Search Results (240)

To mitigate driving risks from brake failure on long and steep downhill sections, this study designs three deployment schemes for radar–video fusion devices: a baseline scenario with no coverage, a scenario with partial coverage in high-risk areas, and a scenario with full coverage. Corresponding information service strategies are delivered via Human–Machine Interfaces (HMIs), forming an integrated active prevention and control framework from risk perception to preventive action. Driving simulation experiments focusing on the car-following process were conducted to collect vehicle operational data and extract characteristic indicators based on the Wiedemann model. A Generalized Linear Mixed Model was employed to comprehensively examine the effects of HMIs on car-following behavior to identify the optimal active prevention strategy. Results show that drivers exhibit greater caution under the partial coverage scheme, with time headway increasing by 47.63% compared to the scheme with no radar–video fusion devices to ensure safety. Under full coverage conditions, drivers can obtain real-time information about the leading vehicle’s status and the distance between the two vehicles in key risk sections. Drivers choose to follow the leading vehicle, balancing both safety in car-following and efficiency on long and steep downhill sections. As the level of accompanying services improves, drivers engage in self-regulation to avoid rear-end collisions. Particularly under the scheme with full coverage of radar–video fusion devices, the standing distance significantly increases by 219.37% compared to the partial coverage condition. Drivers demonstrate optimal vehicle control capabilities. Furthermore, there is an interaction effect between the accompanying service strategy and drivers’ attributes on car-following behaviors. Under different schemes, more experienced drivers exhibit a certain degree of aggressiveness, providing a basis for the targeted design of information services for different types of drivers. The findings support the deployment and application of risk perception and prevention devices on long and steep downhill sections, which can effectively enhance the comprehensive safety of such special roads in the connected vehicle environment. Full article

Accurate object detection remains a major challenge in autonomous systems and surveillance, particularly when objects are partially or fully obscured by occlusions. To address this issue, we revisit FuDensityNet as a multimodal detection framework that jointly leverages 2D RGB images and 3D LiDAR point clouds for robust feature representation. The model integrates spatial and depth cues through low-rank tensor fusion (LRTF) and incorporates an Occlusion Rate (OR) assessment module that estimates the degree of occlusion and dynamically selects the most suitable detection pathway to preserve performance. Experiments on the KITTI and NuScenes datasets indicate that this adaptive strategy improves robustness under high occlusion while maintaining competitive accuracy in less challenging conditions. In particular, FuDensityNet attains 76.6% AP for car detection under “Hard” conditions on KITTI and outperforms several RGB-only and RGB–LiDAR baselines. Owing to its adaptive and modular design, FuDensityNet remains compatible with both 2D and 3D detection pipelines, making it a practical option for real-world environments where visual obstructions are frequent. Full article

Foggy traffic scenes pose significant challenges for object detection because reduced contrast, blurred object boundaries, and the loss of local details weaken discriminative feature representations. These degradations are particularly detrimental to lightweight detectors used in intelligent transportation and vehicle perception systems, where both accuracy and real-time efficiency are required. To address this problem, this paper proposes YOLO-GCM, a lightweight detector-side feature enhancement framework built upon YOLO11n. Instead of relying on an external image dehazing stage, YOLO-GCM improves the internal feature representation of the detector through three complementary modules: a gated additive feature block (GAFB) for adaptive channel-wise feature selection and noise suppression, a context-aware feature enhancement module (CAFEM) for strengthening high-level semantic context, and a multi-scale adaptive fusion (MSAF) module for enhancing cross-scale feature interaction. By integrating these modules into a unified one-stage detector, the proposed method improves detection robustness under low-visibility traffic conditions while maintaining a compact architecture. Experiments on the FoggyCar dataset show that YOLO-GCM achieved 89.81% mAP@0.5 and 67.99% mAP@0.5:0.95, outperforming standard YOLO baselines and dehazing-assisted detection pipelines under a consistent evaluation protocol. Additional evaluation on Foggy Cityscapes further verified the generalization capability of the proposed method under domain shift. The results demonstrate that detector-side feature enhancement provides an effective and efficient alternative to multi-stage dehazing-plus-detection pipelines for foggy traffic object detection. These findings can provide useful guidance for the development of robust and efficient perception modules in roadside monitoring, intelligent transportation systems, and vehicle-assisted driving applications under adverse weather conditions. Full article

