Search Results (72)

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

The accessibility of nature trails for people with motor disabilities and impairments stands as a significant challenge for inclusive tourism. In the present study, we would like to present a review of research, approaches, and solutions to enable people with motor impairments to enjoy nature trails independently or with assistance. The study is conducted from the perspective of public bodies that aim to reduce the accessibility barriers for People with Disabilities (PwDs) by adapting and improving the conditions of the trails and by providing clear and comprehensive information about the difficulties that hikers may encounter on a trail while using a specific aid. The paper initially presents the wide variety of aids for outdoor mobility, including both those to be used independently (i.e., self-propelled wheelchairs that can be equipped with additional small wheels, off-road wheels and/or auxiliary drives) and those that require assistance (e.g., single-wheeled wheelchairs). Then, we shift focus onto the difficulty classification of trails for PwDs, analysing papers and guidelines that tried to define objective evaluation criteria such as the slope, the trail surface, and the length of the sloping sections. Starting from these studies, the paper proposes a synthesis of the different classifications that consider, for the first time, all the aids available on the market, thus filling the gaps of the single studies. In the last sections, we present some national and international guidelines with tailored and practical solutions to improve the accessibility of nature trails and some studies about the inclusive planning that directly involves PwDs, as well as on the need for a better training of tourism service providers. The present work aims to stimulate a debate on the barriers and opportunities related to the accessibility of hiking trails, contributing to making nature a truly accessible experience for all. Full article

In recent years, autonomous driving technology has made remarkable progress in urban transportation and logistics, while its application in complex off-road environments has gradually become a research hotspot. Compared to traditional manned vehicles, unmanned vehicles demonstrate higher safety and flexibility in scenarios such as rapid transportation, emergency rescue, and environmental reconnaissance. However, current research on path planning is predominantly focused on structured environments, with limited attention given to unstructured off-road conditions. This paper proposes an improved A* algorithm tailored to address the challenges of path planning in complex off-road environments. First, a grid map incorporating multi-dimensional information is constructed by integrating elevation data, risk zones, and surface attributes, significantly enhancing environmental perception accuracy. At the algorithm level, the heuristic function and search strategy of the A* algorithm are optimized to improve its efficiency and path smoothness in complex terrains. Furthermore, the method supports the flexible planning of three types of paths—minimizing time, minimizing risk, or optimizing smoothness—based on specific task requirements. Simulation results demonstrate that the improved A* algorithm effectively adapts to dynamic off-road environments, providing intelligent and efficient path planning solutions for unmanned vehicles. The proposed method holds significant value for advancing the application of autonomous driving technology in complex environments. Full article

Kruger National Park is one of the most well-preserved national parks in the Southern Hemisphere. However, cases of visitors participating in deviant leisure practices (DLPs) are reported in the park, threatening the sustainability of sensitive tourism resources. Adopting a deviant leisure lens, this study assesses the extent to which visitors participate in DLPs at the Kruger National Park (KNP) and the causes of those behaviours. Variables adopted from the KNP codes of conduct for visitors were used to measure the DLPs based on the visitors’ perception of the park. A quantitative survey design, with a sample size of 237 respondents, assessed respondents’ participation in DLPs. The study results reveal that visitors participate in DLPs at KNP. However, the level at which visitors participate in DLPs is inconsistent. The most common DLPs by visitors are getting close to animals to take pictures and driving off-road to see animals. The reasons for visitors participating in these behaviours are the need to create memorable experiences and being in “holiday mode”. The least violated codes of conduct in the park are picking up archaeological objects to keep them as souvenirs and bringing prohibited items into the park without declaring. This study is significant as it is the first to investigate the extent visitors participate in DLPs using a self-reported instrument. Based on the results, park managers may develop effective strategies to reduce the number of visitors getting close to animals to take pictures and driving off-road to observe animals at close range. Full article

