Search Results (19)

Rare and safety-critical traffic situations remain challenging for autonomous driving (AD) because they are underrepresented in common training data and may include objects outside standard detector classes. This paper presents a real-time RGB-LiDAR fusion framework for detecting and reacting to rare traffic situations in CARLA (Car Learning to Act), a reproducible simulator for AD research. The approach combines YOLOv8n-based RGB perception, bird’s-eye-view (BEV) LiDAR clustering, decision-level fusion, an interpretable rule-based safety agent with hysteresis, Time-to-Collision (TTC)-aware escalation, and an automatic emergency braking (AEB) override above the CARLA autopilot. Fused observations are classified as semantic–geometric detections, semantic-only detections, or geometric-only obstacle candidates, where unmatched LiDAR clusters are treated conservatively as candidate-level physical evidence rather than confirmed rare objects. The framework was evaluated on three CARLA maps and 3CSim-inspired corner-case scenarios comprising 19,253 frames, with additional weather/lighting stress tests and a public nuScenes mini cross-platform check. On a manually annotated subset of 4800 CARLA frames, corresponding to approximately $24.9\%$ of the recorded CARLA log, the full framework achieved $96.2\%$ precision, $97.3\%$ recall, and a $96.7\%$ F1-score for safety-relevant threat detection. The control experiments show that the fusion-based safety agent reduced unnecessary braking to $1.7\%$ compared with $8.6\%$ for the LiDAR-only baseline and achieved event-level success on the annotated critical intervals. The proposed CPU-only implementation maintained real-time performance, with an average processing time of $34.7\mathrm{ms}$. Full article

Multi-agent trajectory prediction serves as a critical component in autonomous driving systems, bridging environment perception, behavior understanding, and motion planning. Its outputs not only affect candidate trajectory evaluation and interactive decision-making but also directly influence downstream processes such as risk anticipation, braking and yielding, and safety margin allocation. Therefore, obtaining accurate and stable prediction results is of great importance. Although existing methods have achieved remarkable progress in single-timestep prediction accuracy, most of them still adopt an independent decoding paradigm under a sliding-window setting. As a result, during continuous online prediction, these models are prone to frequent mode switching, temporal discontinuities in overlapping segments, and local trajectory jitter, which become particularly pronounced in complex interactive scenarios such as yielding, merging, and unprotected turning. To address these issues, this paper proposes PHR-Net, a two-stage proposal-level historical retrieval framework that introduces cross-timestep historical context to perform consistency-aware refinement of current predictions on top of multimodal coarse proposals. Experiments on the Argoverse 1 benchmark show that PHR-Net achieves competitive performance under both Top-1 and Top-6 settings. PHR-Net obtains a Top-1 minFDE of 1.0834 and MR of 0.1046 and achieves an MR of 0.1027 under the Top-6 setting. In the overlapping-interval consistency evaluation, PHR-Net reduces the summed ADE to 2.08. These results show that proposal-level historical retrieval improves endpoint reliability and cross-timestep temporal consistency. Full article

Reducing traction energy in urban rail systems while preserving safety, punctuality, and passenger comfort remains challenging. Additionally, route-level tram studies that train deep reinforcement learning (DRL) policies using Operational Train Monitoring Recorder (OTMR) logs and benchmark them across multiple objectives remain limited. This study develops and evaluates a Human-Assisted Deep Reinforcement Learning (HADRL) framework for multi-objective tram control in an OTMR-grounded simulation. Two HADRL agents were trained using a human-assistance action mapping: a standard Proximal Policy Optimisation (PPO) baseline and a recurrent, history-augmented PPO. Their performance was compared against that of four human drivers using indices for speed-limit compliance, schedule deviation, traction energy, jerk-based comfort, and stopping accuracy. These performance measures were aggregated using the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) with both equal and entropy-derived weights. Both HADRL agents reproduce the characteristic accelerate–coast–brake driving pattern, reduce traction energy relative to all human baselines, and achieve near-complete speed-limit compliance, all while remaining within the specified schedule-deviation and comfort thresholds. TOPSIS yields identical rankings under both weighting schemes, with Multi-Objective Tram Operation Non-Stationary Proximal Policy Optimisation (MOTO-NSPPO, a recurrent, history-augmented PPO) ranked first and PPO second. Full article

