Search Results (220)

In modern vehicles, Autonomous Driving Systems (ADSs) are designed to operate partially or fully without human intervention. The ADS pipeline comprises multiple layers, including sensors, perception, localization, mapping, path planning, and control. The Robot Operating System (ROS) is a widely adopted framework that supports the modular development and integration of these layers. Among them, the path-planning and control layers remain particularly challenging due to several limitations. Classical path planners often struggle with non-smooth trajectories and high computational demands. Meta-heuristic optimization algorithms have demonstrated strong theoretical potential in path planning; however, they are rarely implemented in real-time ROS-based systems due to integration challenges. Similarly, traditional PID controllers require manual tuning and are unable to adapt to system disturbances. This paper proposes a ROS-based ADS architecture composed of eight integrated nodes, designed to address these limitations. The path-planning node leverages a meta-heuristic optimization framework with a cost function that evaluates path feasibility using occupancy grids from the Hector SLAM and obstacle clusters detected through the DBSCAN algorithm. A dynamic goal-allocation strategy is introduced based on the LiDAR range and spatial boundaries to enhance planning flexibility. In the control layer, a modified Pure Pursuit algorithm is employed to translate target positions into velocity commands based on the drift angle. Additionally, an adaptive PID controller is tuned in real time using the Differential Evolution (DE) algorithm, ensuring robust speed regulation in the presence of external disturbances. The proposed system is practically validated on a four-wheel differential drive robot across six scenarios. Experimental results demonstrate that the proposed planner significantly outperforms state-of-the-art methods, ranking first in the Friedman test with a significance level less than 0.05, confirming the effectiveness of the proposed architecture. Full article

3D object detection is a fundamental task in autonomous driving. In recent years, voxel-based methods have demonstrated significant advantages in reducing computational complexity and memory consumption when processing large-scale point cloud data. A representative method, Voxel-RCNN, introduces Region of Interest (RoI) pooling on voxel features, successfully bridging the gap between voxel and point cloud representations for enhanced 3D object detection. However, its robustness deteriorates when detecting distant objects or in the presence of noisy points (e.g., traffic signs and trees). To address this limitation, we propose an enhanced approach named Self-Attention Voxel-RCNN (SA-VoxelRCNN). Our method integrates two complementary attention mechanisms into the feature extraction phase. First, a full self-attention (FSA) module improves global context modeling across all voxel features. Second, a deformable self-attention (DSA) module enables adaptive sampling of representative feature subsets at strategically selected positions. After extracting contextual features through attention mechanisms, these features are fused with spatial features from the base algorithm to form enhanced feature representations, which are subsequently input into the region proposal network (RPN) to generate high-quality 3D bounding boxes. Experimental results on the KITTI test set demonstrate that SA-VoxelRCNN achieves consistent improvements in challenging scenarios, with gains of 2.49 and 1.87 percentage points at Moderate and Hard difficulty levels, respectively, while maintaining real-time performance at 22.3 FPS. This approach effectively balances local geometric details with global contextual information, providing a robust detection solution for autonomous driving applications. Full article

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

With the advantages of industrial integration, China’s recreational fishery sector represents a new trajectory in the transformation of the fishery industry. Coastal regions possess abundant fishery resources and have favorable geographical conditions, offering natural advantages for developing recreational fishing. However, substantial variations can be observed among regions regarding their resource endowments and economic conditions, leading to diversity in the driving forces and paths of recreational fishery development. This study employs panel data for 11 coastal provinces, municipalities, and autonomous regions in the Chinese mainland from 2005 to 2023 to explore the driving forces and regional heterogeneity of recreational fishery development. This paper employs fixed-effects estimation and further incorporates a mediating-effect model to explore the role of market demand in shaping the development path of recreational fisheries. The results are as follows: (1) Natural resource endowments and market demand are key driving forces that promote growth in the output value of recreational fisheries. (2) There is heterogeneity in the driving forces across regions. In areas with richer resource endowments or lower economic development levels, recreational fishery growth relies more on natural resource-driven mechanisms, whereas in regions with weaker resource endowments or higher economic development levels, market demand plays a more dominant role. (3) Market demand drives recreational fishery growth through the expansion of the tertiary sector. This paper offers a valuable reference for policymakers seeking to allocate resources more efficiently, support balanced regional development, and formulate tailored development strategies in accordance with local conditions, thereby facilitating the sustainable and high-quality development of the recreational fishery industry in the Chinese mainland. Full article

