Search Results (613)

This paper evaluates the feasibility of real-time traffic data analysis on resource-constrained edge devices using a hybrid processing approach. The proposed architecture integrates an LF Edge eKuiper complex event processing engine, deployed within Docker containers, with a native YOLO deep learning model for pedestrian detection. The model processes video frames at 480 × 240 resolution on CPU-only Raspberry Pi devices, achieving up to 30 FPS. The research specifically investigates the performance limits of Raspberry Pi 3 and Raspberry Pi 4 platforms when simultaneously processing high-throughput simulated traffic data from the SUMO simulator (Belgrade scenario, with vehicle distributions and densities adjusted for small, medium, and large traffic volumes) and live video streams, respectively. Experimental results indicate that while both platforms can process up to 2600 messages per second in the settings without image processing, the introduction of a camera sensor reveals a significant hardware bottleneck. The Raspberry Pi 4 maintains robust real-time performance with an average complex event detection latency of less than 500 ms. In contrast, the Raspberry Pi 3 exhibits severe performance degradation, with image processing delays exceeding 8 s, rendering it unsuitable for real-time safety alerts. The findings demonstrate that with appropriate hardware selection, edge-based complex event processing can successfully detect critical safety events, such as sudden vehicle acceleration near pedestrians, without relying on cloud infrastructure. Full article

With the widespread application of autonomous vehicles (AVs), their dynamic interactions with other road users pose significant challenges to trajectory planning. Previous research on trajectory planning in shared spaces has mainly focused on generating smooth trajectories, while research considering the risks of human–vehicle interactions remains insufficient. Therefore, a risk-considered trajectory planning framework for autonomous vehicles is proposed. This framework includes two modules: pedestrian trajectory prediction and vehicle planning. In the prediction module, Social-STGCNN is used to predict pedestrian trajectories, obtaining a series of trajectories and probabilities, which serve as input to the planning module. To ensure the rationality of trajectory planning, a planning model is established in Frenet coordinates based on a quintic polynomial. Combining Bayesian and equality principles, a risk-considered cost function is designed. Under this framework, the risk value is calculated using the pedestrian trajectory prediction probability, and further Bayesian and equality costs are calculated. Based on the constraints, the trajectory with the minimum cost is solved. To evaluate the rationality of this framework, we designed simulation experiments for five typical high-conflict scenarios: overtaking in the same direction, head-on collision, pedestrian crossing, encountering pedestrians from multiple directions, and turning while encountering pedestrians crossing. Simultaneously, the framework is validated in a real-world environment. The results show that the proposed method can accurately capture pedestrians’ crossing intentions and effectively avoid pedestrians. The trajectory generated in the real environment is highly consistent with that of a driver, and it exhibits excellent adaptability and robustness in high-density mixed traffic environments. Full article

In this paper, an improved state-space method (SSM) is proposed for gait feature extraction. By introducing zero-phase component analysis Whitening (ZCA Whitening) and an algorithm to search estimated echo as the preprocessing method, pedestrian echoes are divided into three groups according to the frequency probability density: torso, feet, and other segments. Two channels of echoes are selected as inputs to the SSM, which is employed to identify the corresponding micro-Doppler trajectory. On this basis, five gait features of torso amplitude, stride length, walking cycle, torso maximum speed, and feet maximum speed are extracted. Simulation based on the Boulic model, compared with the traditional SSM, demonstrated that there is no need to estimate the model order and that a more accurate torso micro-Doppler trajectory and effective micro-motion features of the feet can be obtained by the proposed method. Finally, 77 GHz FMCW radar was used to collect the echoes of four pedestrians. The classifier was designed based on a support vector machine (SVM), and the classification experiment verified the effectiveness of the extracted gait features. Full article

