Automatic Vehicle Research Articles

Capturing the Mind: Non-Driving-Related Tasks as a Window into Cognitive Engagement in Automated Driving

Supervising automated driving requires visual, manual, and cognitive engagement from the driver. While visual and manual engagement measures are already developed and implemented, cognitive engagement is much more difficult to observe. Considering drivers’ self-regulatory behavior when involved in non-driving-related tasks (NDRTs) during partial automation, the demand and duration of these NDRTs may indicate a certain level of driver cognitive engagement. The study explores a rating measure to partially estimate driver cognitive engagement based on the demand and duration of NDRTs and evaluate the psychometric properties of the NDRT rating. We examined the internal consistency of the measure by computing split-half reliability, tested its sensitivity to factor manipulation, and assessed criterion validity. Our initial findings suggest that the method is reliable and valid, showing satisfactory internal consistency, sensitivity to experimental manipulation, and criterion validity in predicting the takeover performance of supervising vehicle automation.

Adaptive Sliding Mode Control for AUV based on Backstepping and Neural Networks

Abstract Automatic Underwater Vehicle (AUV) inevitably suffers from various interference issues in the marine environment. Due to the limitations of underwater measurement methods and tools, as well as the complexity of AUV's control parameters in the underwater environment, dynamic measurement errors are easily cascaded and amplified, leading to the failure of the control system. In response to this phenomenon, this paper focuses on overcoming the influence of internal and external unknown factors in the tracking and control process of AUV trajectories. The internal factors are mainly the uncertainties generated by the model mismatch problem, and the external factors are mainly from the dynamic ocean currents. The AUV disturbances mainly affect the kinematics and dynamics levels directly or indirectly. In order to achieve the control of internal and external dynamic disturbances, we have designed a control system that employs backstepping (BS) and a sliding mode controller (SMC) with RBF neural networks to achieve the cascaded control of kinematics and dynamics. Comparison of multiple sets of simulations shows that our proposed algorithm has excellent anti-disturbance performance for dynamic conditions with low measurement accuracy.

An Improved UNet-Based Path Recognition Method in Low-Light Environments

The fruit industry is a significant economic sector in China, with modern orchards gradually transitioning to trellis orchards. For mechanized orchard operations, automatic vehicle navigation is essential. However, in trellis orchards, the shading from trees results in low average light intensity and large variations in lighting, posing challenges for path navigation. To address this, a path navigation algorithm for trellis orchards is proposed based on the UNet-CBAM model. The network structures of UNet, FCN, and SegNet are compared to identify and select the optimal structure for further improvement. Among the three attention mechanisms of channel attention, spatial attention, and combined attention, the most effective mechanism is identified. The optimal attention mechanism is incorporated into the optimized network to enhance the model’s ability to detect path edges and improve detection performance. To validate the effectiveness and generalizability of the model, a total of 400 images were collected under varying lighting intensities. The experimental results show that this method achieves an accuracy of 97.63%, a recall of 93.94%, and an Intersection over Union (IoU) of 92.19%. These results significantly enhance path recognition accuracy in trellis orchards, particularly under low light under conditions. Compared to the FCN and SegNet algorithms, this method provides higher detection accuracy and offers a new theoretical foundation and research approach for path recognition in low-light environments.

Smart Zone-Based Vehicle Speed Retarding System Utilizing Radio Frequency (RF) in Electronic Vehicles

The proposed system aims in designing an efficient automatic wireless vehicle speed control in low-speed zones using RF communication. The advent of new high-speed technology and the growing computer capacity provided realistic opportunity for new robot controls and realization of new methods of control theory. This technical improvement together with the need for high performance robots created faster, more accurate and more intelligent robots using new robots control devices, new drivers and advanced control algorithms. The proposed method uses RF transmitter and receiver modules for establishing wireless communication, DC motors for the vehicle movement controller. The status of the project will display on LCD display. The controlling device of the whole system is a Microcontroller to which RF receiver module, DC motors are interfaced through a motor driver. Whenever the vehicle enters into a low-speed zone, the data from RF transmitter of low-speed zone will be received by the vehicle system. The microcontroller in the vehicle system automatically slows down the speed to the speed limit of that zone. The microcontroller checks the data with the program embedded in it and performs appropriate actions on the electric motors. The microcontroller is programmed using Embedded C language.