Path planning and collision avoidance are essential components of an autonomous driving system (ADS), ensuring safe navigation in complex environments shared with other road users. High-quality planning and reliable obstacle avoidance strategies are essential for advancing the SAE autonomy level of autonomous vehicles, which can largely reduce the risk of traffic accidents. In daily driving scenarios, lane changing is a common maneuver used to avoid unexpected obstacles such as parked vehicles or suddenly appearing pedestrians. Notably, lane-changing behavior is also widely regarded as a key evaluation criterion in driver license examinations, highlighting its practical importance in real-world driving. Motivated by this observation, this paper aims to develop an autonomous lane-changing system capable of dynamically avoiding obstacles in multi-lane traffic environments. To achieve this objective, we propose a hierarchical decision-making and control framework in which a Double Deep Q-Network (DDQN) agent operates as the high-level planner to select lane-level maneuvers, while a High-Order Control Lyapunov Function–High-Order Control Barrier Function–based Quadratic Program (HOCLF-HOCBF-QP) serves as the low-level controller to ensure safe and stable trajectory tracking under dynamic constraints. Simulation studies are used to evaluate the planning efficiency and overall collision avoidance performance of the proposed hierarchical control framework. The results demonstrate that the system is capable of autonomously executing appropriate lane-changing maneuvers to avoid multiple obstacles in complex multi-lane traffic environments. In computational cost tests, the low-level controller operates at 100 Hz with an average solve time of 0.66 ms per step, and the high-level policy operates at 5 Hz with an average solve time of 0.60 ms per step. The results demonstrate real-time capability in autonomous driving systems. Full article

The Segment Anything Model 2 (SAM2) has achieved state-of-the-art performance in pixel-level object segmentation for both static and dynamic visual content. Its streaming memory architecture maintains spatial context across video sequences, yet struggles with long-term tracking due to its static inference framework. SAM 2’s fixed temporal window approach indiscriminately retains historical frames, failing to account for frame quality or dynamic motion patterns. This leads to error propagation and tracking instability in challenging scenarios involving fast-moving objects, partial occlusions, or crowded environments. To overcome these limitations, this paper proposes SAM2Plus, a zero-shot enhancement framework that integrates Kalman filter prediction, dynamic quality thresholds, and adaptive memory management. The Kalman filter models object motion using physical constraints to predict trajectories and dynamically refine segmentation states, mitigating positional drift during occlusions or velocity changes. Dynamic thresholds, combined with multi-criteria evaluation metrics (e.g., motion coherence, appearance consistency), prioritize high-quality frames while adaptively balancing confidence scores and temporal smoothness. This reduces ambiguities among similar objects in complex scenes. SAM2Plus further employs an optimized memory system that prunes outdated or low-confidence entries and retains temporally coherent context, ensuring constant computational resources even for infinitely long videos. Extensive experiments on two video object segmentation (VOS) benchmarks demonstrate SAM2Plus’s superiority over SAM 2. It achieves an average improvement of 1.0 in J&F metrics across all 24 direct comparisons, with gains exceeding 2.3 points on SA-V and LVOS datasets for long-term tracking. The method delivers real-time performance and strong generalization without fine-tuning or additional parameters, effectively addressing occlusion recovery and viewpoint changes. By unifying motion-aware physics-based prediction with spatial segmentation, SAM2Plus bridges the gap between static and dynamic reasoning, offering a scalable solution for real-world applications such as autonomous driving and surveillance systems. Full article

Autonomous vehicles are increasingly being adopted, with manufacturers competing to enhance automation capabilities. While full automation eliminates human input, lower levels still require driver intervention under specific conditions. This study presents the design and development of a prototype vehicle featuring both low- and high-level control systems, integrated with a 5G-based teleoperation interface that enables seamless switching between autonomous and remote-control modes. The system includes a malfunction surveillance unit that monitors communication latency and obstacle conditions, triggering a hardware-based emergency braking mechanism when safety thresholds are exceeded. Field experiments conducted over four test phases around Chulalongkorn University demonstrated stable performance under both driving modes. Mean lateral deviations ranged from 0.19 m to 0.33 m, with maximum deviations up to 0.88 m. Average end-to-end latency was 109.7 ms, with worst-case spikes of 316.6 ms. The emergency fallback system successfully identified all predefined fault conditions and responded with timely braking. Latency-aware stopping analysis showed an increase in braking distance from 1.42 m to 2.37 m at 3 m/s. In scenarios with extreme latency (>500 ms), the system required operator steering input or fallback to autonomous mode to avoid obstacles. These results confirm the platform’s effectiveness in real-world teleoperation over public 5G networks and its potential scalability for broader deployment. Full article