Rapid urbanisation and climate change are intensifying urban heat stress, posing significant challenges for climate-responsive urban planning. Digital and data-driven approaches, including GIS, remote sensing, microclimate simulation, and artificial intelligence (AI), have advanced urban climate analysis; however, their capacity to support human-centred planning remains insufficiently synthesised. This review analyses 78 peer-reviewed studies (2015–2025) to evaluate how digital methods address urban microclimate and outdoor thermal comfort. The reviewed studies are classified into four methodological groups: spatial data analytics, simulation-based models, parametric and optimisation workflows, and AI-driven or hybrid approaches. The results show that the majority of studies rely on proxy indicators, such as land surface temperature and sky view factor, while physiologically based comfort indices (e.g., PET and UTCI) are applied in a limited proportion of studies and remain largely confined to microscale simulations. A persistent scale mismatch is identified between large-scale analytics and pedestrian-level thermal experience, alongside geographic and climatic biases, particularly in hot-arid regions. Unlike previous reviews, this study integrates digital methodologies, urban microclimate processes, and human-centred thermal comfort within a unified framework. The findings provide actionable insights for planners and designers by supporting the integration of thermal comfort into multi-scale, climate-responsive decision-making. Full article

Autonomous cleaning robots operating in semi-structured dynamic environments must execute task-oriented motions while safely interacting with surrounding agents. These agents include pedestrians, vehicles, and other robots. In such environments (e.g., interaction-rich campus environments), reliable self-decision-making requires anticipating the future motions of surrounding agents rather than relying solely on reactive obstacle avoidance. This paper presents a trajectory prediction-enabled self-decision-making framework for autonomous cleaning robots in campus environments. A learning-based multi-agent trajectory prediction model is trained offline using public benchmarks and real-world operational data to capture typical interaction patterns in corridor-following, edge-cleaning, and intersection scenarios. The predicted trajectories are then incorporated as forward-looking priors into the robot’s online decision-making and planning process, enabling prediction-aware yielding, detouring, and task continuation decisions. The proposed framework is evaluated using real-world data-driven scenario reconstruction on a high-fidelity simulation platform that incorporates realistic vehicle dynamics and heterogeneous traffic participants. This evaluation focuses on short-horizon prediction performance and its impact on downstream decision-making stability. The results show that integrating trajectory prediction into the decision-making loop leads to more stable motion behavior and fewer abrupt adjustments in interaction scenarios. Under short-term prediction horizons, the evaluation results show that the proposed model achieves ADERate and FDERate exceeding 90% under predefined error thresholds, while lane-change prediction accuracy remains around 79%. In addition, the robot maintains stable speed tracking with only minor fluctuations under medium-density traffic conditions. Full article

High-fidelity simulation testing is a critical component in ensuring the safety and reliability of autonomous driving systems. However, traditional methods for constructing simulation scenarios face two major bottlenecks. First, acquiring realistic road network topologies that adhere to physical and traffic rules is expensive. Second, the manual placement of scenario elements (e.g., vehicles and pedestrians) is a time-consuming and labor-intensive process, which struggles to meet the demands of large-scale and diverse testing. To address these challenges, this paper proposes an efficient and automated simulation scenario generation method and toolchain. The proposed approach begins by extracting road network topologies from real-world data sources (e.g., open map datasets) and then uses specialized tools, such as RoadRunner, to automatically assign traffic semantics and rules. The key innovation lies in leveraging the powerful image-text understanding capabilities of large multimodal models (LMMs) to analyze road network images and textual descriptions, generating a semantic heatmap that represents the spatial distribution probabilities of scenario elements. This heatmap guides the procedural content generation (PCG) process, enabling the intelligent and scalable deployment of traffic participants. Experimental results demonstrate that the proposed method can efficiently generate large-scale, high-fidelity, and cost-effective simulation scenarios. The generated scenarios not only maintain realism in topology and traffic rules but also feature rich perception and interaction capabilities. Furthermore, based on this method, we have constructed and released a novel simulation dataset tailored for training perception algorithms, further validating the practical value and advancement of the toolchain. Full article