LiDAR-based place recognition (LPR) is crucial for the navigation and localization of autonomous vehicles and mobile robots in large-scale outdoor environments and plays a critical role in loop closure detection for simultaneous localization and mapping (SLAM). Existing LPR methods, which utilize 2D bird’s-eye view (BEV) projections of 3D point clouds, achieve competitive performance in efficiency and recognition accuracy. However, these methods often struggle with capturing global contextual information and maintaining robustness to viewpoint variations. To address these challenges, we propose R2SCAT-LPR, a novel, transformer-based model that leverages self-attention and cross-attention mechanisms to extract rotation-robust place feature descriptors from BEV images. R2SCAT-LPR consists of three core modules: (1) R2MPFE, which employs weight-shared cascaded multi-head self-attention (MHSA) to extract multi-level spatial contextual patch features from both the original BEV image and its randomly rotated counterpart; (2) DSCA, which integrates dual-branch self-attention and multi-head cross-attention (MHCA) to capture intrinsic correspondences between multi-level patch features before and after rotation, enhancing the extraction of rotation-robust local features; and (3) a combined NetVLAD module, which aggregates patch features from both the original feature space and the rotated interaction space into a compact and viewpoint-robust global descriptor. Extensive experiments conducted on the KITTI and NCLT datasets validate the effectiveness of the proposed model, demonstrating its robustness to rotation variations and its generalization ability across diverse scenes and LiDAR sensors types. Furthermore, we evaluate the generalization performance and computational efficiency of R2SCAT-LPR on our self-constructed OffRoad-LPR dataset for off-road autonomous driving, verifying its deployability on resource-constrained platforms. Full article

Conventional energy management strategies based on reinforcement learning often fail to achieve their intended performance when applied to driving conditions that significantly deviate from their training conditions. Therefore, the conventional reinforcement-learning-based strategy is not suitable for complex off-road conditions. This research suggests an energy management strategy for hybrid tracked vehicles operating in off-road conditions that is based on adaptive reinforcement learning. Power demand is described using a Markov chain model that is updated online in a recursive way. The technique updates the MC model and recalculates the reinforcement learning algorithm using the intrinsic matrix norm (IMN) as a criteria. According to the simulation results, the suggested method can increase the adaptability of energy management based on the reinforcement learning strategy in off-road conditions, as evidenced by the 7.66% reduction in equivalent fuel consumption when compared with the conventional Q-learning based energy management strategy. Full article

This paper proposes a framework for predicting traversability probability in off-road environments by distilling knowledge from large language models (LLMs) such as GPT-4o into lightweight models. The GPT-4off approach utilizes GPT-generated data to train a compact model capable of real-time operation on edge devices, such as the NVIDIA Orin board. Unlike traditional systems that focus on identifying traversable areas, this study emphasizes the prediction of traversability probability to facilitate faster decision-making in complex environments. This is particularly advantageous for unmanned ground vehicles, for which obstacles and terrain variability present significant challenges. The GPT-4off framework improves real-time performance through knowledge distillation and domain-specific optimization, ensuring efficient resource use while maintaining LLM-level performance. Experimental results on the RUGD off-road dataset show that the lightweight model achieves GPT-level performance while being deployable on edge devices. This framework effectively reduces human annotation costs and RAM power consumption, improves the practicality of off-road autonomous driving systems, and demonstrates the potential of leveraging LLM capabilities for low-power real-time applications. Full article

The purpose of this review is to comprehensively compare the developments and challenges in the energy performance of unconventional pneumatic suspension (PS) and hydropneumatic suspension (HPS), which have special applications in passenger cars, trucks, military vehicles and agricultural equipment. The main differences between PS and HPS, as well as their advantages and disadvantages, are presented. The PS system is discussed along with its principle of operation, advances in development, principle of operation of air springs, their models, characteristics, vibration isolation, and simulation models. The HPS system is discussed, along with its operational principles, progress in development, models, and characteristics. This review also discusses new trends in HPS development, such as the effect of a pressure fluctuation damper (PFD) placed in a hydraulic cylinder on the damping performance index (DPI) of an HPS under off-road driving conditions. It highlights innovative solutions that can be expected in the future in PS and HPS systems, with the expectations of drivers and passengers. The review focused on trends and challenges in PS and HPS development, such as integration with electronics, smart solutions, customized solutions, emphasis on compliance with ecological and environmental requirements, and applications in electric vehicles (EVs) and autonomous vehicles (AVs). Full article