Bluetooth Active Noise Cancellation (ANC) Technology: Principles, Integration, Applications, and Performance Evaluation

Thanks to the development of wireless audio transmission technology, Bluetooth technology made it possible to give users a seamless and convenient connection experience. However, in a noisy environment, preserving the audio quality is still difficult, which motivated people to explore the technology of Active Noise Cancellation (ANC). This paper aims to analyze integration of ANC technology and the potential of Bluetooth audio transmitting to improve the audio effect, especially in application scenarios where clear audio is required. At the beginning of this paper, how Bluetooth and ANC are evolved is reviewed for the preparatory works. Then, the technology mechanism of the ANC and the advantages in particular application scenarios such as Industrial automation and autonomous vehicles are described in detail. In addition, this paper give experimental data to illustrate that the ANC systems is effective in reducing ambient noise. The central technology of ANC system is using a microphone to detect environmental noise information and then creates a sound wave phase-inverted to the original noise to cancel. Furthermore, by connecting artificial intelligence technique, the ANC system dynamically fits from different acoustic environment to improve the audio quality. Finally, the experimental results that are quoted reveal that the advanced ANC system can reduce the noise level in a wide range of environments, cutting down the sound pressure level to 65 dB. It is clearly demonstrated that the ANC technology is widely applicable and effective to enhance the audio experience.

Does Prosocial Automation Increase Driver’s Well-being?

As societies transition to hybrid mobility systems, interactions between automated vehicles (AVs) and human users in public spaces become more complex, highlighting the critical role of prosocial behaviors. These behaviors are essential for the seamless operation of interdependent transportation networks, helping to address integration challenges of AVs with human-operated vehicles and enhancing well-being by creating more efficient, less stressful, and inclusive environments. This study explores the impact of receiving prosocial behaviors on the cognition, riding performance, and well-being of micromobility users in simulated urban traffic scenarios. Using a mixed-method design, the research contrasts two types of social interactions—prosocial and asocial—across three temporal conditions: relaxed, neutral, and urgent. The Structural Equation Modeling underscored the intricate relationships between prosocial behaviors, satisfaction, cognition, riding performance, and well-being. Incorporating social factors into driving systems could enhance safety and improve urban mobility solutions.

Simultaneous Remote Monitoring of Multiple Automated Vehicles

As vehicle automation continues to become a more prevalent part of everyday life, remote operators may be able to contribute to making this technology safer and more efficient. Such operators could be expected to monitor vehicles until it is necessary for them to intervene. In recent years several countries have passed legislation mandating the implementation of remote operation, making it a plausible scenario. For many practical reasons, operators may monitor more than one vehicle. This study provides an initial look into how remote operators might perform when asked to attend to multiple concurrent displays using simulated automated vehicles. The initial results indicate that participants retained a comparable level of accuracy in detecting failures in automation as the number of vehicles they monitored rose from one to two, albeit with a higher workload. The results and the methodology provide insights into potential task designs for remote operators of automated vehicles.

Modeling and Estimating the Effect of a Mix of Varying Levels of Automated Vehicles on Operational Performance of Urban Freeways

Automated vehicles (AVs) will likely influence various aspects of the existing transportation system in the next few decades. Existing literature documents the operational benefits of AVs at different penetration rates. However, estimating the effect of the mix of different levels of AVs on the operational performance of traffic flow has not been explored in the past. This study employs a microsimulation approach to model and estimate the potential effect of varying levels of AVs on the operational performance of freeways. The proposed approach involves a two-step process for calibrating the simulation model. In the first step, the model is calibrated from an operational perspective. In the second step, the calibration is performed from a safety perspective. Thirteen scenarios were generated considering varying penetration rates of different levels of AVs. Congestion index (CI), buffer time (BT), travel time uncertainty (TTU), and delay were computed for each scenario and segment type. The estimations indicate that increasing the penetration of level 3 to level 5 AVs significantly reduces CI, BT, TTU, and delay. In contrast, the effect of level 1 and 2 AVs on freeway operational performance is negligible. Notably, the operational benefits are more pronounced with higher penetration of level 3 and higher AVs. Additionally, the reduction in delay is greater on interchange segments compared with basic freeway segments. The study findings are valuable insights concerning the operational performance of freeways under varying penetration of different levels of AVs, assisting practitioners in formulating AVs-inclusive policies.

How can level of trust in conditional driving automation vehicles be improved? Road condition feedback strategies and the mediating role of anxiety

ABSTRACT Conditional driving automation (CDA, Level 3) vehicles will become widespread in the next few years. The driver only needs to take over the vehicle in an emergency and pay attention to the feedback from the vehicle. However, the mechanism by which feedback strategies and drivers' emotional factors influence drivers' levels of trust in automation is not clear. This study compares the effect of three road condition feedback strategies on drivers' trust in automation: no feedback, concentrated feedback (multiple feedback messages are presented together before the takeover request is issued) and real-time feedback (the road condition messages are fed in real time based on changes in the external environment). The mediating effect of anxiety in the relationship is also examined by a within-subjects factorial simulated driving experiment (N = 41). The anxiety score was significantly lower in the real-time feedback group than in the other two groups, but the level of trust in automation was significantly higher. Furthermore, an analysis of the mediating effect showed that anxiety plays a fully mediating role in the relationship between real-time feedback and the level of trust in automation. This finding will help professionals design more trustworthy feedback strategies from a psychological perspective.