As a typical biomimetic robotic system, quadruped robots replicate the flexible locomotion of quadruped mammals, outperforming wheeled robots in human-centered daily scenarios. To improve the social navigation adaptability of biomimetic quadruped robots in human–robot shared environments, this paper proposes a collision-aware orthogonal steering social force model (COSFM), an enhanced social force model that integrates collision prediction and social norms, inspired by human-like collision avoidance behaviors and social interaction rules. The model addresses key limitations of conventional social force models: delayed responses to dynamic pedestrians and inadequate consideration of pedestrians’ comfort zones. It introduces a time-to-collision prediction mechanism to mimic human predictive decision-making in dynamic social interactions, enhancing the robot’s anticipation of pedestrian motion intentions, and designs an orthogonal steering-based avoidance strategy for four typical human–robot interaction scenarios (head-on encounters, intersecting paths, active overtaking, passive yielding). This strategy replicates humans’ natural priority of lateral steering over abrupt deceleration or retreat, generating socially compliant trajectories aligned with human behavioral expectations. The proposed method is validated via simulation and real-world experiments on a Unitree Aliengo quadruped robot. Results show that the COSFM algorithm achieves a higher navigation success rate and better performance in path length, navigation time, and minimum human-robot distance than existing approaches, while its human-like lateral avoidance priority effectively preserves pedestrians’ psychological comfort zones, demonstrating robust social adaptability and great application potential for biomimetic legged robots. Full article

Extreme heat poses growing health risks in high-density cities, yet static assessments often fail to capture dynamic pedestrian exposure. This study quantifies the supply and demand disparity between urban shade provision and actual pedestrian demand in Fuzhou, China, during a specific extreme heat event. Integrating high-resolution mobile signaling data with dynamic urban shade simulations, we classified the road network into risk quadrants and analyzed behavioral drivers using XGBoost and SHAP algorithms. Results show a pronounced disparity: high-risk zones carry the highest pedestrian flows (a mean daily volume of 28.6 pedestrian trajectories per segment) but exhibit minimal shade coverage (3.14%), while comfort zones provide 5.5 times greater shading coverage for comparable activity levels. In contrast, surplus zones exhibit substantial shading capacity but limited pedestrian use, indicating inefficient spatial allocation of cooling resources. Further analysis shows that pedestrian accumulation in high-risk zones is primarily driven by functional necessity, whereas pedestrian flows in comfort zones are more sensitive to thermal conditions. These findings reveal structurally embedded thermal exposure risk and support a shift from static metrics toward dynamic urban planning to protect vulnerable pedestrian flows. Full article

As urbanization intensifies, improving street thermal comfort has become a critical issue in urban renewal. While existing studies generally assume that increasing the Green View Index (GVI) linearly improves pedestrian thermal comfort, this study identifies a significant “Decoupling Effect” in high-density commercial areas through field measurements and numerical simulations of three typical street types (commercial–service, ecological–recreational, and historical–cultural) in Shenyang. Integrating DeepLab V3 semantic segmentation with ENVI-met version 5.1.1 microclimate simulation, the results demonstrate a robust monotonic negative correlation between GVI and Physiological Equivalent Temperature (PET) in ecological streets (Spearman’s ρ = −0.692, p < 0.001), confirming the consistent cooling benefit of greenery in nature-dominated environments. However, a distinct “Threshold Effect” was identified in commercial streets using Piecewise Linear Regression (PLR). A critical breakpoint was detected at GVI = 22.08%. Below this threshold, visual greenery effectively contributes to cooling (slope = −0.454); yet, once GVI exceeds 22.08%, the cooling efficacy diminishes significantly (slope = −0.109), marking the onset of a “decoupling” phase. Specifically, despite Wenhua Road achieving a GVI of ~24.5% with a complex “three-board, four-belt” structure, its PET peak reaches 46.15 °C, approximately 5.5 °C higher than ecological streets. Mechanism analysis reveals that under peak thermal stress (Traffic Heat ≈ 75 W/m²), the high-intensity anthropogenic heat and hardscape radiation exceed the evaporative cooling threshold of vegetation. This study reveals the non-linear relationship between visual greenery and the physical thermal environment, suggesting that simply pursuing visual green quantity is ineffective in commercial canyon renewal; instead, a threshold-based synergistic optimization of canopy shading and pavement thermal performance is required. These findings provide a quantitative basis for sustainable street landscape planning and urban climate adaptation strategies in high-density cities. Full article

