Search

This article proposes a three-point adaptive preview steady-state compensation driver model based on articulated heavy vehicles (AHVs). Although AHVs have extremely high road transportation efficiency, they have poor driving stability and high accident risk during high-speed transportation due to their large weight, high center of mass and multi-body characteristics. However, there are few studies on intelligent driving control of AHVs. In order to improve the active safety performance of AHVs, a three-point adaptive preview driver model is designed in this article. Based on the driver model, a sliding mode steady-state compensation controller is added. The three-point adaptive preview driver is different from other driver models. Its characteristic is that the preview distance can be automatically adjusted according to the vehicle speed and road curvature. A driver model with three-point preview weighted deviation, preview time, current vehicle speed and vehicle state as input and front wheel angle as output is established. Considering the trailer state, the front wheel angle is compensated and corrected by sliding mode steady-state compensation controller. The simulation results show that the model can reasonably judge the relationship between the target path and the vehicle position, adapt to the dynamic adjustment mechanism of the preview distance, and has good tracking accuracy. The front wheel compensation angle provided by the sliding mode controller under high speed and extreme conditions can ensure that the AHVs can track the target trajectory while maintaining driving stability. [ABSTRACT FROM AUTHOR]

Real driving emissions (RDE) test procedures for type approval were initiated in Japan in 2022. In Japan, the test vehicle is driven on a test road (test course) by tracing the speed pattern prepared for each RDE test. The vehicle needs to trace the patterns in the same manner as in the conventional chassis dynamometer test. The use of a driving robot is effective for reproducibility in precisely tracing the target vehicle speed during these tests. In this study, we developed a driving robot for electrified vehicles (HEV, plug-in HEV, BEV, and FCV), which have regenerative brake-control systems. We applied a new logic to our robot that was developed in-house for conventional engine vehicles. We focused on braking deceleration of the regenerative brake control to change the operation timing from the accelerator pedal to the brake pedal. We verified the improvement of speed traceability of the driving robot installed with the proposed logic on the chassis dynamometer and test road. [ABSTRACT FROM AUTHOR]

• A four sub-model crash causation model for rear-end scenario generation is proposed. • The crash causation model considers off-road glances, low deceleration, short headway, and no reaction. • Challenges of validating scenario generation are identified and addressed. • A sample selection transform is needed for accurate validation. Safety assessment of crash and conflict avoidance systems is important for both the automotive industry and other stakeholders. One type of system that needs such an assessment is a driver monitoring system (DMS) with some intervention (e.g., warning or nudging) when the driver looks off-road for too long. Although using computer simulation to assess safety systems is becoming increasingly common, it is not yet commonly used for systems that affect driver behavior, such as DMSs. Models that generate virtual crashes, taking crash-causation mechanisms into account, are needed to assess these systems. However, few such models exist, and those that do have not been thoroughly validated on real-world data. This study aims to address this research gap by validating a rear-end crash-causation model which is based on four crash-causation mechanisms related to driver behavior: a) off-road glances, b) too-short headway, c) not braking with the maximum deceleration possible, and d) sleepiness (not reacting before the crash). The pre-crash kinematics were obtained from the German GIDAS in-depth crash database. Challenges with the validation process were identified and addressed. Most notably, a process was developed to transform the generated crashes to mimic the crash severity distribution in GIDAS. This step was necessary because GIDAS does not include property-damage-only (PDO) crashes, while the generated crashes cover the full range of severities (including low-severity crashes, of which many are PDOs). Our results indicate that the proposed model is a reasonably good crash generator. We further demonstrated that the model is a valid method for assessing DMSs in virtual simulations; it shows the safety impact of shorter 'longest' off-road glances. As expected, 'cutting away' long off-road glances substantially reduces the number of crashes that occur and reduces the average delta-v. This work highlights the need to both a) thoroughly understand the process of generating virtual scenarios and b) have the tools to validate them. While more work to develop validation processes for scenario generation is needed across all levels of crash severity, the transform and other validation tools that were developed bring us one step closer to accurate validation methodologies. [ABSTRACT FROM AUTHOR]