Rating the Surrounding Vehicle-to-Everything Field, Based on Channel Utilization and Information Influence

<div>Automated vehicles (AVs) can get additional information from infrastructure and other vehicles via vehicle-to-everything (V2X) communication. However, how can an AV decide if the surrounding V2X field can reliably provide qualitative, relevant, and trustworthy information? Related research analyzes V2X performance from various angles. However, not only are there identified open gaps in the analysis of loaded channels, but there has also not yet been an effort to design a lightweight metric for rating the quality of the surrounding V2X field. Hence, this work aims to close this existing performance measurement gap and develop a metric for rating the quality of the surrounding V2X field. This article first highlights the gaps identified in performance analysis before closing them with a dedicated measurement campaign. Next, it combines these findings with related research to design a straightforward V2X field rating metric. The resulting V2X field rating metric is a starting point for the AD system to decide if sensor information from the V2X field should be directly incorporated or handled with care.</div>

Evaluation of Drivers’ Mental Model, Trust, and Reliance Toward Level 2 Automated Vehicles

Level 2 automated vehicles (AVs) have been commercially available for years, yet the extent to which drivers are cognizant of their capabilities and limitations remains largely unknown. This study aimed to assess the public’s mental model of Level 2 AVs and investigate the relationships between mental model, trust, and reliance. Moreover, it sought to explore driver heterogeneity through cluster analysis to identify typical driver classes. Employing Tesla Autopilot as a representative Level 2 automation system, we designed a questionnaire measuring mental model from three dimensions: functional condition, sensorimotor preparation, and automation monitoring. This questionnaire was administered to both Tesla Autopilot owners (N = 357) and non-owners (N = 357). The results showed that, on average, drivers possessed an inadequate mental model regarding Level 2 AVs, and those with a relatively better mental model exhibited lower levels of trust and reliance. Owning a Level 2 AV did not result in a better understanding of the system, but it led to a higher trust level. Moreover, the results suggested that drivers’ trust and reliance in AVs tended to increase within the initial 6 months of usage and then kept stabilized after that. Through cluster analysis, we identified three distinct driver classes that exhibited significant differences in their mental model levels and attitudes towards AVs: Class 1 (blurred positive), Class 2 (sober neutral), and Class 3 (cautiously positive). This further validates the presence of heterogeneity among drivers. The insights gained from this study can serve as a valuable resource for supporting and guiding the development and implementation of training programs aimed at enhancing drivers’ comprehension of Level 2 AVs.

A unified longitudinal trajectory dataset for automated vehicle

Automated Vehicles (AVs) promise significant advances in transportation. Critical to these improvements is understanding AVs’ longitudinal behavior, relying heavily on real-world trajectory data. Existing open-source trajectory datasets of AV, however, often fall short in refinement, reliability, and completeness, hindering effective performance metrics analysis and model development. This study addresses these challenges by creating a Unified longitudinal trajectory dataset for AVs (Ultra-AV) to analyze their microscopic longitudinal driving behaviors. This dataset compiles data from 14 distinct sources, encompassing various AV types, test sites, and experiment scenarios. We established a three-step data processing: 1. extraction of longitudinal trajectory data, 2. general data cleaning, and 3. data-specific cleaning to obtain the longitudinal trajectory data and car-following trajectory data. The validity of the processed data is affirmed through performance evaluations across safety, mobility, stability, and sustainability, along with an analysis of the relationships between variables in car-following models. Our work not only furnishes researchers with standardized data and metrics for longitudinal AV behavior studies but also sets guidelines for data collection and model development.

Interactive strategy of shared control vehicle and automated vehicles based on adaptive non-cooperative game

Considering the complex traffic environment in the future, an interactive strategy between human-machine shared control vehicle (HSCV) and automated vehicles (AVs) based on the adaptive non-cooperative game (NCG) theory is proposed to ensure the safety of vehicles interaction control involving drivers with different characteristics. In HSCV, first, considering the environmental risk potential field (ERPF) and the human-machine conflict coefficient, an adaptive weight distribution method is designed to realize the weight distribution between a driver and an automation system. Subsequently, the steering angle command imposed by a driver is introduced into the game solving process between HSCV and AVs, enabling adaptive dynamic game through weight adjustment. During V2V interaction, based on NCG and distributed model predictive control, a motion planning controller (MOPC) is designed to integrate the optimal solution problem of path planning and tracking control and solve the interaction problem with constraints. Two typical interactive scenarios are used to verify the feasibility of the strategy. The results demonstrate that the interaction strategy considering the different drivers’ operating commands not only realizes the interaction between a driver and an ego vehicle but also realizes the interaction between an ego vehicle and nearby vehicles to ensure the safety of vehicles.