In the field of autonomous driving, cooperative perception through vehicle-to-vehicle communication significantly enhances environmental understanding by leveraging multi-sensor data, including LiDAR, cameras, and radar. However, traditional early or late fusion methods face challenges such as high bandwidth and computational resources, which make it difficult to balance data transmission efficiency with the accuracy of perception of the surrounding environment, especially for the detection of smaller objects such as pedestrians. To address these challenges, this paper proposes a novel cooperative perception framework based on two-stage intermediate-level sensor feature fusion specifically designed for complex traffic scenarios where pedestrians and vehicles coexist. In such scenarios, the model demonstrates superior performance in detecting small objects like pedestrians compared to mainstream perception methods while also improving the cooperative perception accuracy for medium and large objects such as vehicles. Furthermore, to thoroughly validate the reliability of the proposed model, we conducted both qualitative and quantitative experiments on mainstream simulated and real-world datasets. The experimental results demonstrate that our approach outperforms state-of-the-art perception models in terms of mAP, achieving up to a 4.1% improvement in vehicle detection accuracy and a remarkable 29.2% enhancement in pedestrian detection accuracy. Full article

With the rapid progress of intelligent vehicle technology, the accurate recognition of road surface types and conditions has emerged as a crucial technology for improving the safety and comfort levels in autonomous driving. This paper puts forward a multi-feature fusion approach for road surface identification. Relying on a 24 GHz millimeter-wave radar, statistical features are combined with wavelet transform techniques. This combination enables the efficient classification of diverse road surface types and conditions. Firstly, the discriminability of radar echo signals corresponding to different road surface types is verified via statistical analysis. During this process, six-dimensional statistical features that display remarkable differences are extracted. Subsequently, a novel radar data reconstruction approach is presented. This method involves fitting discrete echo signals into coordinate curves. Then, discrete wavelet transform is utilized to extract both low-frequency and high-frequency features, thereby strengthening the spatio-temporal correlation of the signals. The low-frequency information serves to capture general characteristics, whereas the high-frequency information reflects detailed features. The statistical features and wavelet transform features are fused at the feature level, culminating in the formation of a 56-dimensional feature vector. Four machine learning models, namely the Wide Neural Network (WNN), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Kernel methods, are employed as classifiers for both training and testing purposes. Experiments were executed with 8865 samples obtained from a real-vehicle platform. These samples comprehensively represented 12 typical road surface types and conditions. The experimental outcomes clearly indicate that the proposed method is capable of attaining a road surface type identification accuracy as high as 94.2%. As a result, it furnishes an efficient and cost-efficient road perception solution for intelligent driving systems. This research validates the potential application of millimeter-wave radar in intricate road environments and offers both theoretical underpinning and practical support for the advancement of autonomous driving technology. Full article

High-precision indoor positioning technology is increasingly prominent in its application value in emerging fields such as the Industrial Internet of Things, smart cities, and autonomous driving. 5G networks can transmit large-bandwidth signals and have the capability to transmit and receive signals with multiple antennas, enabling the simultaneous acquisition of angle and distance observation information, providing a solution for high-precision positioning. Differences in the types and quantities of observation information in complex environments lead to positioning scenarios having a multimodal nature; how to propose an effective observation model that covers multimodal scenarios for high-precision robust positioning is an urgent problem to be solved. This paper proposes a three-stage time–frequency synchronization method based on group peak time sequence tracing. Timing coarse synchronization is performed through a group peak accumulation timing coarse synchronization algorithm for multi-window joint estimation, frequency offset estimation is based on cyclic prefixes, and finally, fine timing synchronization based on the primary synchronization signal (PSS) sliding cross-correlation is used to synchronize 5G signals to chip-level accuracy. Then, a tracking loop is used to track the Positioning Reference Signal (PRS) to within-chip accuracy, obtaining accurate distance information. After obtaining distance and angle information, a high-precision positioning method for multimodal scenarios based on 5G heterogeneous measurement combination is proposed. Using high-precision angle observation values as intermediate variables, this algorithm can still solve a closed-form positioning solution under sparse observation conditions, enabling the positioning system to achieve good positioning performance even with limited redundant observation information. Full article