Our previous research showed that it is important to project a visual target on fovea centralis stably for good dynamic visual acuity while riding in a car. In this research, to enable a numerical evaluation about dynamic visual acuity in a car, we propose a new single eye movement model based on physiological knowledge about eye movement. Our eye movement model has three characteristics as follows: (i) to stabilize eye motion by feedforward controllers using head motions, (ii) to decrease a retinal slip by feedback controller using the difference between a future position of visual target and current eye position, (iii) to estimate model parameters by regression equation of variance of head rotational angular velocity. And we show effectiveness of our proposed model by validation using the comparison between numerical result and experimental result of eye movement. [ABSTRACT FROM AUTHOR]

To improve the stability and tracking accuracy of intelligent driving vehicle tracking controller, a lateral tracking control strategy based on LQR control algorithm and driver preview model is proposed, and combined with the longitudinal PID control algorithm to achieve lateral and longitudinal control. Firstly, a LQR controller with feed-forward is established, and the weight parameters of the LQR controller are optimized by gradient descent optimization algorithm. On this basis, the preview model of the driver is introduced, and an adaptive controller for preview distance based on experience is designed. Secondly, dual PID longitudinal controllers are established for velocity control. Finally, the test verification is carried out through Carsim and Matlab/Simulink joint simulation and real vehicle. The results show that the maximum lateral deviation of simulation is less than 0.035 m, the maximum heading deviation is less than 0. 09 rad, the overall trend of the planned trajectory can also be well followed under real vehicle test conditions, and the front wheel rotation angle and yaw rate change smoothly. The controller can ensure high-precision and smooth trajectory tracking, and it is more obvious at high velocity. [ABSTRACT FROM AUTHOR]

Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles. However, existing traffic psychology models of adaptive driving behavior either lack computational rigor or only address specific scenarios and/or behavioral phenomena. While models developed in the fields of machine learning and robotics can effectively learn adaptive driving behavior from data, due to their black box nature, they offer little or no explanation of the mechanisms underlying the adaptive behavior. Thus, generalizable, interpretable, computational models of adaptive human driving behavior are still rare. This paper proposes such a model based on active inference, a behavioral modeling framework originating in computational neuroscience. The model offers a principled solution to how humans trade progress against caution through policy selection based on the single mandate to minimize expected free energy. This casts goal-seeking and information-seeking (uncertainty-resolving) behavior under a single objective function, allowing the model to seamlessly resolve uncertainty as a means to obtain its goals. We apply the model in two apparently disparate driving scenarios that require managing uncertainty, (1) driving pastan occluding object and (2) visual time-sharing between driving and a secondary task, and show how human-like adaptive driving behavior emerges from the single principle of expected free energy minimization. [ABSTRACT FROM AUTHOR]

• Drivers can initiate steering to recover from a lane departure while looking off-road. • Primary corrective steering amplitudes can be modeled using a single predictor. • Drivers scale the steering amplitude to get back in lane already at first response. • Splay angles had the strongest influence on steering amplitudes in naturalistic data. • Relative yaw angle influenced the steering amplitude most in driving simulator data. Unintentional lane departures on straight roads cause many road fatalities each year. The objective of this study was to explore and model drivers' recovery steering maneuvers in unintentional drift situations, to enable the prospective safety benefit assessment of lane departure warning and avoidance systems through counterfactual simulations. The timing and amplitude of the steering adjustments drivers make to avoid lane departure were studied over three data sets with different origins, consisting of both naturalistic data and experimental data from a driving simulator study. With respect to timing, the main finding was that visually distracted drivers often initiate the corrective steering response prior to looking back towards the road, demonstrating that lane-keeping information in the visual periphery is sufficient to trigger the response. As for steering amplitude, the observed amplitudes were correlated against different lane departure risk metrics from the literature, resulting in a model capable of accounting for human behavior across all three data sets with good performance. Surprisingly, a very simple model (which describes the steering amplitude as increasing quadratically with the vehicle's orientation to the road) predicted the amplitude of the primary corrective steering adjustment better than models based on more complex lane departure risk metrics. This result indicates that drivers scale the amplitude of their steering adjustment to the steering input needed to get the vehicle back in the lane already at first response. However, it was possible to obtain a similar model fit using a more complex threshold model, with different dynamics depending on the vehicle's current orientation to the road. We discuss how these findings can be applied to models of human steering for safety benefit assessment. [ABSTRACT FROM AUTHOR]

