Automatic Vehicle Research Articles

Performance of a freight platform equipped with automated handling units. Analysis thought an optimization model

Automation should help the freight platforms to be more competitive and sustainable. The automatic handling units (AHUs) allow to speed up the freight handling operations by eliminating time wasters, increasing safety, and also allowing for a reduction in traditional labour; but they require continuous monitoring and intelligent management entrusted to specialized personnel. The use of AHUs is also seen positively from an energy and environmental sustainability point of view.The paper focuses on a smart organizational and functional structure of a freight platform equipped with automated handling vehicles. The study proposes the mathematical formulation of an optimization model that aims to minimize the operating times of handling goods in a logistics platform through the introduction of fully automatic vehicles that replace traditional systems. So, this article concerns the scientific lock of automatic and optimized fleet management of AHU. It is a question of proposing a routing of this kind of smart vehicle fleet without blockages that allow regularly submitted missions to be carried out.

Automatic Identification and Tracking Method of Case-Related Vehicles Based on Computer Vision Algorithm

Abstract Amidst the rapid advancement of artificial intelligence, computer vision algorithms have found extensive applications across various societal sectors. This paper presents the development of an automatic vehicle identification algorithm for crime-related scenarios, leveraging enhancements in computer vision technology. Initially, we refine the multi-scale feature fusion within the YOLOv4 architecture, subsequently substituting the standard convolution in the feature extraction network with depth-separable convolution to minimize parameter computation. Furthermore, we replace the conventional CIOU target localization loss function with EIOU to expedite model convergence. To address the issue of target vehicle detection failures, we incorporate the Kalman filter algorithm, ensuring precise tracking. Our experimental analysis, which utilizes both target detection and multi-target tracking evaluation indices, demonstrates that the modified YOLOv4 algorithm excels in recall, precision, and average IOU metrics compared to other algorithms, with a mean Average Precision (mAP) of 95.68% and an average detection speed of 0.039 seconds per image, satisfying real-time operational criteria. Vehicle tracking efficacy, compared using the YOLOv4-based detector before and after the modifications, shows significant improvements, indicated by a reduction in Identification Switches (IDS) across all video samples. This study introduces a robust method for the accurate identification and localization of vehicles involved in criminal activities, significantly enhancing case resolution efficiency.

User Experience and Behavioural Adaptation Based on Repeated Usage of Vehicle Automation: Online Survey

User Experience and Behavioural Adaptation Based on Repeated Usage of Vehicle Automation: Online Survey

A mathematical analysis of teleoperator optimization using multiple sensors

As the role of remote vehicle operation gains prominence, ensuring robust wireless communication systems is crucial. Prior studies have delved into various aspects of vehicle teleoperation, including its legal framework and workforce implications. Some have even formulated models to estimate the number of remote operators for large automated vehicle fleets. These models suggest that automated vehicles overseen by remote operators could supplant a significant portion of current driving jobs in the United States. Such findings underscore the need for governmental review and policy adjustment to better accommodate the burgeoning field of teleoperation, which could substantially accelerate the advancement of vehicle automation. The present study focuses on evaluating the reliability of a bi-directional communication channel based on key variable parameters. This assessment aids in determining the optimal parameter settings, thereby enhancing the effectiveness of teleoperation systems.

Models of Human Behavior for Human-Robot Interaction and Automated Driving: How Accurate Do the Models of Human Behavior Need to Be?

There are many examples of cases where access to improved models of human behavior and cognition has allowed creation of robots which can better interact with humans, and not least in road vehicle automation this is a rapidly growing area of research. Human-robot interaction (HRI) therefore provides an important applied setting for human behavior modeling - but given the vast complexity of human behavior, how complete and accurate do these models need to be? Here, we outline some possible ways of thinking about this problem, starting from the suggestion that modelers need to keep the right end goal in sight: A successful human-robot interaction, in terms of safety, performance, and human satisfaction. Efforts toward model completeness and accuracy should be focused on those aspects of human behavior to which interaction success is most sensitive. We emphasise that identifying which those aspects are is a difficult scientific objective in its own right, distinct for each given HRI context. We propose and exemplify an approach to formulating a priori hypotheses on this matter, in cases where robots are to be involved in interactions which currently take place between humans, such as in automated driving. Our perspective also highlights some possible risks of overreliance on machine-learned models of human behavior in HRI, and how to mitigate against those risks.