Lane-changing and overtaking constitute a typical complex driving manoeuvre for intelligent vehicles operating on structured roads; this task demands that the vehicle not only plan a safe and smooth lane-change trajectory but also requires the control system to maintain high tracking accuracy and lateral stability. Addressing the challenges of real-time path planning and stable tracking control inherent in lane-changing and overtaking scenarios, this paper proposes a trajectory planning and control method that integrates an improved artificial potential field (APF) approach with a lateral–longitudinal cooperative controller. Regarding path planning, the proposed method constructs attractive and repulsive fields based on the APF framework, while introducing virtual target points, elliptical obstacle models, and velocity-dependent repulsive fields to mitigate the risk of local minima and enhance dynamic obstacle avoidance capabilities. To ensure trajectory continuity and trackability, a fifth-order polynomial is employed to smooth the planned path. Regarding control, the method utilises a Linear Quadratic Regulator (LQR)—optimised via a genetic algorithm—for lateral control; this is coupled with a dual-PID longitudinal controller that generates throttle and braking commands based on vehicle speed errors, thereby establishing a cooperative lateral–longitudinal tracking control strategy. The proposed method is validated using a CarSim–MATLAB/Simulink co-simulation platform. Simulation results demonstrate that the proposed method significantly improves trajectory-tracking accuracy and vehicle stability during lane-changing and overtaking manoeuvres. In a single lane-change scenario, the maximum lateral error is reduced from approximately 0.62 m to 0.22 m, and the heading angle error decreases from about 0.058 rad to 0.01 rad; in a continuous lane-changing scenario, the maximum lateral error drops from approximately 0.30 m to 0.04 m, while the heading angle error falls from about 0.016 rad to 0.005 rad. Furthermore, the yaw rate, sideslip angle, and lateral acceleration are reduced by 39.1%, 22.2%, and 28.9%, respectively. These results confirm that, under the specified simulation conditions, the proposed method exhibits superior tracking performance and stability. Future research could further explore more complex driving scenarios, such as curved roads, multi-vehicle interactions, sensor uncertainties, actuator delays, and real-vehicle field experiments. Full article

Background/Objectives: Chimeric antigen receptor T-cell (CAR T) therapy is an effective treatment for relapsed/refractory (r/r) aggressive B-cell lymphomas; however, acute toxicities, such as immune effector cell-associated neurotoxicity syndrome (ICANS), remain common. Interleukin-1 (IL-1) has been implicated in the pathogenesis of ICANS, suggesting that prophylactic anakinra, an IL-1 receptor antagonist, might reduce its incidence or severity. Methods: We retrospectively analyzed 80 patients with B-cell lymphomas who received CD19-directed CAR T-cell therapy (tisagenlecleucel, axicabtagene ciloleucel, or lisocabtagene maraleucel) at the Bern University Hospital between April 2019 and June 2022. One cohort received prophylactic anakinra (100 mg subcutaneously on days 0 to +6 post-infusion), while the comparison cohort did not. Results: The incidence of ICANS was similar between groups (14 patients, 35%) with anakinra vs. 10 (25%) in the standard cohort (p = 0.464). Rates of grade 3 ICANS were also comparable (eight (20%) vs. seven (18%), p > 0.999). Among patients who developed ICANS, median hospitalization was numerically shorter with anakinra (27 vs. 40 days, p = 0.077). Anakinra did not impair CAR T-cell expansion and was well tolerated, with no treatment-related adverse events. Survival outcomes, including overall survival (OS) and progression-free survival (PFS), were similar between cohorts. Conclusions: In summary, prophylactic anakinra did not reduce the incidence or severity of ICANS in our analysis; however, it may be associated with shorter hospitalization in affected patients. Whether this reflects a direct therapeutic effect or improved overall toxicity management remains uncertain. Larger prospective studies are warranted to further clarify the role of anakinra for prophylactic treatment of ICANS following CAR T-cell therapy. Full article

AI and Machine Learning (ML) have advanced rapidly, yet their theoretical underpinnings remain incomplete. We developed an integrated framework combining mathematical theory, uncertainty quantification, and dynamic validation across autonomous platforms such as unmanned aerial vehicles and self-driving cars. We address key challenges in generalization bounds, safety-guaranteed control, and multimodal sensor fusion by exploring the role of Large Language Models (LLMs) in experiment design and teaching material generation. Preliminary simulation and system-level results demonstrate the feasibility of bridging theoretical AI models with real-world engineering systems. The proposed framework aims to provide a reproducible research and teaching platform that fosters interpretable, robust, and certifiable AI applications. Full article

