Search Results (30)

Modern robotic systems are evolving toward conducting missions based on semantic knowledge. Such systems require environmental modeling as essential for successful mission execution. However, there is an inefficiency in that manual modeling is required whenever a new environment is given, and adaptive modeling that can adapt to the environment is needed. In this paper, we propose an integrated framework that enables autonomous environmental modeling for service robots by fusing domain knowledge with open-vocabulary-based Vision-Language Models (VLMs). When a robot is deployed in a new environment, it builds occupancy maps through autonomous exploration and extracts semantic information about objects and places. Furthermore, we introduce human–robot collaborative modeling beyond robot-only environmental modeling. The collected semantic information is stored in a structured database and utilized on demand. To verify the applicability of the proposed framework to service robots, experiments are conducted in a simulated home environment and a real-world indoor corridor. Through the experiments, the proposed framework achieved over 80% accuracy in semantic information extraction in both environments. Semantic information about various types of objects and places was extracted and stored in the database, demonstrating the effectiveness of DK-SMF for service robots. Full article

Despite significant advancements in indoor navigation technology over recent decades, it still faces challenges due to excessive dependency on external infrastructure and unreliable positioning in complex environments. This paper proposes an autonomous localization system that integrates advanced adaptive pedestrian dead reckoning (APDR) and binocular vision, designed to provide a low-cost, high-reliability, and high-precision solution for rescuers. By analyzing the characteristics of measurement data from various body parts, the chest is identified as the optimal placement for sensors. A chest-mounted advanced APDR method based on dynamic step segmentation detection and adaptive step length estimation has been developed. Furthermore, step length features are innovatively integrated into the visual tracking algorithm to constrain errors. Visual data is fused with dead reckoning data through an extended Kalman filter (EKF), which notably enhances the reliability and accuracy of the positioning system. A wearable autonomous localization vest system was designed and tested in indoor corridors, underground parking lots, and tunnel environments. Results show that the system decreases the average positioning error by 45.14% and endpoint error by 38.6% when compared to visual–inertial odometry (VIO). This low-cost, wearable solution effectively meets the autonomous positioning needs of rescuers in disaster scenarios. Full article

Autonomous navigation in indoor environments demands reliable perception and control strategies for nonholonomic mobile robots operating under geometric constraints. While visual servoing offers a promising framework for such tasks, conventional approaches often rely on explicit 3D feature estimation or predefined reference trajectories, limiting their adaptability in dynamic scenarios. In this paper, we propose a novel nonholonomic mobile robot corridor-following and doorway-passing method based on image-based visual servoing (IBVS) by using a single dioptric camera. Based on the unifying central spherical projection model, we present the projection mechanism of 3D lines and properties of line images for two 3D parallel lines under different robot poses. In the normalized image plane, we define a triangle enclosed by two polar lines in relation to line image conic features, and adopt a polar representation for visual features, which will naturally become zero when the robot follows the corridor middle line. The IBVS control law for the corridor-following task does not need to pre-calculate expected visual features or estimate the 3D information of image features, and is extended to doorway-passing by simply introducing an upper door frame to modify visual features for the control law. Simulations including straight corridor-following, anti-noise performance, convergence of the control law, doorway-passing, and loop-closed corridor-following are conducted. We develop a ROS-based IBVS system on our real robot platform; the experimental results validate that the proposed method is suitable for the autonomous indoor visual navigation control task for a nonholonomic mobile robot equipped with a single dioptric camera. Full article

Urban open space evaluation is crucial for enhancing human well-being and ecological sustainability, yet existing frameworks often overlook visual connectivity. This study integrates vision as a primary factor in accessibility assessment, combining the Analytic Hierarchy Process (AHP), user experience, and sustainable development frameworks. Focusing on the Chicago River corridor, we employed open data, spatial syntax, and Visibility Graph Analysis (VGA) using DepthmapX software to quantify visual parameters such as clustering coefficient, control, entropy, and integration. Results revealed fragmented visual connectivity, with obstructed zones and highly integrated nodes. Inspired by the Las Vegas Strip’s linear connectivity, design interventions prioritized vision-led strategies: removing visual barriers, establishing viewing platforms, and enhancing waterborne transportation hubs. These interventions demonstrated that visual optimization significantly improves spatial continuity and user engagement. The findings underscore the necessity of incorporating visual metrics into open space evaluation systems, offering planners a replicable methodology to address fragmentation and foster cohesive urban environments. Full article