Connected and Intelligent Framework for Vehicle Automation in Smart-Ports

Connected and Intelligent Framework for Vehicle Automation in Smart-Ports

Navigating the landscape of automated truck platooning: A systematic review on stakeholder perspectives, employment implications, and regulatory challenges

Despite the economic and social benefits of vehicle automation and platooning, the penetration of automation in the trucking industry is concerning to the industry stakeholders. Assuming that future technical innovations will address the safety and reliability issues associated with automated truck platooning (ATP), societal concerns, especially the employment implications, require deeper exploration to frame adequate policies to allow ATP. Therefore, a systematic review of 33 relevant research articles and reports was conducted using the PRISMA technique. The study analyzed the perspectives of multiple stakeholders including drivers, policymakers, and fleet owners/industry explored in previous studies through interviews and discussions. The review suggests both positive and negative implications on employment rate, dependent on the scenario of ATP, potential of alternative job creation, and the pace of automation deployment. Previous discussions about ATP scenarios and pace of deployment further reveal the barriers perceived by stakeholders. The gap between research, stakeholders’ perspectives, and policy is identified as the root cause of delay in ATP deployment. Additionally, due to the varied physical and industrial geography and stringent safety considerations, platooning laws adopted across the US vary in requirements, such as licensing and on-site human presence, pre-approved travel corridors, etc. This review suggests that owners seek timely and incentivizing policies to invest in automation and upskill the existing workforce. Future studies should also explore the perspectives of state Departments of Transportation in addition to other stakeholders, to develop strategies and policies aimed at mitigating the concerns identified in this study to support the realization of ATP.

The Illusion of the Shared Electric Automated Vehicles Transition

The Illusion of the Shared Electric Automated Vehicles Transition

On data-induced CO[formula omitted] emissions of vehicle automation: An overlooked emission source

CO2 emission of vehicles and its influence on climate change is a widely discussed topic already for many years. New CO2 emission norms for vehicles have been introduced based on the propulsion of the vehicle, to reduce future CO2 emissions. Automated vehicles (AVs) have potential in reducing emissions by optimizing routes and speed profiles. However, they also generate extra emissions due to large data involved. Whether the norms can be met with these extra data-induced emissions of AVs remains an open question. This paper provides an approach to determine the CO2 emissions of these data related aspects. The approach dissects data-induced emissions stemming from energy consumption of the sensing components, the computing platform, disks inside the vehicle, wireless communication networks and data centers. We apply the approach to estimate CO2 emissions for varying scenarios of technology composition and energy mix. Sensitivity analysis shows that the energy intensity of wireless communication networks and the data transmission rate from vehicle to data center have the strongest influence on the resulting CO2 emissions. The energy mix also significantly affects whether the norms can be met. For high amounts of data transmission, compliance with the norms seem to be difficult in most scenarios. We recommend that the energy consumption of wireless communication networks and data transmission from vehicle to data center should be further optimized. Future work should focus on empirical evidence to validate/falsify the key assumptions in this paper, which will lead to a more accurate estimate of automation-induced emissions.

How effective is automated vehicle education? – A Kentucky case study revealing the dynamic nature of education effectiveness

This study is motivated by the need to quantitatively understand the dynamic nature of Automated Vehicle (AV) education's effectiveness, given the fact that existing research has identified factors that associated with the change of AV acceptance between before and after education. To address this research gap, an online state-wide survey study was conducted in Kentucky, USA, offering the opportunity to receive AV education via watching a video and assessing survey respondents' AV acceptance before and after education. By employing a Structural Equation Modeling (SEM) approach with multi-layer endogenous variables included, what makes AV education effective and the underlying reasons were identified and quantitatively revealed with focusing on respondents' socio-demographics, affordability, travel needs, built environment, and exposure level to AV knowledge. As a result, significant factors that impact the probability of “AV acceptance being increased after education” were identified from the aforementioned perspectives. Overall, older generations are less likely to increase their AV acceptance after education for two particular reasons: (a) concerning the comfortableness of Level 5 (full) automation and (b) living in the rural setting, which leads to fewer chances of experiencing automated driving. From a gender perspective, women are more likely to be affected by AV education because they are less familiar with AV technology than men. Also, our results suggest that Level 5 comfort rating plays the most influential role in determining the likelihood of increasing AV acceptance after education. The likelihood is improved by 33% if there is a one-unit increase in the Level 5 comfort rating. As such, the research informs AV policymakers of identities that make AV education effective for future AV education considerations.