Climate change is expected to modify precipitation patterns and increase flood hazard in urban areas, potentially affecting critical infrastructures such as wastewater treatment plants (WWTPs), often located in flood-prone zones. This study assesses the impacts of climate-driven changes in extreme rainfall on flood hazard, pedestrian safety, and tangible physical damage at WWTPs in the Metropolitan Area of Barcelona, Spain. Twenty-four future flood scenarios are defined using CMIP6-based downscaled climate projections (SSP126 and SSP585), two time horizons (2041–2070 and 2071–2100), and different climate model percentiles. Climate Change Coefficients derived from updated Intensity–Duration–Frequency curves are applied to hydrodynamic simulations to evaluate flooded and high-hazard areas for plant workers, as well as direct economic damage at the Montcada i Reixac WWTP, used as a case study. Results indicate limited changes under SSP126, while SSP585 leads to systematic increases in hazard extent and damage, particularly for long-term projections (2071–2100) and extreme percentiles (90th). A large dispersion among climate models is also observed, especially for extraordinary flood events. Finally, a site-specific nature-based adaptation measure targeting frequent floods is proposed, demonstrating the potential of integrated assessments to support sustainable adaptation planning and to reduce the Expected Annual Damage in future climate conditions by 93%. Full article

In frequency-modulated continuous-wave (FMCW) radar systems, the detection of Doppler-extended targets (DETs) is a critical challenge. The micro-Doppler effects induced by the motion of extended targets such as pedestrians cause the echo energy to spread along the Doppler dimension. As a result, a single range-Doppler cell is unlikely to form a pronounced amplitude peak above the background noise level. Consequently, existing constant false alarm rate (CFAR) methods that rely on single-cell amplitude decisions tend to suffer from performance degradation in DET scenarios and exhibit limited adaptability under varying clutter conditions. To solve these issues, we propose a nonlinear transform–based variability index CFAR detector for DET (DET-NTVI-CFAR), with the aim of improving detection probability and maintaining stable false alarm control in complex clutter backgrounds. This work constructs a detection statistic by applying a nonlinear transform to the accumulated power cells and derives the threshold from the corresponding probability distribution model. A variability index CFAR (VI-CFAR) decision strategy is introduced to select the appropriate detection branch under different operating conditions. In the threshold design stage, the false alarm probability expressions of three sub-detection methods are derived to guide the selection of threshold parameters. Simulation results demonstrate that the proposed method achieves stable false alarm control and improves detection probability in various environments. Field test results also confirm the applicability of the DET-NTVI-CFAR detector. Full article

Mitigating heat stress in high-density historical districts remains a critical challenge in urban renewal due to complex morphological heterogeneity. Existing research often relies on isolated intervention measures, lacking systematic, multi-strategy assessments driven by high-precision spatial data. This study addresses this gap by establishing a quantitative framework that couples thermal infrared remote sensing with Computational Fluid Dynamics (CFD) to optimize microclimate responses in Beijing’s Liulichang Historic District. Remote sensing data were utilized to retrieve high-resolution Land Surface Temperature (LST), providing accurate thermal boundary conditions for micro-scale wind-thermal simulations. A baseline scenario (S0) and seven renewal strategies (S1–S7)—integrating varying configurations of greenery, water bodies, and permeable pavements—were evaluated using pedestrian-level comfort indices. Results reveal that single-factor interventions yield marginal improvements or thermodynamic trade-offs; specifically, adding greenery (S1) in narrow street canyons increased aerodynamic roughness, thereby obstructing ventilation and inducing localized warming. Conversely, composite strategies significantly enhanced microclimatic quality. The “greenery-water-permeable pavement” strategy (S4) achieved optimal synergistic effects, characterized by substantial cooling and spatial homogenization. Regression analysis identified water bodies as the dominant cooling driver, where a 10% increase in water coverage resulted in a temperature reduction of approximately 5.17 °C. Conversely, greenery alone showed no statistically significant cooling contribution (p > 0.05) without the synergistic presence of water or pavement modifications. This research suggests that urban renewal in high-temperature zones (>36 °C) should prioritize composite cooling networks. Furthermore, vegetation layouts near wind corridors must be precisely regulated to prevent ventilation degradation. These findings provide a scientific basis for the climate-adaptive sustainable regeneration of culturally significant, high-density urban blocks. Full article