Navigating the blame game: Investigating automated vehicle fault in collisions under mixed traffic conditions

Vehicle being at fault in a crash has extensively been associated with its driver's behaviors and other human errors for human-driven vehicles (HDV). The introduction of automated vehicles (AVs) is expected to eliminate such human errors due to the ability of AVs to communicate with the external environment. However, various reports have documented AVs being at fault in collisions. This study applied text mining and mixed-effects logistic regression (MELR) on crash data involving AVs collected between 2017 and 2022 in California to explore the likelihood of an AV being at fault during a collision. It was found that among 497 crashes, a relatively small percentage (14.29 %) involved AVs being at fault. The text network results revealed patterns of keywords associated with the AVs being at fault. Such patterns include conventional mode of operation, area of impact, and resulting injuries. Furthermore, with about a 93 % prediction accuracy and an 83 % sensitivity score, the MELR results revealed that the likelihood of AVs being at fault increases when they are operated in conventional mode or when disengagement is involved. Moreover, turning, merging, or changing lane movements, unclear weather conditions, and operating on roadways with four or more lanes significantly increased the odds of an AV being at fault during a crash. Conversely, AVs were less likely to be at fault in commercial land use than residential land use, at intersection locations, and when the crash involved a truck. The practical implications of the findings are presented to improve AV operations.

Impact of Mixed-Vehicle Environment on Speed Disparity as a Measure of Safety on Horizontal Curves

Due to the transition of vehicle fleets from conventional driver-operated vehicles (DVs) to connected vehicles (CVs) and/or automated vehicles (AVs), vehicles with different technologies will soon operate on the same roads in a mixed-vehicle environment. Although a major goal of vehicle connectivity and automation is to improve traffic safety, negative safety impacts may persist in the mixed-vehicle environment. Speed disparity measures have been shown in the literature to be related to safety performance. Therefore, speed disparity measures are derived from the expected speed distributions of different vehicle technologies and are used as surrogate measures to assess the safety of mixed-vehicle environments and identify the efficacy of prospective countermeasures. This paper builds on speed models in the literature to predict the speed behavior of CVs, AVs, and DVs on horizontal curves on freeways and major arterials. The paper first proposes a methodology to determine speed disparity measures on horizontal curves without any control in terms of speed limit. The impact of speed limit or advisory speed, as a safety countermeasure, is modeled and assessed using different strategies to set the speed limit. The results indicated that the standard deviation of the speeds of all vehicles (σc) in a mixed environment would increase on arterial roads under no control compared to the case of DV-only traffic. This speed disparity can be reduced using an advisory speed as a safety countermeasure to decrease the adverse safety impacts in this environment. Moreover, it was shown that compared to the practice of a constant speed limit based on road classification, the advisory speed is more effective when it is based on the speed behavior of various vehicle types.

Investigation of Deep Learning Model for Vehicle Classification

The usage of automobiles in cities and metropolitan areas has increased drastically throughout the years and there is a need to monitor the flow of road traffic to improve the traffic congestion and safety. One of the best ways to monitor the traffic is using an artificial intelligence and machine learning. An automatic vehicle tracking system based on artificial intelligence and machine learning can offers capability to analyse the real-time traffic video data for the purpose of traffic surveillance. The computer vision is one of the subsets in machine learning that can train the computer to understand the visual data and perform specific tasks such as object detection and classification. A Vision-based system can be proposed to detect road accidents, predict traffic congestion and further road traffic analytics. This can improve the safety in transportation where it can recognize types of vehicles on the road, detecting road accidents, predicting the traffic congestion and further road traffic analytics. In the context of road traffic monitoring, the parameters of the traffic such as the type and number of vehicles that passes through must be recorded in order to gain valuable insights and make prediction such as the occurrence of traffic congestion. However, this requires reliable informative and accurate data as input for analytics. Therefore, in this research the deep learning model for vehicle classification is investigated to detect, classify types of vehicles and further predictive analytics. The vehicle classification is proposed based on Single Shot Detector (SSD) architecture model. The proposed model is tested on five different classes of vehicles with a total of 1263 images. Experimental results show that SSD model able to achieve 0.721 of precision, 0.741 of recall and 0.731 of F1 Score. Finally, the result show that the SSD model is more accurate among all the models for all the performance measure with the difference of more than 0.052 of precision, 0.706 of recall and 0.05 of F1 Score.