Otonom mobil robotların Voronoi diyagramı ve karınca kolonisi optimizasyonuna dayalı yol planlaması

Path planning aims to enable autonomous robots to navigate safely and efficiently from a starting point to a target point in challenging and dynamic environments. Path planning in robotics is highly significant and still an ongoing subject of research. The increasing use of robots in various applications such as industrial automation, service robotics, and autonomous vehicles has brought forth the need for reliable and efficient path planning algorithms. The inherent capability of Voronoi diagrams to partition space based on proximity makes them an effective framework for research in path planning. Ant colony optimization, a bio-inspired optimization technique, is based on the foraging behavior of ants and is commonly employed to address the traveling salesman problem and various other combinatorial optimization problems. A hybrid method was adopted in this study by combining a Voronoi diagram and an ant colony algorithm. To create paths for the robot where it can stay as far away from obstacles as possible, a Voronoi diagram was utilized. Additionally, to find the shortest path from the starting point to the destination among these paths, ant colony optimization was employed. The main contribution of the study lies in the combination of the Voronoi diagram for obstacle avoidance and ant colony optimization for finding the optimal path. The combination of these techniques makes an effective contribution to robotic path planning by focusing on ensuring safety by avoiding obstacles while optimizing the shortest path. Experimental studies show that the hybrid method produces successful results for the desired purpose.

DESIGN NEEDS AND PERCEPTIONS OF OLDER ADULTS REGARDING SHARED-USE AUTOMATED VEHICLES

Abstract Many communities struggle to provide safe, accessible, and reliable transportation services for older adults due to high demand, rising costs, driver shortages, and other evolving challenges. Innovative transportation solutions are needed to support the current and future populations of older adults. Low-speed, shared-use, driverless shuttles present an exciting development in automated vehicle (AV) technology with potential to meet mobility needs of older adults in their community. Understanding older adults’ perceptions about and willingness to consider using these emerging modes of transportation is vital to realizing the full potential of these technologies. This presentation summarizes an in-person study conducted with 12 older (average: 66 +/- 4 years of age, range: 60 to 80 years) and 10 younger (average: 44 +/- 11 years) adults that evaluated a stationary, proof-of-concept shared-use AV retrofitted with accessibility features. We will present findings on perceptions regarding accessibility, safety, and willingness to use driverless AVs along with human factors design recommendations. While questionnaire-based studies have been the dominant approach to understanding older adults’ perceptions about shared-use AVs, in-person evaluations even with prototype AVs as described here, provide opportunities to identify goals, needs and preferences of older adults concerning usability and safety in early design stages, and through hands-on exploration help older adults develop good mental models, i.e., understand AV capabilities and limitations, towards building trust and acceptance for these emerging modes of transportation. Research and policy implications will be discussed towards enabling emerging driverless shared-use AV technologies that support safe and independent community mobility for older adults.

Driver behavior while using Level 2 vehicle automation: a hybrid naturalistic study

Vehicle automation is becoming more prevalent. Understanding how drivers use this technology and its safety implications is crucial. In a 6–8 week naturalistic study, we leveraged a hybrid naturalistic driving research design to evaluate driver behavior with Level 2 vehicle automation, incorporating unique naturalistic and experimental control conditions. Our investigation covered four main areas: automation usage, system warnings, driving demand, and driver arousal, as well as secondary task engagement. While on the interstate, drivers were advised to engage Level 2 automation whenever they deemed it safe, and they complied by using it over 70% of the time. Interestingly, the frequency of system warnings increased with prolonged use, suggesting an evolving relationship between drivers and the automation features. Our data also revealed that drivers were discerning in their use of automation, opting for manual control under high driving demand conditions. Contrary to common safety concerns, our data indicated no significant rise in driver fatigue or fidgeting when using automation, compared to a control condition. Additionally, observed patterns of engagement in secondary tasks like radio listening and text messaging challenge existing assumptions about automation leading to dangerous driver distraction. Overall, our findings provide new insights into the conditions under which drivers opt to use automation and reveal a nuanced behavioral profile that emerges when automation is in use.