As autonomous driving technology progresses, efficient and accurate object detectors are able to detect pedestrians, vehicles, road signs, and obstacles in real time, thereby enhancing driving safety and serving as a part of autonomous driving. However, the performance of such object detectors is limited and cannot be leveraged to satisfy modern autonomous driving systems. To address this issue, we develop an object detection network for autonomous driving scenarios, SST-YOLO, which is based on YOLOv8. First, we propose a Sobel Convolution & Convolution (SCC) module to enhance the backbone, which incorporates a SobelConv branch to explicitly model gradient-based edge information and improve structural feature representation. In addition, we replace the original path aggregation feature pyramid network (PAFPN) with a Small Object Augmentation Pyramid Network (SOAPN), which integrates SPDConv and CSP-OmniKernel modules to strengthen multi-scale feature fusion and enhance small object representation. Finally, a Task-Adaptive Decomposition & Alignment Head (TADAHead) is designed, which employs task decomposition, dynamic deformable convolution, and classification-aware modulation to decouple tasks and achieve adaptive spatial alignment, thereby improving detection accuracy and robustness in complex scenarios. Experiments on the public autonomous driving dataset KITTI show that our proposed method outperforms the baseline YOLOv8 model. Compared with the baseline results, mAP@0.5:0.95 ranges from 65.1% to 69.2%, which indicates that the proposed SST-YOLO network can achieve object detection for autonomous cars. Full article

Background: Ciltacabtagene autoleucel (cilta-cel) and idecabtagene vicleucel (ide-cel) have transformed the treatment landscape of relapsed/refractory multiple myeloma (RRMM). Given their recent regulatory approval and limited availability, mainly due to logistical issues, real-world data remain scarce. Methods: A retrospective study was conducted using the TriNetX database, identifying adult patients with RRMM treated with either cilta-cel or ide-cel. The clinical outcomes evaluated included overall survival (OS), progression-free survival (PFS), as well as the safety profile. Results: A total of 697 patients treated with cilta-cel and 575 with ide-cel were identified. The median age was 65 and 67 years, with ~16% being Black/African American. The 12-month OS was 89.6% for cilta-cel and 86.0% for ide-cel. In a descriptive subgroup analysis, renal impairment (eGFR < 60 mL/min/1.73 m²) seemed to be associated with significantly inferior OS in both cohorts (HR = 3.66, p < 0.001 for cilta-cel; HR = 1.73, p = 0.003 for ide-cel). Conversely, prior anti-CD38 exposure did not seem to impact survival in any of the two treatment groups. Any-grade CRS occurred in 45.9% (cilta-cel) and 41.8% (ide-cel), while any-grade ICANS was observed in 15.4% and 11.8%, respectively. Severe (grade ≥ 3) ICANS remained rare (<3%) in both cohorts. Hematologic toxicity was prevalent, with grade ≥ 3 neutropenia occurring in 76.0% (cilta-cel) and 68.0% (ide-cel). Notably, any-grade infections (28.5–40.1%) and hypogammaglobulinemia (41.1–43.1%) were frequent, highlighting a significant long-term immunosuppressive burden. Conclusions: In these real-world cohorts, both approved CAR T-cell therapies demonstrated favorable survival outcomes. While the incidence of severe hematologic and immune-related toxicities was high, these findings are compatible with published data from clinical trials and it seems that the clinical utility of these drugs overcomes the adverse safety profile. Full article

Potholes are typical negative road obstacles that can significantly compromise vehicle safety and ride comfort when traversed at inappropriate speeds. To address this issue, this paper proposes a pothole-detection-based, comfort-oriented pothole traversal algorithm that integrates multi-sensor fusion perception, comfort-constrained speed planning, and fuzzy control. A camera and a single-point ranging LiDAR are first fused to extract key geometric features of potholes, including contour, area, and depth. Based on these features, a vehicle–pothole dynamic model is developed in ADAMS to quantify the influence of pothole area and depth on vehicle vertical vibration. The vertical frequency-weighted root-mean-square (RMS) acceleration is adopted as the ride comfort indicator, based on which the maximum allowable traversal speed under different pothole geometries is determined. Furthermore, a longitudinal pothole traversal control strategy based on fuzzy theory is designed to regulate vehicle acceleration, enabling the vehicle to reach the comfort-constrained limiting speed within a finite preview distance while ensuring braking safety. The proposed method is validated through multi-scenario co-simulations using MATLAB/Simulink and CarSim, as well as real-vehicle experiments. Results demonstrate that the proposed strategy can effectively adjust vehicle speed before pothole traversal, satisfying comfort constraints and improving ride comfort without sacrificing driving safety. Full article