Path tracking is an essential task for autonomous driving (AD), for which controllers are designed to issue commands so that vehicles will follow the path of upper-level decision planning properly to ensure operational safety, comfort, and efficiency. Current path-tracking methods still face challenges in balancing tracking accuracy with computational overhead, and more critically, lack consideration for Motion Sickness (MS) mitigation. However, as AD applications divert occupants’ attention to non-driving activities at varying degrees, MS in self-driving vehicles has been significantly exacerbated. This study presents a novel framework, the Hybrid Supervised–Reinforcement Learning (HSRL), designed to reduce passenger discomfort while achieving high-precision tracking performance with computational efficiency. The proposed HSRL employs expert data-guided supervised learning to rapidly optimize the path-tracking model, effectively mitigating the sample efficiency bottleneck inherent in pure Reinforcement Learning (RL). Simultaneously, the RL architecture integrates a passenger MS mechanism into a multi-objective reward function. This design enhances model robustness and control performance, achieving both high-precision tracking and passenger comfort optimization. Simulation experiments demonstrate that the HSRL significantly outperforms Proportional–Integral–Derivative (PID) and Model Predictive Control (MPC), achieving improved tracking accuracy and significantly reducing passengers’ cumulative Motion Sickness Dose Value (MSDV) across several test scenarios. Full article

Localization is the foundation and core of autonomous driving. Current visual localization methods rely heavily on high-definition maps. However, high-definition maps are not only costly but also have poor real-time performance. In autonomous driving, place recognition is equally crucial and of great significance. Existing place recognition methods are deficient in local feature extraction and position and orientation errors can occur during the matching process. To address these limitations, this paper presents a robust multi-dimensional feature fusion framework for place recognition. Unlike existing methods such as OrienterNet, which homogenously process images and maps at the underlying feature level while neglecting modal disparities, our framework—applied to existing 2D maps—introduces a heterogeneous structural-semantic approach inspired by OrienterNet. It employs structured Stixel features (containing positional information) to capture image geometry, while representing the OSM environment through polar coordinate-based building distributions. Dedicated encoders are designed to adapt to each modality. Additionally, global relational features are generated by computing distances and angles between the current position and building pixels in the map, providing the system with detailed spatial relationship information. Subsequently, individual Stixel features are rotationally matched with global relations to achieve feature matching at diverse angles. During the BEV map matching process in OrienterNet, visual localization relies primarily on horizontal image information. In contrast, the novel method proposed herein performs matching based on vertical image information while fusing horizontal cues to complete place recognition. Extensive experimental results demonstrate that the proposed method significantly outperforms the mentioned state-of-the-art approaches in localization accuracy, effectively resolving the existing limitations. Full article

Accurate traffic light status detection and the appropriate response to changes in that status are crucial for autonomous driving systems (ADSs) starting from SAE Level 3 automation. The dilemma zone problem occurs during the amber phase of traffic lights, when the ADS must decide whether to stop or proceed through the intersection. This paper proposes a methodology for developing a runtime monitor that addresses the dilemma zone problem and monitors the autonomous vehicle’s behavior at traffic lights, ensuring that the ADS’s decisions align with the system’s safety requirements. This methodology yields a set of safety requirements formulated in controlled natural language, their formal specification in linear temporal logic (LTL), and the implementation of a corresponding runtime monitor. The monitor is integrated within a safety-oriented software architecture through a modular autonomous driving system pipeline, enabling real-time supervision of the ADS’s decision-making at intersections. The results show that the monitor maintained stable and fast reaction times between 40 ms and 65 ms across varying speeds (up to 13 m/s), remaining well below the 100 ms threshold required for safe autonomous operation. At speeds of 30, 50, and 70 km/h, the system ensured correct behavior with no violations of traffic light regulations. Furthermore, the monitor achieved 100% detection accuracy of the relevant traffic lights within 76 m, with high spatial precision (±0.4 m deviation). While the system performed reliably under typical conditions, it showed limitations in disambiguating adjacent, irrelevant signals at distances below 25 m, indicating opportunities for improvement in dense urban environments. Full article