Pedestrian inertial navigation is a pivotal technology for achieving seamless indoor and outdoor positioning. Traditional methods based on the Extended Kalman Filter (EKF) suffer from cumulative errors induced by inertial measurement unit (IMU) noise, which severely degrade the accuracy of pedestrian trajectory estimation over long durations. To address this critical limitation, a post-processing trajectory optimization approach for pedestrian inertial navigation based on the Birkhoff pseudospectral method is proposed in this paper. Leveraging the initial attitude and position estimates derived from the Zero-Velocity Update (ZUPT) technique and the EKF framework, the proposed method first parameterizes continuous-time acceleration measurements by adopting Chebyshev nodes as collocation points, and then formulates and solves the trajectory optimization problem via a Birkhoff pseudospectral framework, which effectively suppresses noise interference from the IMU accelerometer. Simulation experiments validate the superior noise suppression capability of the proposed algorithm. Furthermore, physical experiments conducted with a foot-mounted IMU demonstrate that the final position error is reduced by approximately 90% in comparison with the traditional EKF-based method. Full article

Urban heat islands (UHIs) pose escalating threats to public health and thermal comfort in dense urban environments. However, physics-based evaluations of material-specific cooling interventions and their integration into operational digital twin platforms remain limited. This study develops an integrated framework connecting computational fluid dynamics (CFD) modeling with digital twin visualization to evaluate UHI mitigation strategies. The objectives are to quantify the thermal mitigation effects of surface emissivity optimization on land surface temperature (LST) and pedestrian-level air temperature ($T_{air}$) to establish a data preprocessing pipeline converting CFD outputs into platform-independent visualization datasets, and to comparatively evaluate 2D GIS-based and 3D voxelization visualization approaches. Four emissivity scenarios were simulated using STAR-CCM+ for a 4 km² residential area in Gwacheon City, Republic of Korea. Comprehensive optimization (Case D) reduced the mean LST from 46.6 °C to 42.0 °C and T_air from 35.7 °C to 35.3 °C. Concrete-only optimization achieved 90.5% of the total thermal reduction while decreasing spatial variability (σ) from 7.1 to 5.8 during peak hours. The voxel-based 3D visualization provided a superior representation of vertical thermal stratification compared to 2D mapping. These findings establish a scalable foundation for climate-responsive urban management. Full article

How closely do the subjective perceptions simulated by Artificial Intelligence align with the subjective perceptions of human participants when evaluating an urban environment? This study serves as a pilot investigation to explore how far multimodal Large Language Models can effectively model human responses to visual stimuli based on subjective criteria. The exploratory nature of this research intends to test the feasibility of the methodology rather than provide a definitive standard. By focusing on a small set of detailed audits, a small-scale experiment performs an in-depth, qualitative examination of how machines and human assessments compare to each other in specific situations. To conduct the comparison, ratings of urban scenes were collected from human participants and two multimodal Large Language Models: ChatGPT and Gemini. After showing them an image of a sidewalk, these appraisers used a set of proposed statements to rate three sidewalks on a Likert scale. The investigation focuses on seven statements that subjectively characterize walkability factors, overall friendliness of an area, and the environment’s influence on well-being. Each participant rated each image once for all statements to establish a human baseline. The algorithms’ scores were generated using the exact same prompt, repeated multiple times to account for non-determinism. We then compared the AI’s scores to the humans’ distribution of scores and evaluated their alignment according to different experiential qualities across diverse visual environments. Full article