Featured Application: The control, stability, or even safety of a vehicle can be influenced by crosswinds. The findings of the current study can be helpful for the reliable design of ground vehicles with less wind sensitivity early in their development processes. The development of lateral disturbance compensation algorithms and autonomous vehicles can also benefit from the results of the study. The general approach in the previous studies was to ignore the driver's steering contribution to a vehicle while investigating the interactions between crosswind and vehicle. Therefore, the goal of this study is to find out how steering inputs by drivers affect a heavy-ground vehicle's dynamic reaction to crosswinds. In the investigation, a two-way interaction between vehicle dynamics and aerodynamic simulations was employed. The steering inputs of drivers were modelled using a driver model taken from the previous literature that is able to reproduce the steering responses of a human driver. The study's findings demonstrated that the steering inputs made by drivers significantly impacted how the vehicle responded to crosswinds. For instance, the greatest lateral displacement of the least skilled driver (Driver 1) was around 1.53 times the greatest lateral displacement of the most skilled driver (Driver 3) at the delay time of tδ,delay = 0.5 s in the steering input. Additionally, the maximum lateral displacement results of Driver 1 and Driver 3 at tδ,delay = 1.0 s became 1.39 and 1.56 times greater than their maximum lateral displacement results at tδ,delay = 0.5 s. Similarly, the total steering inputs of Driver 1 and Driver 3 at tδ,delay = 1.0 s were 1.4 and 2.2 times greater than their total steering inputs at tδ,delay = 0.5 s, respectively. In general, the results of a driver who is more skilled than Driver 1 (Driver 2) fall in between the respective results of Driver 1 and Driver 3. On the other hand, each driver's total steering inputs at tδ,delay = 0.5 s were roughly the same as their total steering inputs at tδ,delay = 0 s. In all delay scenarios for the start of the driver's steering inputs, the drivers' steering inputs amplified the yaw moment applied to the vehicle. Meanwhile, they diminished the lateral force and roll moment. [ABSTRACT FROM AUTHOR]

This paper describes the impact of communication latency (delay) on drivability in remote driving systems, with the aim of expanding the Operational Design Domain (ODD) of remotely controllable automated driving systems. One effective way to expand the ODD is to increase vehicle speed. Understanding how delay affects vehicle behavior and determining an acceptable level of delay are important. In this paper, a driving simulator capable of controlling delay is used to perform specific tasks and correlates delay with driving ease. Through analysis of driver steering operation and yaw-rate, the relationship between driving ease and vehicle behavior is clarified. Additionally, a man-machine simulation model is defined to expand the experimental conditions and reveals the mechanism of vehicle behavior under delay conditions. Finally, the appropriate acceptable level of delay needed to achieve the desired vehicle behavior is clarified. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles. However, existing traffic psychology models of adaptive driving behavior either lack computational rigor or only address specific scenarios and/or behavioral phenomena. While models developed in the fields of machine learning and robotics can effectively learn adaptive driving behavior from data, due to their black box nature, they offer little or no explanation of the mechanisms underlying the adaptive behavior. Thus, generalizable, interpretable, computational models of adaptive human driving behavior are still rare. This paper proposes such a model based on active inference, a behavioral modeling framework originating in computational neuroscience. The model offers a principled solution to how humans trade progress against caution through policy selection based on the single mandate to minimize expected free energy. This casts goal-seeking and information-seeking (uncertainty-resolving) behavior under a single objective function, allowing the model to seamlessly resolve uncertainty as a means to obtain its goals. We apply the model in two apparently disparate driving scenarios that require managing uncertainty, (1) driving past an occluding object and (2) visual time-sharing between driving and a secondary task, and show how human-like adaptive driving behavior emerges from the single principle of expected free energy minimization.