This paper presents the design, development, and evaluation of a Reinforcement Learning (RL)–based torque-split controller for the regenerative braking system (RBS) in battery electric vehicles (BEVs). The controller employs a Deep Deterministic Policy Gradient (DDPG) agent to distribute the braking demand between regenerative and frictional braking systems with the aim of maximizing energy recovery while adhering to the physical and operational constraints. To capture the charging limitation of the battery, a State-of-Power (SoP) calculation mechanism is incorporated, providing a time-varying bound on the regenerative charge power. The agent is trained in a MATLAB/Simulink environment representing the digital twin of a BEV drivetrain, and considers a mix of different braking scenarios, i.e., light braking, medium braking, hard braking, and emergency braking. The RL’s reward shaping promotes efficient utilization of the SoP-limited regenerative capability while discouraging constraint violations and aggressive control behavior. Across a range of State-of-Charge (SoC) conditions and driving cycles, including the Worldwide Harmonized Light–Vehicle Test Procedure (WLTP) and synthetic random-rich driving cycle, the RL controller consistently delivers promising performance, yielding energy recovery of up to ~98% of the total braking energy available on WLTP type 3 driving cycle while being able to operate closely to the battery SoP limit. The results demonstrate the proposed controller’s capability for adaptive, constraint-aware energy management in BEVs and underline its potential for future intelligent braking strategies. Full article

As the maritime industry transitions towards green shipping, operational sustainability and energy efficiency are increasingly crucial for long-endurance Unmanned Surface Vehicle (USV) missions. To this end, proactively adjusting driving strategies based on the prediction of other USVs’ motion is essential. This proactive approach directly minimizes carbon emissions and reduces high-energy driving behaviors resulting from passive sudden braking or sharp turns in unexpected situations. However, existing trajectory prediction methods are trained based on low-frequency automatic identification system data of large merchant vessels, which cannot be directly used on the highly dynamic USV data. To address this limitation, this study constructs a large-scale simulated USV scenario dataset grounded in nonlinear ship hydrodynamics, which contains complicated interactive scenarios with multiple USV agents. To effectively model the interaction among agents for accurate prediction, we further propose USV-Former, a hierarchical encoder-decoder architecture designed for proactive navigation. The framework integrates a symmetric encoding structure with a dual-stage pipeline: a Local Attention Module captures high-frequency dynamics, while a Global Graph Attention Module enforces COLREGs-compliant topological constraints. Experimental results demonstrate that the proposed model outperforms established baselines in prediction accuracy. Qualitative analysis further reveals that by accurately anticipating target intentions, the model minimizes unnecessary avoidance maneuvers, enabling more stable and momentum-conserving velocity profiles. Ultimately, this architecture exhibits high computational efficiency, reduces operational energy waste, and provides a robust, measurable algorithmic foundation for green autonomous shipping and marine environmental protection. Full article

This paper introduces a novel observer-based, fully distributed fault-tolerant consensus control algorithm for model-free adaptive control, specifically designed to tackle the consensus problem in nonlinear multi-agent systems. The method addresses the issue of followers lacking direct access to the leader’s state by employing a distributed observer that estimates the leader’s state using only local information from the agents. This transforms the consensus control challenge into multiple independent tracking tasks, where each agent can independently follow the leader’s trajectory. Additionally, an extended state observer based on a data-driven model is utilized to estimate unknown actuator faults, with a particular focus on brake faults. Integrated into the model-free adaptive control framework, this observer enables real-time fault detection and compensation. The proposed algorithm is supported by rigorous theoretical analysis, which ensures the boundedness of both the observer and tracking errors. Simulation results further validate the algorithm’s effectiveness, demonstrating its robustness and practical viability in real-time fault-tolerant control applications. Full article

This article presents an interaction-aware motion planning framework that integrates a graph neural network (GNN) based multi-modal trajectory predictor with a model predictive control (MPC) based planner. Unlike past studies that predict a single future trajectory per agent, our algorithm outputs three distinct trajectories for each surrounding road user, capturing different interaction scenarios (e.g., yielding, non-yielding, and aggressive driving behaviors). We design a GNN-based predictor with bi-directional gated recurrent unit (Bi-GRU) encoders for agent histories, VectorNet-based lane encoding for map context, an interaction-aware attention mechanism, and multi-head decoders to predict trajectories for each mode. The MPC-based planner employs a bicycle model and solves a constrained optimal control problem using CasADi and IPOPT (Interior Point OPTimizer). All three predicted trajectories per agent are fed to the planner; the primary prediction is thus enforced as a hard safety constraint, while the alternative trajectories are treated as soft constraints via penalty slack variables. The designed motion planning algorithm is examined in real-world intersection scenarios from the INTERACTION dataset. Results show that the multi-modal trajectory predictor covers possible interaction outcomes, and the planner produces smoother and safer trajectories compared to a single-trajectory baseline. In high-conflict situations, the multi-modal trajectory predictor anticipates potential aggressive behaviors of other drivers, reducing harsh braking and maintaining safe distances. The innovative method by integrating the GNN-based multi-modal trajectory predictor with the MPC-based planner is the backbone of the effective motion planning algorithm for robust, safe, and comfortable autonomous driving in complex intersections. Full article

