraction layer was designed to capture and encode the interactions between vehicles to obtain the vehicle spatial features of the trajectories. Finally, the obtained temporal–spatial features were inputted into a multimodal decoding layer to decode and complete the trajectory prediction. Experimental results of the Argoverse dataset revealed that the proposed model outperformed other existing map-free prediction schemes and reached the level of other map-based trajectory prediction models in certain performance metrics.

In mixed traffic of human-driven vehicles (HDVs) and connected and automated vehicles (CAVs), it is essential to predict the driving intention of HDVs to avoid potential risks. Data quality is crucial to intention prediction under a cooperative vehicle-infrastructure system, whereas the data collection of HDVs relies on the vehicle-infrastructure cooperative perception, which is inevitably exposed to perception errors. In this paper, a robust driving intention prediction framework based on multi-stage learning is proposed in mixed traffic under the vehicle-infrastructure cooperative perception situation. To address this issue, different information sources from vehicles and traffic are considered to derive the implied vehicle dynamic interaction relation and traffic flow context. A feature extraction module is developed to respectively capture the local and global features based on convolutional neural network (CNN) for reducing the impact of noise, which ensures the prominent detailed and overall descriptions of driving intention can be comprehensively acquired. Then, the deep multi-scale technique and multi-layer perceptron network are introduced to further extract deep features, and improve the model adaptability by complementary feature learning mechanism and nonlinear mapping ability. Experiment results on a real-world dataset confirm the effectiveness of our proposal in reducing the impact of poor data quality and accurately predicting driving intention.

Highway on-ramps are typical bottlenecks for the deployment of connected and automated vehicles (CAVs). However, few studies have considered time-varying traffic volume and dynamic uncertainties in real-world scenarios. This paper proposes an adaptive robust formation control strategy (ARFC) for CAVs to address these challenges. The ARFC consists of two stages: 1) In the tactical stage, the constraint-oriented platoon formation algorithm classifies approaching CAVs into multiple local virtual platoons (LVP), assigns the collision-free merging sequences and driving modes, thereby enabling the strategy to adapt to time-varying traffic volume. Unified spatial-dependent constraints are formulated to construct this geometry topology, where the spatial dependence ensures collision avoidance in the merging conflict zone. 2) In the operational stage, an adaptive robust control scheme is designed based on the Lyapunov min-max approach, rendering uniform boundedness, uniform ultimate boundedness performance of tracking errors, and string stability of LVP, regardless of time-varying uncertainties. Comprehensive validations demonstrate that the proposed strategy performs effectively under different traffic demands, and improves ride comfort and fuel economy compared to baseline methods.

This study investigates the effects of information presentation on operator performance in digital control systems at different levels of task difficulty in order to resolve the conflict between ‘large amounts of information’ and ‘limited display’. By using software to present figures of varying difficulty as target information, the operator’s behaviour such as page switching and target clicking is simulated to obtain data. Simultaneously, eye-tracking technique was used to analyse how the way information was presented at different levels of difficulty influenced the subjects’ search performance. The results show that subjects’ performance gradually decreases as the difficulty of the numbers grows for both presentations, and it is found that the complexity of the content of the navigation bar may have influenced the subjects to some extent. In addition, the different position of the navigation bar where the target is located will result in a change in the search pattern. It is noticeable that dividing the single page into double pages can effectively alleviate the contradiction of ‘large amount of information’ and ‘limited display’ in designing the system interface. Therefore, this study provides certain guideline value for the interface design of digital control systems.

Estimating the 6-D pose of an object is a vital and challenging task for robot vision systems in industrial robotic grasping. With the wide use of 3-D cameras, the additional acquired depth image provides geometric information of the scene to increase the pose estimation performance but leads to a challenge, fully leveraging the two-modal data, the color image and the depth image. Previous works usually adopt two individual strategies to handle the data, which suffer from limited accuracy and efficiency since the two complementary data are not fully explored. Thus, we propose a depth adaptive feature extraction and dense prediction network that decouples the scale-dependent and the scale-invariant information from the depth image. The former guides the network to perceive the 3-D structure of the scene, and the latter, together with color image, provides the scene textures for feature extraction. The proposed network not only fuses multimodal textures but also retains their 3-D structure. In addition, a dense prediction strategy is adopted to regress the object pose; this approach can mitigate the instability caused by outliers. We conduct various evaluations on a real-world industrial dataset to illustrate the advantages of the proposed approach; and a practical robotic grasping platform is presented to demonstrate its application performance.