Analysing the Effects of Scenario-Based Explanations on Automated Vehicle HMIs from Objective and Subjective Perspectives

Automated vehicles (AVs) are recognized as one of the most effective measures to realize sustainable transport. These vehicles can reduce emissions and environmental pollution, enhance accessibility, improve safety, and produce economic benefits through congestion reduction and cost savings. However, the consumer acceptance of and trust in these vehicles are not ideal, which affects the diffusion speed of AVs on the market. Providing transparent explanations of AV behaviour is a method for building confidence and trust in AV technologies. In this study, we investigated the explainability of user interface information in an Automated Valet Parking (AVP) system—one of the first L4 automated driving systems with a large commercial landing. Specifically, we proposed a scenario-based explanation framework based on explainable AI and examined the effects of these explanations on drivers’ objective and subjective performance. The results of Experiment 1 indicated that the scenario-based explanations effectively improved drivers’ situational trust and user experience (UX), thereby enhancing the perception and understanding that drivers had of the system’s intelligence capabilities. These explanations significantly reduced the mental workload and elevated the user performance in objective evaluations. In Experiment 2, we uncovered distinct explainability preferences among new and frequent users. New users sought increased trust and transparency, benefiting from guided explanations. In contrast, frequent users emphasised efficiency and driving safety. The final experimental results confirmed that solutions customised for different segments of the population are significantly more effective, satisfying, and trustworthy than generic solutions. These findings demonstrate that the explanations for individual differences, based on our proposed scenario-based framework, have significant implications for the adoption and sustainability of AVs.

Application of machine learning models to predict driver left turn destination lane choice behavior at urban intersections

When there are multiple lanes to choose from downstream of a turning movement, drivers should choose the innermost lane so that drivers at other approaches of the intersection may make concurrent turning movements in the outermost lane(s). However, human drivers do not always choose the innermost lane, which could lead to crashes with other vehicles. Therefore, predicting human driver behaviors is vital in reducing crashes, as the need to share the roadways with automated vehicles (AVs) continues to grow. In this research, various machine learning models have been used to predict the left turn destination lane choice of human-driven vehicles (HDVs) at urban intersections based on several quantifiable parameters. A total of 174 subject vehicles were extracted and analyzed in Los Angeles, California, and Atlanta, Georgia, using HDV trajectory data from the Next Generation SIMulation (NGSIM) database. Five machine learning techniques, namely binary logistic regression, k nearest neighbors, support vector machines, random forest, and adaptive neuro-fuzzy inference system, were applied to the extracted data to predict the lane choice behavior of drivers. The k nearest neighbors model showed the most promising results for the evaluated data with a correct decision score of over 93% for the unseen test data. This model may be programmed into: (i) AVs, in conjunction with sensors, to predict if an HDV is about to turn into the incorrect destination lane; and (ii) microscopic traffic simulation tools so that modelers can identify potential conflicts when HDVs do not select the appropriate destination lane.

Optimization of energy consumption in smart homes using firefly algorithm and deep neural networks

Electronic gadget advancements have increased the demand for IoT-based smart homes as the number of connected devices grows rapidly. The most prevalent connected electronic devices are smart environments in houses, grids, structures, and metropolises. Smart grid technology advancements have enabled smart structures to cover every nanosecond of energy use. The problem with smart, intelligent operations is that they use a lot more energy than traditional ones. Because of the growing growth of smart cities and houses, there is an increasing demand for efficient resource management. Energy is a valuable resource with a high unit cost. Consequently, authors are endeavoring to decrease energy usage, specifically in smart urban areas, while simultaneously ensuring a consistent terrain. The objective of this study is to enhance energy efficiency in intelligent buildings for both homes and businesses. For the comfort indicator ("thermal, visual, and air quality"), three parameters are used: temperature, illumination, and CO2. A hybrid rule-based Deep Neural Network (DNN) and Fire Fly (FF) algorithm are used to read the sensor parameters and to operate the comfort indication, as well as optimize energy consumption, respectively. The anticipated user attributes contributed to the system's enhanced performance in terms of the ease of use of the smart system and its energy usage. When compared to traditional approaches in expressions of Multi View with 98.23%, convolutional neural network (CNN) with 99.17%, and traffic automatic vehicle (AV) with 98.14%, the activities of the contributed approach are negligibly commanding.

External effects of urban automated vehicles on sustainability

The transport sector is responsible for an important share of pollutant emissions, and urban mobility systems are facing major challenges, such as congestion and parking needs. Automated vehicles are expected to mitigate effects of this kind, and may positively affect the sustainability of the mobility sector. We quantify the external effects of human-driven battery electric vehicles in comparison to automated ones, regarding external costs for urban areas in Germany. In our analysis we focus on environmental, social and economic external cost components. We find that vehicle automation can lower external costs by 34%, suggesting savings of 51.6 billion euros per year for Germany alone, with congestion and parking space costs accounting for the largest share of costs and savings. Our results provide an understanding of the magnitude of the external effects of automated vehicles, conducting sensitivity analyses and additionally discussing the impact of travel behavior.

