Search Results (30)

LiDAR-based 3D object detection is fundamental in autonomous driving but remains challenging due to the irregularity, unordered nature, and non-uniform density of point clouds. Existing methods primarily rely on either graph-based or tree-based representations: Graph-based models capture fine-grained local geometry, while tree-based approaches encode hierarchical global semantics. However, these paradigms are often used independently, limiting their overall representational capacity. In this paper, we propose density-aware tree–graph cross-message passing (DA-TGCMP), a unified framework that exploits the complementary strengths of both structures to enable more expressive and robust feature learning. Specifically, we introduce a density-aware graph construction (DAGC) strategy that adaptively models geometric relationships in regions with varying point density and a hierarchical tree representation (HTR) that captures multi-scale contextual information. To bridge the gap between local precision and global contexts, we design a tree–graph cross-message-passing (TGCMP) mechanism that enables bidirectional interaction between graph and tree features. The experimental results of three large-scale benchmarks, KITTI, nuScenes, and Waymo, show that our method achieves competitive performance. Specifically, under the moderate difficulty setting, DA-TGCMP outperforms VoPiFNet by approximately 2.59%, 0.49%, and 3.05% in the car, pedestrian, and cyclist categories, respectively. Full article

Decades of migration and refugee influxes have driven Amman’s rapid urban growth, yet newer neighborhoods increasingly grapple with fragmented social cohesion. This study examines whether walkable design can strengthen community bonds, focusing on Deir Ghbar, a car-centric district in West Amman. Using GIS and mixed-methods analysis, we assess how walkability metrics (residential density, street connectivity, land-use mix, and retail density) correlate with sense of community. The results reveal that street connectivity and residential density enhance social cohesion, while land-use mix exhibits no significant effect. High-density, compact neighborhoods foster neighborly interactions, but major roads disrupt these connections. A critical mismatch emerges between quantitative land-use metrics and resident experiences, highlighting the need to integrate spatial data with community insights. Amman’s zoning policies, particularly the stark contrast between affluent low-density Zones A/B and underserved high-density Zones C/D, perpetuate socio-spatial segregation—a central critique of this study. We urge the Greater Amman Municipality’s 2025 Master Plan to prioritize mixed-density zoning, pedestrian retrofits (e.g., traffic calming and sidewalk upgrades), and equitable access to amenities. This study provides a replicable GIS and survey-based framework to address urban socio-spatial divides, aligning with SDG 11 for inclusive cities. It advocates for mixed-density zoning and pedestrian-first interventions in Amman’s Master Plan. By integrating a GIS with social surveys, this study offers a replicable model for addressing socio-spatial divides in cities facing displacement and inequality. Full article

3D object detection plays a pivotal role in achieving accurate environmental perception, particularly in complex traffic scenarios where single-modal detection methods often fail to meet precision requirements. This highlights the necessity of multi-modal fusion approaches to enhance detection performance. However, existing camera-LiDAR intermediate fusion methods suffer from insufficient interaction between local and global features and limited fine-grained feature extraction capabilities, which results in inadequate small object detection and unstable performance in complex scenes. To address these issues, the multi-modal 3D object detection algorithm with pointwise and voxelwise fusion (MPVF) is proposed, which enhances multi-modal feature interaction and optimizes feature extraction strategies to improve detection precision and robustness. First, the pointwise and voxelwise fusion (PVWF) module is proposed to combine local features from the pointwise fusion (PWF) module with global features from the voxelwise fusion (VWF) module, enhancing the interaction between features across modalities, improving small object detection capabilities, and boosting model performance in complex scenes. Second, an expressive feature extraction module, improved ResNet-101 and feature pyramid (IRFP), is developed, comprising the improved ResNet-101 (IR) and feature pyramid (FP) modules. The IR module uses a group convolution strategy to inject high-level semantic features into the PWF and VWF modules, improving extraction efficiency. The FP module, placed at an intermediate stage, captures fine-grained features at various resolutions, enhancing the model’s precision and robustness. Finally, evaluation on the KITTI dataset demonstrates a mean Average Precision (mAP) of 69.24%, a 2.75% improvement over GraphAlign++. Detection accuracy for cars, pedestrians, and cyclists reaches 85.12%, 48.61%, and 70.12%, respectively, with the proposed method excelling in pedestrian and cyclist detection. Full article