Connected vehicle data have the potential to warn motorists of impending slowdowns and congestion in real time. Multiple data providers have recently begun providing in-cab alerts to commercial vehicle drivers. This study reports on one such deployment of in-cab alerts on 44 corridors in Indiana from April–June 2024. Approximately 20,000 alerts were analyzed, with 92% being Congestion alerts and 8% being Dangerous Slowdown alerts. Observations showed that 15% of trucks lowered their speeds by at least 5 mph 30 s after receiving a Congestion alert, while 21% of trucks reduced their speeds by at least 5 mph 30 s after receiving a Dangerous Slowdown alert. The analysis also showed that a majority of Congestion alerted trucks encountered slow-speed traffic about 3 min after receiving an alert, while a majority of Dangerous Slowdown alerted drivers had traveled through the zone of slow speeds 2 min after receiving the alert. Although these results are encouraging, the study also found that 8.1% of Congestion alerts and 8.3% of Dangerous Slowdown alerts were received by trucks when they were operating at speeds of less than or equal to 45 mph, indicating they were already in congested conditions. The study reports that 43% of trucks that received Dangerous Slowdown alerts never reduced their speed below 45 mph. The paper concludes that it is important to converge on a shared vision for these performance measures so that public agencies, in-cab alert providers, and trucking companies can agilely improve these systems and increase driver confidence in the alerts. Full article

Saudi Arabian cities have rapidly expanded their urban areas, especially their city centers, over the last four decades. This growth has led to increased vehicular usage. As a result, the daily walking experience for residents has been adversely affected. Walkability has several positive effects on people’s health and the urban environment. It serves as a means of transportation and helps create a sense of place. This enhances the legibility of urban structures and deepens emotional bonds with the city. This study uses the medium-sized Saudi Arabian city of Onaizah as a case study. It explores the feasibility of creating urban walking corridors to encourage more walking. According to Saudi Arabia’s Vision 2030, sustainable urban development and improved quality of life are key priorities. The study addresses walkability as a way to enhance the urban landscape of the city center. Geographic Information Systems (GISs) were used to analyze data and generate urban corridors in the city center. The results indicate that walking in Onaizah can be improved through three urban corridors. These corridors measure 1335 m, 1624 m, and 1937 m, respectively. They represent urban, commercial, and heritage corridors. This provides planners and decision makers an opportunity to prioritize pedestrian connectivity and improve the physical environment. Such efforts contribute to sustainable urban development. Various criteria-analysis methods were employed to assess the factors that led to the conclusion of these urban corridors. This includes evaluations of land use, transportation, and environmental considerations. The study aligns with Saudi Arabia’s Vision 2030 by promoting walking and enhancing overall walkability. It also aims to create a sustainable and livable urban environment for the community in Onaizah. Full article

In recent years, the accuracy of visual SLAM (Simultaneous Localization and Mapping) technology has seen significant improvements, making it a prominent area of research. However, within the current RGB-D SLAM systems, the estimation of 3D positions of feature points primarily relies on direct measurements from RGB-D depth cameras, which inherently contain measurement errors. Moreover, the potential of triangulation-based estimation for ORB (Oriented FAST and Rotated BRIEF) feature points remains underutilized. To address the singularity of measurement data, this paper proposes the integration of the ORB features, triangulation uncertainty estimation and depth measurements uncertainty estimation, for 3D positions of feature points. This integration is achieved using a CI (Covariance Intersection) filter, referred to as the CI-TEDM (Triangulation Estimates and Depth Measurements) method. Vision-based SLAM systems face significant challenges, particularly in environments, such as long straight corridors, weakly textured scenes, or during rapid motion, where tracking failures are common. To enhance the stability of visual SLAM, this paper introduces an improved CI-TEDM method by incorporating wheel encoder data. The mathematical model of the encoder is proposed, and detailed derivations of the encoder pre-integration model and error model are provided. Building on these improvements, we propose a novel tightly coupled visual-inertial RGB-D SLAM with encoder integration of ORB triangulation and depth measurement uncertainties. Validation on open-source datasets and real-world environments demonstrates that the proposed improvements significantly enhance the robustness of real-time state estimation and localization accuracy for intelligent vehicles in challenging environments. Full article