Neuropathic pain is a chronic and debilitating disorder of the somatosensory system that affects a significant proportion of the population and is characterized by abnormal responses such as hyperalgesia and allodynia. Voltage-gated ion channels, including sodium (Na_V), calcium (Ca_V), and potassium (K_V) channels, play a pivotal role in modulating neuronal excitability and pain signal transmission following nerve injury. This review intends to provide a comprehensive analysis of the molecular and cellular mechanisms by which dysregulation in the expression, localization, and function of specific Na_V channel subtypes (mainly Na_V1.7 and Na_V1.8) and their auxiliary subunits contributes to aberrant neuronal activation, the generation of ectopic discharges, and sensitization in neuropathic pain. Likewise, special emphasis is placed on the crucial role of Ca_V channels, particularly Ca_V2.2 and the auxiliary subunit Ca_Vα₂δ, whose overexpression increases calcium influx, neurotransmitter release, and neuronal hyperexcitability, thus maintaining persistent pain states. Furthermore, K_V channels (particularly K_V7 channels) function as brakes on neuronal excitability, and their dysregulation facilitates the development and maintenance of neuropathic pain. Therefore, targeting specific K_V channel subtypes to restore their function is also a promising therapeutic strategy for alleviating neuropathic pain symptoms. On the other hand, recent advances in the development of small molecules as selective modulators or inhibitors targeting voltage-gated ion channels are also discussed. These agents have improved efficacy and safety profiles in preclinical and clinical studies by attenuating pathophysiological channel activity and restoring neuronal function. This review seeks to contribute to guiding future research and drug development toward more effective mechanism-based treatments by discussing the molecular mechanisms underlying neuropathic pain and highlighting translational therapeutic opportunities. Full article

Reinforcement Learning (RL) methods are regarded as effective for designing autonomous driving policies. However, even when RL policies are trained to convergence, ensuring their robust safety remains a challenge, particularly in long-tail data. Therefore, decision-making based on RL must adequately consider potential variations in data distribution. This paper presents a framework for highway autonomous driving decisions that prioritizes both safety and robustness. Utilizing the proposed Replay Buffer Constrained Policy Optimization (RECPO) method, this framework updates RL strategies to maximize rewards while ensuring that the policies always remain within safety constraints. We incorporate importance sampling techniques to collect and store data in a Replay buffer during agent operation, allowing the reutilization of data from old policies for training new policy models, thus mitigating potential catastrophic forgetting. Additionally, we transform the highway autonomous driving decision problem into a Constrained Markov Decision Process (CMDP) and apply our proposed RECPO for training, optimizing highway driving policies. Finally, we deploy our method in the CARLA simulation environment and compare its performance in typical highway scenarios against traditional CPO, current advanced strategies based on Deep Deterministic Policy Gradient (DDPG), and IDM + MOBIL (Intelligent Driver Model and the model for minimizing overall braking induced by lane changes). The results show that our framework significantly enhances model convergence speed, safety, and decision-making stability, achieving a zero-collision rate in highway autonomous driving. Full article