Spatiotemporal models for the 3-D shape and motion of objects allowed large progress in the 1980s in visual perception of moving objects observed from a moving platform. Despite the successes demonstrated with several vehicles, the “4-D approach” has not been accepted generally. Its advantage is that only the last image of the sequence needs to be analyzed in detail to allow the full state vectors of moving objects, including their velocity components, to be reconstructed by the feedback of prediction errors. The vehicle carrying the cameras can, thus, together with conventional measurements, directly create a visualization of the situation encountered. In 1994, at the final demonstration of the project PROMETHEUS, two sedan vehicles using this approach were the only ones worldwide capable of driving autonomously in standard heavy traffic on three-lane Autoroutes near Paris at speeds up to 130 km/h (convoy driving, lane changes, passing). Up to ten vehicles nearby could be perceived. In this paper, the three-layer architecture of the perception system is reviewed. At the end of the 1990s, the system evolved from mere recognition of objects in motion, to understanding complex dynamic scenes by developing behavioral capabilities, like fast saccadic changes in the gaze direction for flexible concentration on objects of interest. By analyzing motion of objects over time, the situation for decision making was assessed. In the third-generation system “EMS-vision” behavioral capabilities of agents were represented on an abstract level for characterizing their potential behaviors. These maneuvers form an additional knowledge base. The system has proven capable of driving in networks of minor roads, including off-road sections, with avoidance of negative obstacles (ditches). Results are shown for road vehicle guidance. Potential transitions to a robot mind and to the now-favored CNN are touched on. Full article

In field driving activities, off-road areas usually lack existing paths that can be directly driven on by ground vehicles, but their surface environments can still satisfy the planning and passage requirements of some off-road vehicles. Additionally, the existing path planning methods face limitations in complex field environments characterized by undulating terrains and diverse land cover types. Therefore, this study introduces an improved A* algorithm and an adapted 3D model of real field scenes is constructed. A velocity curve is fitted in the evaluation function to reflect the comprehensive influences of different slopes and land cover types on the traffic speed, and the algorithm not only takes the shortest distance as the basis for selecting extension nodes but also considers the minimum traffic speed. The 8-neighborhood search method of the traditional A* algorithm is improved to a dynamic 14-neighborhood search method, which effectively reduces the number of turning points encountered along the path. In addition, corner thresholds and slope thresholds are incorporated into the algorithm to ensure the accessibility of path planning, and some curves and steep slopes are excluded, thus improving the usability and safety of the path. Experimental results show that this algorithm can carry out global path planning in complex field environments, and the planned path has better passability and a faster speed than those of the existing approaches. Compared with those of the traditional A* algorithm, the path planning results of the improved algorithm reduce the path length by 23.30%; the number of turning points is decreased by 33.16%; and the travel time is decreased by 38.92%. This approach is conducive to the smooth progress of various off-road activities and has certain guiding significance for ensuring the efficient and safe operations of vehicles in field environments. Full article

Children on farms face high risks of work- and non-work-related fatalities, with tractors being a significant contributor. This study examines children’s involvement in fatal tractor-related accidents within agriculture in Iceland from 1918 to 2024, explores adult reflections on childhood tractor-driving experiences, and analyses Members of Parliament’s arguments against setting a minimum age for off-road tractor driving. The data are based on parliamentary debates on tractor-related legislation, fatal tractor-related accidents documented in newspaper archives and supplementary sources, and narrative interviews with former summer children who stayed at farms during their childhoods. Over half of the 81 registered accidents involved children—primarily boys—with 75% occurring between 1958 and 1988, when no minimum age for off-road tractor driving existed. The fatality incidence rate for children was more than four times higher than for adults. Arguments against minimum age requirements for off-road driving included the need for child labour, children’s superior driving skills, and the denial that children were more often victims than adults. Since 1988, no child has died while driving a tractor. A human-centred approach focusing on the working conditions, driver capacity, and adherence to safety procedures and legal frameworks is needed to prevent future accidents. Full article