Although the four-wheel steering system expands the flexibility of vehicle control, it also brings the problem of difficult coordination between driver comfort and vehicle stability. To this end, this paper proposes robust coordinated control for a four-wheel steering (4WS) vehicle considering driving comfort and vehicle stability. First, the vehicle dynamics model is constructed to reflect the lateral motion characteristics of a 4WS vehicle. Then, the driver model is coupled into the 4WS vehicle model to describe the driver's handling characteristics. To suppress the system perturbation caused by the uncertainties of driver behavior and vehicle states, the Takagi-Sugeno fuzzy robust control method is developed to design the human-machine co-driving system. Moreover, the robust positive invariant set theory is used to guarantee the stability and safety constraints of the vehicle. Finally, the proposed human-machine shared robust control for 4WS vehicle is verified through the driving simulator platform. The results indicate that the fuzzy robust shared control approach comprehensively improves the driving comfort, vehicle stability, and path tracking. [ABSTRACT FROM AUTHOR]

Based on the cognitive characteristics of drivers in L2-L3 level intelligent vehicles under the condition of human-vehicle co-driving, a stress steering model for drivers was established under the emergency conditions of human-vehicle co-driving intelligent vehicles. The steering characteristics of drivers in the overstressed state were reflected by the model. The degree of driver stress was characterized by the fitting relationship between steering wheel angle amplitude and steering frequency in the stress steering curve. Considering the body roll under high speed and large turning angles, a nonlinear tire model was introduced to establish three-degree-of-freedom nonlinear vehicle dynamics model. The driver stress steering model was verified by tracking the simulation of lateral acceleration. The results indicate that drivers in the state of excessive stress can cause excessive front wheel turning of vehicle. The model output results are well consistent with the actual vehicle test results, and the model can describe the driver stress steering characteristics. [ABSTRACT FROM AUTHOR]

To solve the problem of smooth switching between the car-following model and lane-changing model, the Intelligent Driver Model (IDM) for a single lane was used to study the driver's behavior switching mechanism of normally following, generating intentions to change lanes, creating space and speed gains, and performing lane change. In the case of sufficient lane-changing space and speed gains, the ego vehicle's intention to change lanes was considered to solve the switching boundary between car-following behavior and lane-changing behavior, which is also the IDM failure point. In the event that there are no lane-changing gains, the IDM was optimized by incorporating the constraint components of the target lane vehicles in conjunction with the actual motion state of the ego vehicle, and the Stepless Switching Intelligent Driver Model (SSIDM) was constructed. Drivers' natural driving information was collected, and scenario mining was performed on structured roads. On the basis of the collected data, an elliptic equation was used to fit the behavior switching boundary, and the two component balance coefficients of the front and rear vehicles on the target lane were identified. According to the test set verification results, the Mean Square Error (MSE) of the SSIDM is 2.172, which is 57.98% less than that of the conventional single-lane IDM. The SSIDM can accomplish stepless switching comparable to the driver's behavior between the car-following behavior and the lane-changing behavior, with greater precision than IDM. This research can provide theoretical support for the construction of the point-to-point driving model and the development of L2+ autonomous driving functions. It can provide assistance for the landing and application of full-behavior and full-scene autonomous driving. [ABSTRACT FROM AUTHOR]

This paper presents a novel model predictive adaptive cruise control strategy of intelligent electric vehicles based on deep reinforcement learning algorithm for driver characteristics. Firstly, the influence mechanism of factors such as inter-vehicle distance, relative speed and time headway (THW) on the driver's behavior in the process of car following is analyzed by the correlation coefficient method. Then, the driver behavior in the process of car following is learned from the natural driving data, the car following model is established by the deep deterministic policy gradient (DDPG) algorithm, and the output acceleration of the DDPG model is used as the reference trajectory of the ego vehicle's acceleration. Next, in order to reflect the driver behavior and achieve multi performance objective optimization of adaptive cruise control of intelligent electric vehicles, the model predictive controller (MPC) is designed and used for tracking the desired acceleration produced by the car following DDPG model. Finally, the performance of the proposed adaptive cruise control strategy is evaluated by the experimental tests, and the results demonstrate the effectiveness of proposed control strategy. [ABSTRACT FROM AUTHOR]