A design space for automated material handling vehicles.

Material Handling Vehicles (loaders, excavators, forklifts, harvesters, etc.) have seen a strong increase in automation efforts in recent years. The contexts such vehicles operate in are frequently complex and due to the often very specific nature of industrial material handling scenarios, know-how is fragmented and literature is not as numerous as, for example, for passenger vehicle automation. In this paper, we present a contextual design space for automated material handling vehicles (AMHV), that is intended to inform context analysis and design activities across a wide spectrum of material handling use cases. It was developed on the basis of existing context and design spaces for vehicle and machine automation and extended via expert knowledge. The design space consists of separate context and interaction subspaces, that separately capture the situation and each individual point of interaction, respectively. Implications, opportunities, and limitations for the investigation and design of AMHV are discussed.

Artificial Neural Network-Powered, Driverless Vehicle Concept Development

Autonomous cars are now possible due to significant advances in robotics and intelligent control systems. Before these vehicles can safely operate in traffic and other hostile environments, there are many navigation, vision, and control issues. We want techniques that are both cost-effective and efficient, so that the field of research and academia may fully embrace self-driving cars. Within this scenario, we need something that can convert people to autonomous automobiles and include existing vehicles so that academics and explorers can access them. This study proposes a flexible mechanical layout that can be assembled in a short time and installed in most modern automobiles; it can also be used as a stepping stone in the development of autonomous vehicles. Using various actuators, conventional automobiles can be converted into autonomous vehicles. In the context of motor vehicle automation, motors are often used as actuators. In addition to motors, a pneumatic system was developed to automate the predetermined steps. An autonomous vehicle's mechanical arrangement is crucial, and it must be regularly updated and built to be robust in the face of dynamic conditions. We re-implemented two additional convolutional neural networks in an effort to conduct an objective test of their proposed network and compare our system's structure, technical complexity, and performance test during autonomous driving with theirs. This predicted network is around 250 times larger than the Alex Net network and four times larger than Pilot Net after training. Although the complexity and measurement of the publication's system are lower than other models that contribute lower latency and greater speed throughout inference, the operation was claimed by our system, which achieved autonomous driving with an equivalent efficacy as that achieved with two other models. The projected deep neural system reduces the need to infer ultra-fast computational hardware. This is important for cost efficiency, scale, and cost.

LIDAR-INERTIAL NAVIGATION BASED ON MAP AIDED DISTANCE CONSTRAINT AND FACTOR GRAPH OPTIMIZATION

Abstract. The simultaneous localization and mapping (SLAM) is one of the well-developed positioning technology that provides high accuracy and reliability positioning for automatic vehicles and robotics applications. Integrating Light Detection and Ranging (LiDAR) with an Inertial Measurement Unit (IMU) has emerged as a promising technique for achieving stable navigation results in dense urban environments, outperforming vision-based or pure Inertial Navigation System (INS) solutions. However, conventional LiDAR-Inertial SLAM systems often suffer from limited perception of surrounding geometric information, resulting in unexpected and accumulating errors. In this paper, we proposed a LiDAR-Inertial SLAM scheme that utilizes a prior structural information map which is generated from opensource OpenStreetMap (OSM). In contrast to conventional solutions of OSM-aided SLAM approaches, our method extracts the vectorized models of road and building and synthetically generates dense point maps for LiDAR registration. Specifically, a structural map processing module extracts the road models and building models from OSM and generates a structure information map (SIM) with dense point clouds. Secondly, a map aided distance (MD) constraint is calculated by registering selected keyframes and the prior SIM. Finally, a factor graph optimization (FGO) algorithm is involved to integrate the relative transformation obtained from LiDAR odometry, IMU pre-integration, and the map aided distance constraints. To evaluate the proposed LiDAR-based positioning accuracy, experimental evaluation is implemented in an opensource dataset collected in the urban canyon environments. Experimental results demonstrates that with the help of the proposed MD constraint, the LiDAR-based navigation solution can achieve accurate positioning, with a root mean square deviation (RSME) of 4.7 m.