Large language models (LLMs) exhibit strong semantic reasoning capabilities for autonomous driving decision-making; however, their substantial inference latency poses a critical challenge for real-time closed-loop vehicle control. This study proposes an engineering-oriented framework to enable latency-constrained LLM-based decision-making by integrating bird’s-eye-view (BEV) structured perception with low-bit quantized inference. The BEV perception module compresses multi-view visual inputs into structured semantic representations, thereby reducing input redundancy and enhancing inference efficiency. In addition, 4-bit post-training quantization (PTQ), combined with an optimized inference engine, is employed to alleviate computational and memory bandwidth constraints during autoregressive decoding. Experiments conducted on the CARLA simulation platform under car-following, overtaking, and mixed driving scenarios—validated through 500 independent trials—demonstrate that the proposed framework substantially reduces end-to-end inference latency while maintaining stable decision-making performance. The results indicate that the system satisfies the 10 Hz real-time control requirement and significantly improves control quality, as evidenced by reduced collision rates and lower Average Jerk compared with both traditional imitation learning (Behavioral Cloning, BC) and the Transformer-based TransFuser baseline. Furthermore, sensitivity analyses confirm the robustness of the framework under environmental degradation and perception noise, underscoring the practical feasibility of deploying LLMs for safe and reliable closed-loop autonomous driving. Full article

Suspension architecture has long been a central topic in vehicle chassis research and development. Passive, active, and semi-active suspensions provide different trade-offs in performance, complexity, and energy use. The pseudo-active actuator (PAA) is a newly emerging concept that delivers near active-level performance with semi-active-level energy input, which opens a new direction for suspension architecture design. In this work, a pseudo-active suspension (PAS) based on a PAA is developed. Along with the structural investigation, the corresponding dynamic model and control system are established and experimentally validated. Taking a suspension of a body-on-frame (BoF) vehicle as the application platform, an engineering-feasible PAS configuration is proposed, and design/optimization principles are presented for key geometric parameters and components. A quarter-car three-mass PAS dynamic model is derived, in which the equivalent coupling introduced by the mechanical compensation mechanism is explicitly characterized, leading to a complete state-space representation. To address the multi-objective performance requirements of the PAS, a conventional H_∞ controller and a finite-frequency H_∞ controller with a specified target band are designed, respectively. A quarter-car PAS experimental rig and a real-time control platform are built, and experiments are conducted under various displacement excitation scenarios. Both simulations and experiments demonstrate that the proposed PAS and controllers meet the multi-objective design objectives and provide robust performance, supporting practical implementation. Full article

Domain-adaptive object detection under set-prediction paradigms remains challenging, as Hungarian matching is sensitive to domain shift and fixed pseudo-label thresholds cannot simultaneously handle class imbalance and scene variability. This paper presents SSRT-DETR, a semi-supervised, domain-adaptive framework built on the real-time detector RT-DETR. We adopt a mean teacher–student architecture with style-transferred images to jointly model source and target domains. To stabilize the assignment process during the early stages of cross-domain training, Domain-Aware Matching (DAM) is formulated to augment the Hungarian matching cost with a teacher-guided decoder-query consistency term. Leveraging the more stable EMA teacher representations, DAM guides early matching toward domain-consistent assignments and is gradually annealed to recover standard matching as training converges. In parallel, we introduce Class-/Scene-Adaptive Pseudo-Labeling (CAP) to address a key limitation of existing DAOD methods that rely on fixed or globally tuned pseudo-label thresholds, which struggle with class imbalance and scene-dependent difficulty under domain shift. CAP leverages per-class confidence statistics and multi-view consistency to adapt classification and IoU thresholds across classes and scenes, while temperature scaling and quality-weighted losses provide soft control over pseudo-label reliability. Experiments on standard benchmarks demonstrate the robustness of SSRT-DETR. On Cityscapes→Foggy Cityscapes, SSRT-DETR improves mAP@0.5 from 51.0 to 54.3. On KITTI→Cityscapes and Sim10K→Cityscapes, it achieves 67.3 AP and 64.9 AP on the car category, respectively, clearly outperforming the RT-DETR baseline while maintaining real-time efficiency. Notably, consistent gains are observed in rare categories and adverse weather scenarios, validating the effectiveness of the proposed DAM and CAP modules. Full article