Investigation of Traffic System with Traffic Restriction Scheme in the Presence of Automated and Human-Driven Vehicles

In the context of transportation development, the simultaneous emergence of automated vehicles (AVs) and human-driven vehicles (HDVs) can lead to varied traffic system performance. For the purpose of improving traffic systems, this paper proposes a traffic restriction scheme only for HDVs. We develop a variational inequality (VI) model to describe travel mode and route choices under this restriction scheme and design an algorithm to solve the model. The proposed model and algorithm are applied to a Sioux Falls network example to evaluate the effects of the traffic restriction scheme. Our findings indicate that the scheme improves overall social welfare, with a higher proportion of restricted travelers leading to greater social welfare as well as increased travel demand due to changes in capacity. However, some lower exogenous monetary factors lead to negative social welfare, as the presence of AVs may exacerbate road congestion. Additionally, advancements in technology are needed to adjust the weightings of travel time and congestion level estimates to further enhance social welfare. These results offer valuable insights for traffic demand management in traffic systems with a mix of AVs and HDVs.

Automated vehicles and the urban parking paradigm: Environmental implications and Citizen preference

This study examines parking decisions in a future populated by automated vehicles (AVs), focusing on their energy implications. Using a multinomial logit model, preferences among cruising, garage parking, sending the AV home, and on-street parking in Santander, Spain, were evaluated. Home sending emerged as the favourite (52%) for its convenience, while garage parking was chosen by 36%, valued for security and environmental benefits. Cruising was least popular (6%), deterred by environmental concerns. Integrating survey data with traffic simulations, the research uncovered that cruising, despite its low preference, accounted for 16% of energy consumption due to empty trips. Surprisingly, sending AVs home, despite being the most popular, led to significant energy use, although it maintained a good consumption ratio. Garage parking, especially when located on city outskirts, was also inefficient. The study highlights the urgent need for strategies to mitigate inefficient parking behaviours, thereby enhancing the sustainability of AV-driven mobility.

Virtual Reality Study on Pedestrians’ Perceived Trust in Interactions with Automated Vehicles

This paper investigates the impact of different automated vehicle (AV) communication concepts on pedestrians' perceived trust when interacting with the AV in an urban intersection setting. For this, two virtual reality (VR) studies were conducted. The first examined the influence of vehicle automation on how pedestrians interpret driving behavior, while the second analyzed the effects of explicit communication concepts on pedestrians' perceived trust. The results show that AV driving behavior evokes similar associations as manually driven vehicles, with overall perceived trust scores not differing considerably (with driver: 4.7, without driver: 4.6). However, qualitative interviews revealed that pedestrians ultimately interpret AV behavior differently, yielding insights into the applicability of driving behavior of manually driven vehicles as a model for AV driving behavior. The second study showed an increase in pedestrians' perceived trust when vehicle-based explicit communication was present (mean: 4.9). In contrast, infrastructure-based communication showed no difference compared to implicit communication (mean: 4.6). The investigation of the influence of the traffic infrastructure (presence of traffic lights) has shown different results for implicit and explicit communication of AVs. For implicit communication, pedestrians' perceived trust increased with traffic lights (mean: 4.8) compared to scenarios without them (mean: 4.4). However, for explicit communication, the perceived trust decreased with traffic lights (vehicle-based: 4.7, infrastructure-based: 4.6) compared to scenarios without traffic lights (mean: 5.1). One reason for this is possible cognitive overload caused by the perception of multiple visual aids that are not always in the same field of view.

REVOLUTIONIZING MOBILITY: A COMPREHENSIVE EVALUATION OF THE IMPACT OF AI ON AUTOMATED VEHICLES

Automated vehicles (AVs) represent a game-changing advancement in transportation, utilizing cutting-edge technologies to travel without human intervention. These vehicles, which range from advanced driver assistance systems (ADAS) to completely autonomous versions, rely on artificial intelligence (AI) to perceive and make decisions. Recent advances in sensor technology and machine learning have improved AV capabilities, but understanding how AI responds to various distance metrics is critical for assuring safe journeys. Hypothesizing that the more the distance the car is traveling, the more AI may be able to provide a safe journey for the passengers,this study seeks to investigate the complex relationship between distance and AIs ability to ensure AV safety. Investigating the physical, geographical, and temporal characteristics of distance can help optimize AV performance and reduce safety issues.