Complications from diabetic retinopathy such as diabetic macular edema (DME) and proliferative diabetic retinopathy (PDR) constitute leading causes of preventable vision loss in working-age patients. Since vascular endothelial growth factor (VEGF) plays a major role in the pathogenesis of these complications, VEGF inhibitors have been the cornerstone of their treatment. Anti-VEGF monotherapy is an effective but burdensome treatment for DME. However, due to the intensive and burdensome treatment, most patients in routine clinical practice are undertreated, and therefore, their outcomes are compromised. Even in adequately treated patients, persistent DME is reported anywhere from 30% to 60% depending on the drug used. PDR is currently treated by anti-VEGF, panretinal photocoagulation (PRP) or a combination of both. Similarly, a number of eyes, despite these treatments, continue to progress to tractional retinal detachment and vitreous hemorrhage. Clearly there are other molecular pathways other than VEGF involved in the pathogenesis of DME and PDR. One of these pathways is the angiopoietin–Tie signaling pathway. Angiopoietin 1 (Ang1) plays a major role in maintaining vascular quiescence and stability. It acts as a molecular brake against vascular destabilization and inflammation that is usually promoted by angiopoietin 2 (Ang2). Several pathological conditions including chronic hyperglycemia lead to Ang2 upregulation. Recent regulatory approval of the bi-specific antibody, faricimab, may improve long term outcomes in DME. It targets both the Ang/Tie and VEGF pathways. The YOSEMITE and RHINE were multicenter, double-masked, randomized non-inferiority phase 3 clinical trials that compared faricimab to aflibercept in eyes with center-involved DME. At 12 months of follow-up, faricimab demonstrated non-inferior vision gains, improved anatomic outcomes and a potential for extended dosing when compared to aflibercept. The 2-year results of the YOSEMITE and RHINE trials demonstrated that the anatomic and functional results obtained at the 1 year follow-up were maintained. Short term outcomes of previously treated and treatment-naive eyes with DME that were treated with faricimab during routine clinical practice suggest a beneficial effect of faricimab over other agents. Targeting of Ang2 has been reported by several other means including VE-PTP inhibitors, integrin binding peptide and surrobodies. Full article

As urban centers evolve into smart cities, sustainable mobility emerges as a cornerstone for ensuring environmental integrity and enhancing quality of life. Autonomous vehicles (AVs) play a pivotal role in this transformation, with the potential to significantly improve efficiency and safety, and reduce environmental impacts. This study introduces a novel Multi-Agent Actor–Critic (MA2C) algorithm tailored for multi-AV lane-changing in mixed-traffic scenarios, a critical component of intelligent transportation systems in smart cities. By incorporating a local reward system that values efficiency, safety, and passenger comfort, and a parameter-sharing scheme that encourages inter-agent collaboration, our MA2C algorithm presents a comprehensive approach to urban traffic management. The MA2C algorithm leverages reinforcement learning to optimize lane-changing decisions, ensuring optimal traffic flow and enhancing both environmental sustainability and urban living standards. The actor–critic architecture is refined to minimize variances in urban traffic conditions, enhancing predictability and safety. The study extends to simulating realistic human-driven vehicle (HDV) behavior using the Intelligent Driver Model (IDM) and the model of Minimizing Overall Braking Induced by Lane changes (MOBIL), contributing to more accurate and effective traffic management strategies. Empirical results indicate that the MA2C algorithm outperforms existing state-of-the-art models in managing lane changes, passenger comfort, and inter-vehicle cooperation, essential for the dynamic environment of smart cities. The success of the MA2C algorithm in facilitating seamless interaction between AVs and HDVs holds promise for more fluid urban traffic conditions, reduced congestion, and lower emissions. This research contributes to the growing body of knowledge on autonomous driving within the framework of sustainable smart cities, focusing on the integration of AVs into the urban fabric. It underscores the potential of machine learning and artificial intelligence in developing transportation systems that are not only efficient and safe but also sustainable, supporting the broader goals of creating resilient, adaptive, and environmentally friendly urban spaces. Full article

Optimizing the chemical composition of phosphorus cast iron for the manufacture of brake shoes, which are used in the rolling stock, is based on specific tests, and the results must be within the specified limits of railway standards. This paper presents the processing of data taken from an economic agent producing brake shoes—with chemical composition and hardness values determined through the Brinell method—as well as optimizing these data by obtaining optimal variation intervals. These technological intervals are useful in the case of foundries in order to obtain superior products from a qualitative point of view. Full article