The inserts supporting run-flat tire (ISRFT) is mainly used in military off-road vehicles, which need to maintain high mobility after a blowout. Regulations show that the ISRFT can be driven safely for at least 100 km at a speed of 30 km/h to 40 km/h under zero-pressure conditions. However, the ISRFT generates serious heat during zero-pressure driving, which accelerates the aging of the tire rubber and degrades its performance. In order to study the thermo-mechanical coupling characteristics of the ISRFT, a three-dimensional finite element model verified by bench tests was established. Then, the stress–strain, energy loss and heat generation of the ISRFT were analyzed by the sequential thermo-mechanical coupling method to obtain the steady-state temperature field (SSTF). Finally, four kinds of honeycomb inserts bodies were designed based on the tangent method, and the SSTF of the honeycomb and the original ISRFT were compared. The results indicated that the high-temperature region of the ISRFT is concentrated in the shoulder area. For every 1 km/h increase in velocity, the temperature at the shoulder of the tire increases by approximately 1.6 °C. The SSTF of the honeycomb ISRFT is more uniformly distributed, and the maximum temperature of the shoulder decreases by about 30 °C, but the maximum temperature of the tread increases by about 40 °C. This study provides methodological guidance for investigating the temperature and mechanical characteristics of the ISRFT under zero-pressure conditions. Full article

To overcome the issue of unstable speed output encountered by cotton pickers operating in harsh environments and subject to frequent external load fluctuations, a hydraulic–mechanical transmission (HMT) for cotton pickers is proposed in this study. By analyzing the driving system of the cotton picker, a Lavira-based HMT scheme is developed. The matching characteristics of the HMT speed ratio are analyzed, a continuity and smoothness test of the speed ratio of the changing segment is carried out, and the influence law of smoothness of the HMT changing segment is discussed. The results show that the HMT system effectively satisfies the driving speed requirements for both field harvesting and road transportation of cotton pickers. The HMT speed ratio is continuously controllable and the design is reasonable. The HMT load torque and the oil pressure in the main oil circuit have a significant impact on the smoothness indicators of speed reduction and dynamic load. Additionally, the flow rate of the governor valve has a notable effect on the smoothness indicator of sliding friction power. However, the engine’s output speed has no significant influence on the HMT’s smoothness. This research can provide theoretical support for the development and design of cotton picker gearboxes and the transmission characteristics and experimental research of off-road vehicle gearboxes. Full article

The automotive industry, with particular reference to the off-road sector, is facing several challenges, including the integration of Advanced Driver Assistance Systems (ADASs), the introduction of autonomous driving capabilities, and system-specific requirements that are different from the traditional car market. Current vehicular electrical–electronic (E/E) architectures are unable to support the amount of data for new vehicle functionalities, requiring the transition to zonal architectures, new communication standards, and the adoption of Drive-by-Wire technologies. In this work, we propose an automated methodology for next-generation off-road vehicle E/E architectural design. Starting from the regulatory requirements, we use a MILP-based optimizer to find candidate solutions, a discrete event simulator to validate their feasibility, and an ascent-based gradient method to reformulate the constraints for the optimizer in order to converge to the final architectural solution. We evaluate the results in terms of latency, jitter, and network load, as well as provide a Pareto analysis that includes power consumption, cost, and system weight. Full article

The primary objective of this research is to address the existing gap about the use of a path-planning algorithm that will reduce energy consumption in off-road applications of tracked electric vehicles. The study focuses on examining various off-road terrains and their impact on energy consumption to validate the effectiveness of the proposed solution. To achieve this, a tracked electric vehicle energy model that incorporates vehicle dynamics is developed and verified using real vehicle driving data logs. This model serves as the foundation for devising a strategy that can effectively enhance the energy efficiency of off-road tracked electric vehicles in real-world scenarios. The analysis involves a thorough examination of different off-road terrains to identify strategies that can adapt to diverse landscapes. The path planning strategy employed in this study is a modified version of the A*, called the Energy-Efficient Path Planning (EEPP) algorithm, specifically tailored for the dynamic energy consumption model of off-road tracked electric vehicles. The energy consumption of the produced paths is then compared using the validated energy consumption model of the tracked electric vehicle. It is important to note that the identification of an energy-efficient path heavily relies on the characteristics of the vehicle and the dynamic energy consumption model that has been developed. Furthermore, the algorithm takes into account real-world and practical considerations associated with off-road applications during its development and evaluation process. The results of the comprehensive analysis comparing the EEPP algorithm with the A* algorithm demonstrate that our proposed approach achieves energy savings of up to 6.93% and extends the vehicle’s operational range by 7.45%. Full article