With the advancement of autonomous vehicles and their integration into urbanized areas, new challenges emerge related to safety and risk management. This paper presents an approach to assessing the risks of using autonomous cars in urban environments based on game theory. The analysis focuses on interactions between autonomous and traditional vehicles, as well as other road participants, such as pedestrians and cyclists. By employing game theory models, potential conflicts, risk scenarios, and their impact on traffic safety and efficiency are identified. The proposed methods provide a foundation for developing risk management strategies that contribute to the safe and sustainable integration of autonomous vehicles in urban areas. Full article

Accurate multi-object tracking (MOT) is essential for autonomous vehicles, enabling them to perceive and interact with dynamic environments effectively. Single-modality 3D MOT algorithms often face limitations due to sensor constraints, resulting in unreliable tracking. Recent multi-modal approaches have improved performance but rely heavily on complex, deep-learning-based fusion techniques. In this work, we present CLF-BEVSORT, a camera-LiDAR fusion model operating in the bird’s eye view (BEV) space using the SORT tracking framework. The proposed method introduces a novel association strategy that incorporates structural similarity into the cost function, enabling effective data fusion between 2D camera detections and 3D LiDAR detections for robust track recovery during short occlusions by leveraging LiDAR depth. Evaluated on the KITTI dataset, CLF-BEVSORT achieves state-of-the-art performance with a HOTA score of 77.26% for the Car class, surpassing StrongFusionMOT and DeepFusionMOT by 2.13%, with high precision (85.13%) and recall (80.45%). For the Pedestrian class, it achieves a HOTA score of 46.03%, outperforming Be-Track and StrongFusionMOT by (6.16%). Additionally, CLF-BEVSORT reduces identity switches (IDSW) by over 45% for cars compared to baselines AB3DMOT and BEVSORT, demonstrating robust, consistent tracking and setting a new benchmark for 3DMOT in autonomous driving. Full article

To improve the accuracy of detecting small and long-distance objects while self-driving cars are in motion, in this paper, we propose a 3D object detection method, Att-BEVFusion, which fuses camera and LiDAR data in a bird’s-eye view (BEV). First, the transformation from the camera view to the BEV space is achieved through an implicit supervision-based method, and then the LiDAR BEV feature point cloud is voxelized and converted into BEV features. Then, a channel attention mechanism is introduced to design a BEV feature fusion network to realize the fusion of camera BEV feature space and LiDAR BEV feature space. Finally, regarding the issue of insufficient global reasoning in the BEV fusion features generated by the channel attention mechanism, as well as the challenge of inadequate interaction between features. We further develop a BEV self-attention mechanism to apply global operations on the features. This paper evaluates the effectiveness of the Att-BEVFusion fusion algorithm on the nuScenes dataset, and the results demonstrate that the algorithm achieved 72.0% mean average precision (mAP) and 74.3% nuScenes detection score (NDS), with an advanced detection accuracy of 88.9% and 91.8% for single-item detection of automotive and pedestrian categories, respectively. Full article

The significance of developing shared road infrastructure in cities throughout the world is growing. Driven by the need to improve traffic management in ways that enhance multiple sustainability outcomes, developing the tools needed to test shared space proposals is becoming more sought after by responsible agencies. This paper reviews approaches to simulation modeling focused on representing and assessing shared spaces, culminating in a new approach presented here called the Integrated Pedestrian–Vehicle Model (IPVM)—a novel framework that combines social force models, car-following models and other algorithms from the robotics domain to better describe both mobility and activity within a shared space. The IPVM recognizes that while shared spaces are inherently multimodal, past efforts have tended to use pedestrian models as a starting point. Most consider the interaction of pedestrians with other pedestrians and static road infrastructure. Shared space models are generally microscopic models that integrate a social force model with a variety of car-following models to describe the interaction between vehicles and pedestrians. However, there is little research and few practical methodologies that address the long-range conflict avoidance between vehicles and pedestrians. This aspect is crucial for accurately representing the desire lines and pathways of pedestrians and active transport users in complex environments like shared spaces. The IPVM describes and visualizes shared road infrastructure with an absence of separating infrastructure between users and outputs. It generates metrics that can be used in conjunction with the latest evaluation approaches to gauge the sustainability credentials of shared space road proposals. Enhanced modeling of shared space solutions can lead to more effective implementation, which can potentially reduce the presence of cars, increase public and active transport use and lead to a more sustainable transport system. Full article