The tremendous revolutionary progress of cellular vehicle-to-everything (C-V2X) and vehicular edge computing (VEC) technologies provide new opportunities to overcome the autonomous transportation issue of the mining electric locomotives (MELs), in which the accurate and fast detection of obstacles is crucial for the safe operation. With the VEC and C-V2X, we proposed a new high-precision obstacle detection strategy for MELs (MEL-YOLO). Firstly, we investigated the convolutional attention mechanism integrated into the path aggregation network of the Neck layer to strengthen the feature extraction capabilities. Secondly, we added a small-object oriented prediction layer in the Head to form the multi-scale feature prediction. Thirdly, we introduced a more efficient loss function to alleviate the gradient explosion problem in the feature transfer. Finally, we utilized the K-means++ optimization to derive the anchor boxes matchable with the dataset, which was collected and created by featuring different scenes to train validate the model. The MEL-YOLO was compressed by BN layer pruning and implemented on the edge device in a 6G/B5G based-V2X environment. Experimental results verify that the MEL-YOLO can effectively detect obstacles and significantly improve detection accuracy for small obstacles, computationally increasing mAP by 3.3% to original model, while maintaining detection speed and model size nearly unchanged.

The rapid development of intelligent connected technologies and cellular vehicle-to-everything communication (C-V2X) provide new opportunities to solve the connected automated vehicle (CAV) traffic problem for eco-driving at continuous signalized intersections. With C-V2X, a hierarchical velocity optimization design based on hybrid model predictive control technique (HVO-HMPC) is presented to reduce the fuel consumption and pollution emission. First, a distance–domain velocity optimization problem, with distance as the independent variable, was constructed. Second, a hybrid MPC scheme was developed by combining the multiple shooting method and MPC technique to calculate the optimal velocity profile of a high-level controller, which acts as the reference velocity in a low-level controller. Then, a car-following model was built, the low-level controller tracked the reference velocity with the predictive control as the backbone, and the optimal velocity was calculated while ensuring that the safety velocity constraint is satisfied. Next, the proposed HVO-HMPC was tested in Prescan, and the effect comparisons with different control methods in terms of fuel consumption, pollution emission, braking time, and number of braking applications were studied under different driving scenarios. Results show that once the maximal speed is limited to 40 km/h under short-period signals and 20 km/h under long-period signals, the HVO-HMPC effectively reduces fuel consumption by 27.21%, 25.89%, and pollution emissions by 25.3%, 25.97%, respectively, while achieving best performance. Finally, an experimental prototype is built to confirm the validity of the HVO-HMPC.

Path planning is a crucial technology for autonomous vehicle (AV). However, it is difficult to adapt to dynamic driving environment, and AV may lose lateral dynamic stability due to high speed and various friction. This paper presents an adaptive dynamic path planning method (ADPPM) for AV to address the challenges. The ADPPM is comprised of three components: 1) A dynamic state-fused steering decision method based on a hierarchical fuzzy inference system is designed to calculate the steering position of AV in each iteration step, and the method fuses the multi-state of the dynamic environment; 2) dynamic path optimization method is designed to reduce the mean curvature of the path based on the particle swarm optimization method, which improves the lateral dynamics stability of AV; 3) adaptive speed inference method is proposed to provide desired steering speed for AV according to various road friction and reduce AV’s steering burden. The ADPPM provides path planning in the dynamic environment, and it also improves the stability of AV under various road friction and speeds. Finally, the proposed method is verified by CarSim.

Removed.

The poor cruising range of electric vehicle (EV) is a problem preventing its popularity. To tackle this problem, methods such as battery technology, energy-based motion control technology are developed. This paper proposes a new solution from the perspective of path planning. Such a solution is called 3-D multi-object path planning method (3D-M method), in which both the energy consumption and distance are considered. The 3D-M method mainly realizes multi-object path planning by an energy consumption estimation model (ECEM) and a distance-integrated estimation model (DIEM). The ECEM can estimate the energy consumption between the neighbour position and the destination on the 3-D map, using a novel slope energy model considering energy consumption characteristic of the EV. The DIEM can estimate the integrated distance which includes the corresponding 2-D distance and 3-D distance, respectively. In the planning process, the outputs of ECEM and DIEM are combined to determine the cost of a path. In addition, a chaos-based multi-object optimizer (CBMOO) is used to search the optimal weights for the 3D-M method. The simulation experiments prove that the proposed method can generate an optimal path which saves much energy in comparison with the path provided by the distance-based method.