Autonomous vehicles are one of the key components of smart mobility that leverage innovative technology to navigate and operate safely in urban environments. Traffic light detection systems, as a key part of autonomous vehicles, play a key role in navigation during challenging traffic scenarios. Nighttime driving poses significant challenges for autonomous vehicle navigation, particularly in regard to the accuracy of traffic lights detection (TLD) systems. Existing TLD methodologies frequently encounter difficulties under low-light conditions due to factors such as variable illumination, occlusion, and the presence of distracting light sources. Moreover, most of the recent works only focused on daytime scenarios, often overlooking the significantly increased risk and complexity associated with nighttime driving. To address these critical issues, this paper introduces a novel approach for nighttime traffic light detection using the LNT-YOLO model, which is based on the YOLOv7-tiny framework. LNT-YOLO incorporates enhancements specifically designed to improve the detection of small and poorly illuminated traffic signals. Low-level feature information is utilized to extract the small-object features that have been missing because of the structure of the pyramid structure in the YOLOv7-tiny neck component. A novel SEAM attention module is proposed to refine the features that represent both the spatial and channel information by leveraging the features from the Simple Attention Module (SimAM) and Efficient Channel Attention (ECA) mechanism. The HSM-EIoU loss function is also proposed to accurately detect a small traffic light by amplifying the loss for hard-sample objects. In response to the limited availability of datasets for nighttime traffic light detection, this paper also presents the TN-TLD dataset. This newly curated dataset comprises carefully annotated images from real-world nighttime driving scenarios, featuring both circular and arrow traffic signals. Experimental results demonstrate that the proposed model achieves high accuracy in recognizing traffic lights in the TN-TLD dataset and in the publicly available LISA dataset. The LNT-YOLO model outperforms the original YOLOv7-tiny model and other state-of-the-art object detection models in mAP performance by 13.7% to 26.2% on the TN-TLD dataset and by 9.5% to 24.5% on the LISA dataset. These results underscore the model’s feasibility and robustness compared to other state-of-the-art object detection models. The source code and dataset will be available through the GitHub repository. Full article

As human-driven vehicles (HDVs) and autonomous vehicles (AVs) coexist on the road, the asymmetry between their driving behaviors, decision-making processes, and responses to traffic scenarios introduces new safety challenges, especially in complex merging areas where frequent interactions occur. The existing traffic safety analysis of mixed traffic is mainly to analyze each safety index separately, lacking comprehensive evaluation. To investigate the safety risk more broadly, this study proposes a comprehensive safety evaluation framework for mixed traffic flows in merging areas from the perspective of traffic conflicts, emphasizing the asymmetry between HDVs and AVs. Firstly, an indicator of Emergency Lane Change Risk Frequency is introduced, considering the interaction characteristics of the merging area. A safety evaluation index system is established from lateral, longitudinal, temporal, and spatial dimensions. Then, indicator weights are determined using a modified game theory approach that combines the entropy weight method with the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method, ensuring a balanced integration of objective data and expert judgment. Subsequently, a cloud model enhanced with the fuzzy mean value method is then developed to evaluate comprehensive safety. Finally, a simulation experiment is designed to simulate traffic operation of different traffic scenarios under various traffic flow rates, AV penetration rates, and ramp flow ratios, and the traffic safety of each scenario is estimated. Moreover, the evaluation results are compared against those derived from the fuzzy comprehensive evaluation (FCE) method to verify the reliability of the comprehensive evaluation model. The findings indicate that safety levels deteriorate with increasing total flow rates and ramp flow ratios. Notably, as AV penetration rises from 20% to 100%, safety conditions improve significantly, especially under high-flow scenarios. However, at AV penetration rates below 20%, an increase of the AV penetration rate may worsen safety. Overall, the proposed integrated approach provides a more robust and accurate assessment of safety risks than single-factor evaluations, providing deeper insights into the asymmetries in traffic interactions and offering valuable insights for traffic management and AV deployment strategies. Full article