Pedestrian trajectory prediction is one of the most important topics to be researched for unmanned driving and intelligent mobile robots to perform perceptual interaction with the environment. To solve the problem of the SGAN (social generative adversarial networks) model lacking an understanding of pedestrian interaction and scene constraints, this paper proposes a trajectory prediction method based on a scenario-constrained generative adversarial network. Firstly, a self-attention mechanism is added, which can integrate information at every moment. Secondly, mutual information is introduced to enhance the influence of latent code on the predicted trajectory. Finally, a new social pool is introduced into the original trajectory prediction model, and a scene edge extraction module is added to ensure the final output path of the model is within the passable area in line with the physical scene, which greatly improves the accuracy of trajectory prediction. Based on the CARLA (CAR Learning to Act) simulation platform, the improved model was tested on the public dataset and the self-built dataset. The experimental results showed that the average moving deviation was reduced by $26.4\%$ and the final offset was reduced by $23.8\%$, which proved that the improved model could better solve the uncertainty of pedestrian turning decisions. The accuracy and stability of pedestrian trajectory prediction are improved while maintaining multiple modes. Full article

Disabled pedestrians are among the most vulnerable groups in road traffic. Using technology to assist this vulnerable group could be instrumental in reducing the mobility challenges they face daily. On the one hand, the automotive industry is focusing its efforts on car automation. On the other hand, in recent years, assistive technology has been promoted as a tool for consolidating the functional independence of people with disabilities. However, the success of these technologies depends on how well they help self-driving cars interact with disabled pedestrians. This paper proposes an architecture to facilitate interaction between disabled pedestrians and self-driving cars based on deep learning and 802.11p wireless technology. Through the application of assistive technology, we can locate the pedestrian with a disability within the road traffic ecosystem, and we define a set of functionalities for the identification of hand gestures of people with disabilities. These functions enable pedestrians with disabilities to express their intentions, improving their confidence and safety level in tasks within the road ecosystem, such as crossing the street. Full article

Urban transportation systems encounter distinctive challenges during planned major city events characterized by large gatherings that disrupt traffic patterns. The surge in private car usage for attending such events leads to a sudden increase in traffic, unauthorized parking, pollutant emissions, and risks to pedestrian safety in the vicinity of the event venue. This study delves into the challenges and advantages of employing Decision Support Systems (DSSs) to manage urban mobility during special urban events with the goal of reducing car dependency and promoting sustainable transportation options. The proposed methodology for designing and testing the DSS is based on the living lab principles of co-planning, co-implementing, co-monitoring, co-validating, and co-reviewing with engaged stakeholders. Moreover, testing of the DSS measures in real-world cases (i.e., during a football match at the San Siro Stadium and a concert at the Alcatraz music hall in the city of Milan, Italy) highlights the potential of the DSS in reducing the use of individual private cars in favor of shared mobility and micro-mobility solutions. As a result, the living lab has proven to be a valuable tool for interacting with stakeholders from the outset of brainstorming ideas for potential transport policies to their practical implementation, with the goal of bridging the gap between what decision-makers believe should be done, what transport operators can feasibly do, and what users desire and expect to be done. The insights presented in this paper contribute to the debate on leveraging technology to cultivate more efficient, resilient, and livable urban environments. Full article

The auto industry is accelerating, and self-driving cars are becoming a reality. However, the acceptance of such cars will depend on their social and environmental integration into a road traffic ecosystem comprising vehicles, motorcycles, bicycles, and pedestrians. One of the most vulnerable groups within the road ecosystem is pedestrians. Assistive technology focuses on ensuring functional independence for people with disabilities. However, little effort has been devoted to exploring possible interaction mechanisms between pedestrians with disabilities and self-driving cars. This paper analyzes how self-driving cars and disabled pedestrians should interact in a traffic ecosystem supported by wearable devices for pedestrians to feel safer and more comfortable. We define the concept of an Assistive Self-driving Car (ASC). We describe a set of procedures to identify people with disabilities using an IEEE 802.11p-based device and a group of messages to express the intentions of disabled pedestrians to self-driving cars. This interaction provides disabled pedestrians with increased safety and confidence in performing tasks such as crossing the street. Finally, we discuss strategies for alerting disabled pedestrians to potential hazards within the road ecosystem. Full article

Trajectory prediction in urban scenarios is critical for high-level automated driving systems. However, this task is associated with many challenges. On the one hand, a scene typically includes different traffic participants, such as vehicles, buses, pedestrians, and cyclists, which may behave differently. On the other hand, an agent may have multiple plausible future trajectories based on complex interactions with the other agents. To address these challenges, we propose a multiagent, multimodal trajectory prediction method based on neural networks, which encodes past motion information, group context, and road context to estimate future trajectories by learning from the interactions of the agents. At inference time, multiple realistic future trajectories are predicted. Our solution is based on an encoder–decoder architecture that can handle a variable number of traffic participants. It uses vectors of agent features as inputs rather than images, and it is designed to run on a physical autonomous car, addressing the real-time operation requirements. We evaluate the method using the inD dataset for each type of traffic participant and provide information about its integration into an actual self-driving car. Full article