Path planning has received more and more attention due to its indispensability in autonomous vehicle (AV). Generally speaking, the stability of AV is not fully considered in path planning, therefore, the planned path may be detrimental for maintaining the stability. And this problem is even more acute for roll stability in complex 3D environment, such as off-road terrain environment. To enhance the roll stability on off-road terrain, a 3D gradient reconstruction-based path planning method (3DGRB-PPM) is presented in this work. The 3DGRB-PPM can keep the roll angle at a low level even in complex 3D environment, thus greatly enhancing the roll stability. The 3DGRB-PPM includes two parts, a gradient reconstruction unit and an adaptive fusion unit. In order to ensure the roll stability of AV in path planning, the gradient reconstruction unit is designed by constructing two potential fields, a joint potential field of gradient and roll angle for enhancing the roll stability and a 3D artificial potential field for reaching the destination. In order to coordinate these two potential fields, an adaptive fusion unit is designed by fuzzy inference rule. The simulation is implemented on the Matlab-Carsim co-simulation platform, and the simulation results show that the path planned by 3DGRB-PPM has good performance with enhanced roll stability.

Path following is the basic technology of the autonomous vehicle (AV), many preview control methods have been widely applied to path following tasks. However, less of them take the variable vehicle velocities into account. In fact, the velocity is an important factor affecting the tracking accuracy. Especially, when an AV is in high velocity, it is not easy to achieve path following with high accuracy. To improve the adaptivity of path following in different velocities, an improved adaptive path following control system (PFCS) constructed by a course angle optimal referential model (CAORM) and a model predictive controller (MPC) is developed in this paper. The CAORM can provide the referential course angle, according to the vehicle longitudinal and lateral velocities, which significantly improves the adaptivity of the proposed PFCS in different velocities. And the CAORM is mainly implemented by a fuzzy inference system and a novel preview model, using human driving experience. The MPC is applied to realize the course control with high accuracy via manipulating the steering angle. Finally, the tracking performance of the PFCS is verified via simulation experiments on the Simulink-CarSim platform.

As demonstrated earlier, the learning accuracy of the single-layer-feedforward-network (SLFN) is generally far lower than expected, which has been a major bottleneck for many applications. In fact, for some large real problems, it is accepted that after tremendous learning time (within finite epochs), the network output error of SLFN will stop or reduce increasingly slowly. This report offers an extreme learning machine (ELM)-based learning method, referred to as the parent-offspring progressive learning method. The proposed method works by separating the data points into various parts, and then multiple ELMs learn and identify the clustered parts separately. The key advantages of the proposed algorithms as compared to the traditional supervised methods are twofold. First, it extends the ELM learning method from a single neural network to a multinetwork learning system, as the proposed multiELM method can approximate any target continuous function and classify disjointed regions. Second, the proposed method tends to deliver a similar or much better generalization performance than other learning methods. All the methods proposed in this paper are tested on both artificial and real datasets.

It is clear that the learning effectiveness and learning speed of neural networks are in general far slower than required, which has been a major bottleneck for many applications. Recently, a simple and efficient learning method, referred to as extreme learning machine (ELM), was proposed by Huang , which has shown that, compared to some conventional methods, the training time of neural networks can be reduced by a thousand times. However, one of the open problems in ELM research is whether the number of hidden nodes can be further reduced without affecting learning effectiveness. This brief proposes a new learning algorithm, called bidirectional extreme learning machine (B-ELM), in which some hidden nodes are not randomly selected. In theory, this algorithm tends to reduce network output error to 0 at an extremely early learning stage. Furthermore, we find a relationship between the network output error and the network output weights in the proposed B-ELM. Simulation results demonstrate that the proposed method can be tens to hundreds of times faster than other incremental ELM algorithms.

The appearance model is very effective in tracking multiple persons. The main difficulty in tracking persons is to represent appearance reliably and effectively, especially in the presence of occlusions. In this paper, an effective Attributed Relational Graph (ARG) based tracking algorithm is presented to track multiple persons even under occlusions. The appearance of each person is expressed by an ARG model which not only combines color feature with spatial information but also illustrates the relations among body parts. The similarity of ARG models is computed to build a matching matrix in consecutive frames. Four tracking situations are determined according to the matching matrix. In addition, to track persons under occlusions, probabilistic relaxation labeling in the ARG models of body parts is deduced to label occluded persons optimally. Experimental validation of the proposed tracking method is verified and presented on indoor and outdoor sequences.