Copyright of Journal of the College Of Basic Education is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The general approach in the previous studies was to ignore the driver’s steering contribution to a vehicle while investigating the interactions between crosswind and vehicle. Therefore, the goal of this study is to find out how steering inputs by drivers affect a heavy-ground vehicle’s dynamic reaction to crosswinds. In the investigation, a two-way interaction between vehicle dynamics and aerodynamic simulations was employed. The steering inputs of drivers were modelled using a driver model taken from the previous literature that is able to reproduce the steering responses of a human driver. The study’s findings demonstrated that the steering inputs made by drivers significantly impacted how the vehicle responded to crosswinds. For instance, the greatest lateral displacement of the least skilled driver (Driver 1) was around 1.53 times the greatest lateral displacement of the most skilled driver (Driver 3) at the delay time of tδ,delay = 0.5 s in the steering input. Additionally, the maximum lateral displacement results of Driver 1 and Driver 3 at tδ,delay = 1.0 s became 1.39 and 1.56 times greater than their maximum lateral displacement results at tδ,delay = 0.5 s. Similarly, the total steering inputs of Driver 1 and Driver 3 at tδ,delay = 1.0 s were 1.4 and 2.2 times greater than their total steering inputs at tδ,delay = 0.5 s, respectively. In general, the results of a driver who is more skilled than Driver 1 (Driver 2) fall in between the respective results of Driver 1 and Driver 3. On the other hand, each driver’s total steering inputs at tδ,delay = 0.5 s were roughly the same as their total steering inputs at tδ,delay = 0 s. In all delay scenarios for the start of the driver’s steering inputs, the drivers’ steering inputs amplified the yaw moment applied to the vehicle. Meanwhile, they diminished the lateral force and roll moment.

This paper proposes a test scenario design method that reflects the longitudinal characteristics of reality for effective verification of advanced driver assistance systems (ADAS) and autonomous driving systems (ADS). Since the target systems interact with the external environment differently from the existing vehicle control system, realistic and various verification scenarios are required for verification. The proposed method consists of a vehicle model for simulating the vehicle behavior and a driver model to actively respond to the driving environment. In particular, the driver model used a model predictive control (MPC) algorithm to reflect the characteristic of human drivers. The longitudinal driving characteristics of human drivers were derived through a large-scale driving database analysis and considered in the driver model. The proposed method was compared with an existing car-following model using computer simulations. It was confirmed that its longitudinal driving behavior is similar to that of human drivers and that various scenarios can be designed by changing the model parameters. [ABSTRACT FROM AUTHOR]

Our objectives were to assess the efficacy of active inference models for capturing driver takeovers from automated vehicles and to evaluate the links between model parameters and self-reported cognitive fatigue, trust, and situation awareness.Control transitions between human drivers and automation pose a substantial safety and performance risk. Models of driver behavior that predict these transitions from data are a critical tool for designing safer, human-centered, systems but current models do not sufficiently account for human factors. Active inference theory is a promising approach to integrate human factors because of its grounding in cognition and translation to a quantitative modeling framework.We used data from a driving simulation to develop an active inference model of takeover performance. After validating the model’s predictions, we used Bayesian regression with a spike and slab prior to assess substantial correlations between model parameters and self-reported trust, situation awareness, fatigue, and demographic factors.The model accurately captured driving takeover times. The regression results showed that increases in cognitive fatigue were associated with increased uncertainty about the need to takeover, attributable to mapping observations to environmental states. Higher situation awareness was correlated with a more precise understanding of the environment and state transitions. Higher trust was associated with increased variance in environmental conditions associated with environmental states.The results align with prior theory on trust and active inference and provide a critical connection between complex driver states and interpretable model parameters.The active inference framework can be used in the testing and validation of automated vehicle technology to calibrate design parameters to ensure safety. [ABSTRACT FROM AUTHOR]