Situational Graphs (S-Graphs) merge geometric models of the environment generated by Simultaneous Localization and Mapping (SLAM) approaches with 3D scene graphs into a multi-layered jointly optimizable factor graph. As an advantage, S-Graphs not only offer a more comprehensive robotic situational awareness by combining geometric maps with diverse, hierarchically organized semantic entities and their topological relationships within one graph, but they also lead to improved performance of localization and mapping on the SLAM level by exploiting semantic information. In this paper, we introduce a vision-based version of S-Graphs where a conventional Visual SLAM (VSLAM) system is used for low-level feature tracking and mapping. In addition, the framework exploits the potential of fiducial markers (both visible and our recently introduced transparent or fully invisible markers) to encode comprehensive information about environments and the objects within them. The markers aid in identifying and mapping structural-level semantic entities, including walls and doors in the environment, with reliable poses in the global reference, subsequently establishing meaningful associations with higher-level entities, including corridors and rooms. However, in addition to including semantic entities, the semantic and geometric constraints imposed by the fiducial markers are also utilized to improve the reconstructed map’s quality and reduce localization errors. Experimental results on a real-world dataset collected using legged robots show that our framework excels in crafting a richer, multi-layered hierarchical map and enhances robot pose accuracy at the same time. Full article

The problem of data enrichment to train visual SLAM and VO construction models using deep learning (DL) is an urgent problem today in computer vision. DL requires a large amount of data to train a model, and more data with many different contextual and conditional conditions will create a more accurate visual SLAM and VO construction model. In this paper, we introduce the TQU-SLAM benchmark dataset, which includes 160,631 RGB-D frame pairs. It was collected from the corridors of three interconnected buildings comprising a length of about 230 m. The ground-truth data of the TQU-SLAM benchmark dataset were prepared manually, including 6-DOF camera poses, 3D point cloud data, intrinsic parameters, and the transformation matrix between the camera coordinate system and the real world. We also tested the TQU-SLAM benchmark dataset using the PySLAM framework with traditional features such as SHI_TOMASI, SIFT, SURF, ORB, ORB2, AKAZE, KAZE, and BRISK and features extracted from DL such as VGG, DPVO, and TartanVO. The camera pose estimation results are evaluated, and we show that the ORB2 features have the best results ($Er{r}_d$ = 5.74 mm), while the ratio of the number of frames with detected keypoints of the SHI_TOMASI feature is the best ($r_d=98.97\%$). At the same time, we also present and analyze the challenges of the TQU-SLAM benchmark dataset for building visual SLAM and VO systems. Full article

Computer vision plays a significant role in mobile robot navigation due to the wealth of information extracted from digital images. Mobile robots localize and move to the intended destination based on the captured images. Due to the complexity of the environment, obstacle avoidance still requires a complex sensor system with a high computational efficiency requirement. This study offers a real-time solution to the problem of extracting corridor scenes from a single image using a lightweight semantic segmentation model integrating with the quantization technique to reduce the numerous training parameters and computational costs. The proposed model consists of an FCN as the decoder and MobilenetV2 as the decoder (with multi-scale fusion). This combination allows us to significantly minimize computation time while achieving high precision. Moreover, in this study, we also propose to use the Balance Cross-Entropy loss function to handle diverse datasets, especially those with class imbalances and to integrate a number of techniques, for example, the Adam optimizer and Gaussian filters, to enhance segmentation performance. The results demonstrate that our model can outperform baselines across different datasets. Moreover, when being applied to practical experiments with a real mobile robot, the proposed model’s performance is still consistent, supporting the optimal path planning, allowing the mobile robot to efficiently and effectively avoid the obstacles. Full article

This research tests a sustainability assessment based on the 2030 Agenda’s Sustainable Development Goals (SDGs) through a process of their territorialization and implementation. This process enables the development of a spatial decision support system (SDSS) that can be integrated with strategic environmental assessments in urban planning. The assessment takes place on the transversality of the sustainability concept, considering the three dimensions (environmental, social, and economic) in a single assessment through the spatial sustainability assessment model (SSAM) by integrating geographic information systems (GIS) and multicriteria analyses. Economic development, social equity, and ecological integrity represent the three common visions for rethinking peri-urban edges. The choice of key indicators is due to the possibilities for action of urban plans and the vision of SDG 11a, which aims to support ‘positive economic, social, and environmental links among urban, peri-urban and rural areas by strengthening national and regional development planning’. In addition, they were selected to be representative of sustainable planning processes in the peri-urban area. In recognizing the limits of urban expansion processes, in the peri-urban area, it is necessary to promote a different growth based on agri-environmental values, the production of biodiversity reserves and corridors, new models of inhabiting open space, and the consolidation of civic and collective uses. The paper tests the assessment methodology in two urban plans of the Metropolitan City of Naples that address the development of the peri-urban area with different strategies. This provides insight into how to support decision-making processes so that economic development, social equity, and ecological integrity represent three common and integrated visions to enable development that is consistent with SDGs. The results show that it is possible to identify trade-offs among the three dimensions. In fact, where there are environmental subtractions necessary to accommodate peri-urban land-relation functions, these are offset by the social values of collective use and by the values of the current economy that aim to redistribute present resources. Full article