The importance of an external interaction interface (eHMI) has grown in recent years. Most eHMI concepts focus on communicating autonomous vehicle (AV)’s yielding intention to pedestrians at a crossing. However, according to previous studies, pedestrians at a crossing rely mainly on the vehicle’s movement information (implicit communication) rather than information from eHMIs (explicit communication). This paper has the purpose of proposing a specific use case in which the eHMI of future AVs could play an indispensable role in the safety of other road users (ORUs). Often VRUs cannot see the traffic flow due to a series of parked or stopped vehicles, which is a frequent cause of fatal traffic collision accidents. Drivers may also not be able to see approaching pedestrians or other cars from the side for the same reason. In this paper, the impact of an eHMI is tested from the perspective of drivers with limited visibility when a jaywalker steps into the road. A combination of colors, shapes, and information levels is presented on an eHMI. We show that our proposed eHMI design, in the deadlock scenario of a jaywalker and a driver who both lack visibility, significantly reduced the reaction time compared to when there was no eHMI. In the experiment, the willingness to stop, varying from 0 to 5, was measured from the driver’s perspective. The results showed that most users felt uncertainty and did not move quickly when seeing the light band color alone. Textual information on the eHMI was significantly more effective in providing an urgent warning of this specific scenario than vertical and horizontal light bands with color without text. In addition, red color, blinking rapidly above 3 Hz, and egocentric messages were also necessary to reduce the PRT(perception response time). By using text-added eHMI (Vertical + Text eHMI), the mean time to achieve a score above 4 for willingness to stop was 2.113 s faster than when there was no eHMI. It was 2.571 s faster than the time until the slider of the participants reached the maximum level for willingness to stop. This is a meaningful amount of difference when considering a PRT of 2.5 s, which is the Korean road design standard. As eHMIs tend to be applied for smarter mobility, it is expected that they will be more effective in preventing accidents if the eHMI is standardized in autonomous driving level 2 to 3 vehicles driven by humans before fully autonomous driving becomes a reality. Full article

This study aims to examine child pedestrian safety around parks by considering four rule-compliance measures: temporal, spatial, velocity and visual search compliance. In this regard, street crossing observations of 731 children were recorded at 17 crosswalks around four parks in Montreal, Canada. Information on child behaviors, road features, and pedestrian–vehicle interactions were gathered in three separate forms. Chi-square tests were used to highlight the individual, situational, behavioral and road environmental characteristics that are associated with pedestrian rule compliance. About half of our sampled children started crossing at the same time as the adults who accompanied them, but more rule violations were observed when the adult initiated the crossing. The child’s gender did not have a significant impact on rule compliance. Several variables were positively associated with rule compliance: stopping at the curb before crossing, close parental supervision, and pedestrian countdown signals. Pedestrian–car interaction had a mixed impact on rule compliance. Overall, rule compliance among children was high for each of our indicators, but about two-thirds failed to comply with all four indicators. A few measures, such as longer crossing signals and pedestrian countdown displays at traffic lights, may help to increase rule compliance and, ultimately, provide safer access to parks. Full article

In Latin American cities, the built environment is facing crucial challenges in the 21st century, not only in terms of the redesign of the physical environment, but also how to remodel public spaces as healthier places for walking and social interaction. The objective of this article is to evaluate the effects of the built environment on walking perceptions in a central neighbourhood in the intermediate city of Valdivia, Chile. The methodology integrates quantitative and qualitative methods to explore which elements of the physical built environment ease and hinder walkability. Depthmap software and Simpson’s Diversity Index are used to evaluate connectivity and diversity of land uses at street level. Additionally, the People Following method and 26 walking interviews are conducted using the Natural Go-Along technique to analyse pedestrians’ perceptions about their mobility environment. The results show that the factors that promote walkability mainly include streets with high connectivity values, wide pavements, diversity of greening, and facade characteristics of buildings with architectural heritage causing tranquillity, longing, and happiness. On the contrary, factors that inhibit walkability are related to poor-quality and narrow sidewalks, cars parked on sidewalks, dirty streets, and motorized traffic and vehicular noise causing negative emotions in walking perceptions such as tiredness, anger, disgust, discomfort, and insecurity, with negative effects on the well-being of residents that vary according to age and gender. Finally, recommendations are oriented to improve public spaces in central areas in southern Chile, to address moving towards more liveable and inclusive environments and support well-being through urban design in these types of context. Full article