Driver models are crucial for the safety assessment of autonomous vehicles (AVs) because of their role as reference models. Specifically, an AV is expected to achieve at least the same level of safety performance as a careful and competent driver model. To make this comparison possible, quantitative modeling of careful and competent driver models is essential. Thus, the UNECE Regulation No. 157 proposes two driver models as benchmarks for AVs, enabling safety assessment of AV longitudinal behaviors. However, these two driver models are unable to be applied in non-car-following scenarios, limiting their applications in scenarios such as highway merging. To this end, we propose a careful and competent driver model for highway merging (CCDM2) scenarios using interpretable reinforcement learning-based decision-making and safety constraint control. We compare our model's safe driving capabilities with human drivers in challenging merging scenarios and demonstrate the "careful" and "competent" characteristics of our model while ensuring its interpretability. The results indicate the model's capability to handle merging scenarios with even better safety performance than human drivers. This model is of great value for AV safety assessment in merging scenarios and contributes to future reference driver models to be included in AV safety regulations. • We designed a reference driver model by integrating Monte Carlo Tree Search with model predictive control. • We identified challenging highway merging scenarios in a dataset. • We demonstrated that our model is risk-aware, capability-dominant and interpretable. • Our model outperforms the bare model and even human drivers in some scenarios. [ABSTRACT FROM AUTHOR]

Although the four-wheel steering system expands the flexibility of vehicle control, it also brings the problem of difficult coordination between driver comfort and vehicle stability. To this end, this paper proposes robust coordinated control for a four-wheel steering (4WS) vehicle considering driving comfort and vehicle stability. First, the vehicle dynamics model is constructed to reflect the lateral motion characteristics of a 4WS vehicle. Then, the driver model is coupled into the 4WS vehicle model to describe the driver’s handling characteristics. To suppress the system perturbation caused by the uncertainties of driver behavior and vehicle states, the Takagi-Sugeno fuzzy robust control method is developed to design the human-machine co-driving system. Moreover, the robust positive invariant set theory is used to guarantee the stability and safety constraints of the vehicle. Finally, the proposed human-machine shared robust control for 4WS vehicle is verified through the driving simulator platform. The results indicate that the fuzzy robust shared control approach comprehensively improves the driving comfort, vehicle stability, and path tracking.

To solve the problem of smooth switching between the car-following model and lane-changing model, the Intelligent Driver Model (IDM) for a single lane was used to study the driver’s behavior switching mechanism of normally following, generating intentions to change lanes, creating space and speed gains, and performing lane change. In the case of sufficient lane-changing space and speed gains, the ego vehicle’s intention to change lanes was considered to solve the switching boundary between car-following behavior and lane-changing behavior, which is also the IDM failure point. In the event that there are no lane-changing gains, the IDM was optimized by incorporating the constraint components of the target lane vehicles in conjunction with the actual motion state of the ego vehicle, and the Stepless Switching Intelligent Driver Model (SSIDM) was constructed. Drivers’ natural driving information was collected, and scenario mining was performed on structured roads. On the basis of the collected data, an elliptic equation was used to fit the behavior switching boundary, and the two component balance coefficients of the front and rear vehicles on the target lane were identified. According to the test set verification results, the Mean Square Error (MSE) of the SSIDM is 2.172, which is 57.98% less than that of the conventional single-lane IDM. The SSIDM can accomplish stepless switching comparable to the driver’s behavior between the car-following behavior and the lane-changing behavior, with greater precision than IDM. This research can provide theoretical support for the construction of the point-to-point driving model and the development of L2+ autonomous driving functions. It can provide assistance for the landing and application of full-behavior and full-scene autonomous driving.