Accurate and robust visual localization under changing environments remains a fundamental challenge in autonomous driving and mobile robotics. Traditional handcrafted features often degrade under long-term illumination and viewpoint variations, while recent CNN-based methods, although more robust, typically rely on coarse semantic cues and remain vulnerable to dynamic objects. In this paper, we propose a fine-grained semantics-guided feature extraction framework that adaptively selects stable keypoints while suppressing dynamic disturbances. A fine-grained semantic refinement module subdivides coarse semantic categories into stability-homogeneous sub-classes, and a dual-attention mechanism enhances local repeatability and semantic consistency. By integrating physical priors with self-supervised clustering, the proposed framework learns discriminative and reliable feature representations. Extensive experiments on the Aachen and RobotCar-Seasons benchmarks demonstrate that the proposed approach achieves state-of-the-art accuracy and robustness while maintaining real-time efficiency, effectively bridging coarse semantic guidance with fine-grained stability estimation. Quantitatively, our method achieves strong localization performance on Aachen (up to 88.1% at night under the $(0.2^{°},0.25 \mathrm{m})$ threshold) and on RobotCar-Seasons (up to 57.2%/28.4% under the same threshold for day/night), demonstrating improved robustness to seasonal and illumination changes. Full article

The joint optimization of computing resources and network routing constitutes a central challenge in Computing First Networks (CFNs). However, existing research has predominantly focused on computation offloading decisions, whereas the cooperative optimization of computing power and network routing remains underexplored. Therefore, this study investigates the joint routing optimization problem within the CFN framework. We first propose a computing resource scheduling architecture for CFN, termed SICRSA, which integrates Software-Defined Networking (SDN) and Information-Centric Networking (ICN). Building upon this architecture, we further introduce an ICN-based hierarchical naming scheme for computing services, design a computing service request packet format that extends the IP header, and detail the corresponding service request identification process and workflow. Furthermore, we propose Computing-Aware Routing via Graph and Long-term Dependency Learning (CRGLD), a Graph Neural Network (GNN), and Long Short-Term Memory (LSTM)-based routing optimization algorithm, within the SICRSA framework to address the computing-aware routing (CAR) problem. The algorithm incorporates a decision-making framework grounded in spatiotemporal feature learning, thereby enabling the joint and coordinated selection of computing nodes and transmission paths. Simulation experiments conducted on real-world network topologies demonstrate that CRGLD enhances both the quality of service and the intelligence of routing decisions in dynamic network environments. Moreover, CRGLD exhibits strong generalization capability when confronted with unfamiliar topologies and topological changes, effectively mitigating the poor generalization performance typical of traditional Deep Reinforcement Learning (DRL)-based routing models in dynamic settings. Full article

CD19 CAR T-cell therapy has significantly improved the survival of patients with relapsed or refractory large B cell lymphoma (R/R LBCL) and is considered standard of care for eligible patients in Canada. Axicabtagene ciloleucel (axi-cel) is an autologous CAR T-cell therapy, initially approved by Health Canada for adults with R/R LBCL after 2 or more lines of therapy. This multi-centre analysis, with registry data collected from CIBMTR, aims to present a Canadian perspective on the real-world experience of axi-cel in patients with R/R LBCL. With a median follow-up of 12.4 months, the best objective response rate (ORR) and complete response (CR) rate among all patients were 77% and 59%, respectively. At 12 months, estimated progression-free survival (PFS) and overall survival (OS) were 49% and 59%, respectively. Notably, the incidence and severity of adverse events were lower in this cohort compared to ZUMA-1 and other real-world reports, with CRS occurring in 77% (grade ≥ 3, 3%) and ICANS occurring in 38% (grade ≥ 3, 10%) of patients. Outcomes remained largely consistent across patient and disease characteristics. These findings demonstrate effectiveness and safety profiles comparable to international real-world studies and the ZUMA-1 trial, supporting the use of axi-cel as an effective treatment across broad Canadian populations. Full article