Temporary plugging diversion fracturing (TPDF) technology has been widely used in various oil fields for repeated reconstruction of high-water-cut old oil wells and horizontal well reservoir reconstruction. Previous studies have carried out in-depth study on the pressure-bearing law and placement morphology of different types of temporary plugging agents (TPAs) in fractures, but there are relatively few studies on TPA accumulation body permeability. To solve this problem, an experimental device for evaluating the TPA performance with adjustable fracture pores is proposed in this paper. Based on the test of fracturing fluid breaking time and residue content, the low damage of fracturing fluid to the reservoir is determined. The TPA degradation performance test determines whether the TPA causes damage to the hydraulic fracture after the temporary plugging fracturing. Finally, by testing the TPA pressure-bearing capacity and the temporary plugging aggregation body permeability, the plugging performance and the aggregation body permeability are determined. The results show the following: (1) Guar gum fracturing fluid shows good gel-breaking performance under the action of breaking agent, and the recommended concentration of breaking agent is 300 ppm. At 90~120 °C, the degradation rate of the three types of TPAs can reach more than 65%, and it can be effectively carried into the wellbore during the fracturing fluid flowback stage to achieve the effect of removing the TPA in the fracture. (2) The results of the pressure-bearing performance of the TPA show that the two kinds of TPAs can quickly achieve the plugging effect after plugging start: the effect of ZD-2 (poly lactic-co-glycolic acid (PLGA)) particle-and-powder combined TPA on forming an effective temporary plugging accumulation body in fractures is better than that of ZD-1 (PLGA) pure powder. There are large pores between the particles, and the fracturing fluid can still flow through the pores, so the ZD-3 (a mixture of lactide and PLGA) granular temporary plugging agent cannot form an effective plugging. (3) The law of length of the temporary plugging accumulation body shows that the ZD-2 combined TPA has stronger plugging ability for medium-aperture simulated fracture pores, while the ZD-1 powder TPA has stronger plugging ability for small aperture simulated fracture pores, and the ZD-3 granular TPA should be avoided alone as far as possible. This study further enriches and improves the understanding of the mechanism of temporary plugging diverting fracturing fluid. Full article

With the aging of the population, malignancies are becoming common complications in patients with rheumatoid arthritis (RA), particularly in elderly patients. Such malignancies often interfere with RA treatment. Among several therapeutic agents, immune checkpoint inhibitors (ICIs) which antagonize immunological brakes on T lymphocytes have emerged as a promising treatment option for a variety of malignancies. In parallel, evidence has accumulated that ICIs are associated with numerous immune-related adverse events (irAEs), such as hypophysitis, myocarditis, pneumonitis, and colitis. Moreover, ICIs not only exacerbate pre-existing autoimmune diseases, but also cause de novo rheumatic disease–like symptoms, such as arthritis, myositis, and vasculitis, which are currently termed rheumatic irAEs. Rheumatic irAEs differ from classical rheumatic diseases in multiple aspects, and treatment should be individualized based on the severity. Close collaboration with oncologists is critical for preventing irreversible organ damage. This review summarizes the current evidence regarding the mechanisms and management of rheumatic irAEs with focus on arthritis, myositis, and vasculitis. Based on these findings, potential therapeutic strategies against rheumatic irAEs are discussed. Full article

The aim of our proposed concept is to find new target structures for combating cancers with unmet medical needs. This, unfortunately, still applies to the majority of the clinically most relevant tumor entities such as, for example, liver cancer, pancreatic cancer, and many others. Current target structures almost all belong to the class of oncogenic proteins caused by tumor-specific genetic alterations, such as activating mutations, gene fusions, or gene amplifications, often referred to as cancer “driver alterations” or just “drivers.” However, restoring the lost function of tumor suppressor genes (TSGs) could also be a valid approach to treating cancer. TSG-derived proteins are usually considered as control systems of cells against oncogenic properties; thus, they represent the brakes in the “car-of-life.” Restoring these tumor-defective brakes by gene therapy has not been successful so far, with a few exceptions. It can be assumed that most TSGs are not being inactivated by genetic alteration (class 1 TSGs) but rather by epigenetic silencing (class 2 TSGs or short “C2TSGs”). Reactivation of C2TSGs in cancer therapy is being addressed by the use of DNA demethylating agents and histone deacetylase inhibitors which act on the whole cancer cell genome. These epigenetic therapies have neither been particularly successful, probably because they are “shotgun” approaches that, although acting on C2TSGs, may also reactivate epigenetically silenced oncogenic sequences in the genome. Thus, new strategies are needed to exploit the therapeutic potential of C2TSGs, which have also been named DNA methylation cancer driver genes or “DNAme drivers” recently. Here we present a concept for a new translational and therapeutic approach that focuses on the phenotypic imitation (“mimesis”) of proteins encoded by highly disease-relevant C2TSGs/DNAme drivers. Molecular knowledge on C2TSGs is used in two complementary approaches having the translational concept of defining mimetic drugs in common: First, a concept is presented how truncated and/or genetically engineered C2TSG proteins, consisting solely of domains with defined tumor suppressive function can be developed as biologicals. Second, a method is described for identifying small molecules that can mimic the effect of the C2TSG protein lost in the cancer cell. Both approaches should open up a new, previously untapped discovery space for anticancer drugs. Full article