Bird–forestry relationships have been the subject of research and conservation initiatives for decades, but there are few reviews of resulting recommendations for use by forest managers. We define “bird-friendly forestry” as forest management that applies recommendations from research seeking to reconcile logging with bird conservation in natural forests used for timber production. We reviewed relevant studies to synthesize 10 principles of bird-friendly forestry: (1) protect and enhance vertical structure through uneven-aged silviculture; (2) leave abundant dead wood in different decay stages; (3) maintain residual large green trees; (4) create and maintain sufficient amounts of uncut reserves and corridors; (5) maximize forest interior by retaining large contiguous forest tracts in landscapes with sufficient functional connectivity; (6) maintain buffers along streams, rivers, and wetlands cultural and urban landscapes; (7) maintain horizontal stand structure and enhance vegetation diversity by creating canopy gaps; (8) extend the temporal scale of logging cycles; (9) minimize post-logging disturbance to forests, particularly during the bird breeding season; and (10) manage for focal species and guilds. These principles may serve as guidelines in developing bird-friendly management plans customized for regional priority species, with a clearly articulated vision and quantitative objectives through which success can be measured. Full article

Rockfall constitutes a major threat to the safety and sustainability of transport corridors bordered by rocky cliffs. This research introduces a new approach to rockfall susceptibility modeling for the identification of potential rockfall source zones. This is achieved by developing a data-driven model to assess the local slope morphological attributes with respect to the rock slope evolution processes. The ability to address “where” a rockfall is more likely to occur via the analysis of historical event inventories with respect to terrain attributes and to define the probability of a given area producing a rockfall is a critical advance toward effective transport corridor management. The availability of high-quality digital volumetric change detection products permits new developments in rockfall assessment and prediction. We explore the potential of simulating the conceptualization of slope-scale rockfall susceptibility modeling using computer power and artificial intelligence (AI). We employ advanced 3D computer vision algorithms for analyzing point clouds to interpret high-resolution digital observations capturing the rock slope evolution via long-term, LiDAR-based 3D differencing. The approach has been developed and tested on data from three rock slopes: two in Canada and one in the UK. The results indicate clear potential for AI advances to develop local susceptibility indicators from local geometry and learning from recent rockfall activity. The resultant models produce slope-wide rockfall susceptibility maps in high resolution, producing up to 75% agreement with validated occurrences. Full article

Italy is a natural corridor for entry into Europe, receiving thousands of refugees and migrants needing socio-economic and health assistance yearly. Impaired vision due to eye disease is estimated to affect at least 2.2 billion people worldwide, especially in this underprivileged population. To overcome this deep disparity, new intervention strategies, such as the PROTECT project, were planned with the aim of assessing, in the context of the head–neck area, the eye health in vulnerable applicants and holders of international protection. A total of 3023 migrants were involved in the project. Demographic factors and eye history were collected using a questionnaire. Using portable diagnostic instruments, an eye screening including monocular visual acuity, intraocular pressure, anterior segment, and ocular fundus was performed. The mean age was 31.6 ± 13.1 years and more than 50% underwent the first eye evaluation. Vision impairment was claimed by 16.6% of subjects and the most frequent diseases diagnosed were: refractive errors (11%), strabismus (6%), red eye (6%), cataract (5.3%), and ocular hypertension (1%). Retinal alterations were observed in 5% of migrants. The PROTECT project allows us to increase the accessibility of head–neck disease prevention care. Moreover, our results confirm the utility of an eye screening assessment for early identification of the most relevant and preventable ocular diseases, especially in disadvantaged populations. Full article

This research is about the China–Pakistan Economic Corridor (CPEC), which is an important and first project of the “Belt and Road” initiative (BRI). BRI is the framework and manifesto for the wide-ranging, fundamental collaboration signed by China and Pakistan in 2013. The CPEC vision and mission were initiated to develop economic growth and facilitate free trade, the people’s living standards of Pakistan and China through bilateral investments, trade, cultural exchanges, and economic activities between both countries. The initial investment for the project was $46 billion, with a tentative duration of fifteen years. This research aimed to inquire into the effects of legal risks (LR), social security (SS), and employee environmental awareness (EEA) on the project performance (PP) of the CPEC. It further investigates the significance of gender empowerment perspectives (GEP). A research framework consisting of this quantitative analysis and the bilateral impacts of the study were explored through several policies scenarios into 2025. The results of the risk analysis were rated on a Likert scale. A questionnaire survey was used in order to collect data and test the research framework and hypotheses. An empirical test was conducted using a dataset with partial least square structural equation modeling (PLS-SEM) to validate the study. Full article