The objective of this paper is to propose a methodology to estimate nationwide traffic safety impacts of automated vehicle technologies using multi-agent traffic simulations. The influence of three levels of driver trust in the automation system (appropriate, over trust, distrust) is considered in the simulation and takes different transition modes of control between the driver and the system into account. The nationwide estimation of crashes is obtained by projecting results of the simulations using traffic data for three different and representative municipalities. Results indicated that Automated Driving Systems and Advanced Driver Assistance Systems significantly reduced the number of casualties and fatalities compared to manual driving. Simulation results in consideration of the influence of driver trust also found that this reduction may be negatively affected by over- and under-trust parameters. However, even with the introduction of these parameters, the reduction rate was still significant compared to manual driving. The proposed methodology using multi-agent traffic simulations may thus address concerns surrounding the deployment of automated driving systems which is a feature not found in conventional simulations, provide useful insight for interested parties to develop research and policy making strategies that accelerate traffic safety improvements, and to support social acceptance efforts.

In recent years, automatic driving and advanced driving support systems have become more widespread; however, control systems do not consider the driving characteristics of each driver. This study constructed a personalized driver model for following forward vehicles on highways using LSTM (Long Short-Term Memory). In particular, the setting parameters for training with LSTM was focused upon and consequently, the relationship between the setting parameters and model accuracy was evaluated. The LSTM parameters considered were the number of hidden units, learning rate, number of epochs, and number of LSTM layers. Further, the driving data were measured using a driving simulator. Moreover, the model was evaluated in terms of accuracy using the coefficient of determination, and 125 combinations of parameters were compared using the mean value of the coefficient of determination and its significant difference. The order of parameter comparisons was performed considering the accuracy and learning time of the model. Consequently, the parameter set that is likely to allow efficient building of a highly accurate driver model was determined. Applying the parameter evaluation in this study contributes to the development of personalized driver models with high accuracy.

This paper proposes a driver preview-based path-following controller to control both the lateral and longitudinal movements of a vehicle. First, a lateral tracking controller with two preview points is established by considering the displacement and heading errors of the two preview points: the far point, determined by the vehicle speed and fixed preview time, and the near point located at the center of the front axle. Depending on different parameters of the road input, the steering wheel angle is calculated, and different weights are assigned to the steering wheel angles corresponding to different road inputs. Next, a longitudinal tracking controller is established, which controls the vehicle velocity based on the road information of the far point. The control objects are the brake and accelerator pedals. Subsequently, the coupling of the lateral and longitudinal motion of the vehicle is analyzed, and an integrated longitudinal and lateral tracking controller is established. To verify the performance of the controller, the controller and vehicle model are established in Simulink and CarSim, respectively, to enable joint simulation. It is observed that the coupling is solved, and the near-point control makes the tracking error converge to zero and enhances the control effect. It demonstrates high adaptability and control accuracy of the proposed controller. [ABSTRACT FROM AUTHOR]

A human predictive characteristic may affect the traffic accident factors such as prediction failure and carelessness to other movements. In this paper, we propose a new approach to simulate how human vision predicts the driving environment during driving, and to clarify cognitive mechanisms, using deep neural networks that incorporate predictive coding, which is one of the leading theories as the operating principle of the cerebral cortex. Predictive coding assumes that the brain's internal models predict the visual world at all times and that errors between the prediction and the actual sensory input further refine the internal models. [ABSTRACT FROM AUTHOR]

Accurately recognizing braking intensity levels (BIL) of drivers is important for guaranteeing the safety and avoiding traffic accidents in intelligent transportation systems. In this article, an instance-level transfer learning framework is proposed to recognize BIL for a new driver with insufficient driving data by combining the Gaussian mixture model (GMM) and the importance-weighted least-squares probabilistic classifier (IWLSPC). By considering the statistic distribution, GMM is applied to cluster the data of braking behaviors into three levels with different intensities. With the density ratio calculated by unconstrained least-squares importance fitting, the least-squares probabilistic classifier is modified as IWLSPC to transfer the knowledge from one driver to another and recognize BIL for a new driver with insufficient driving data. Comparative experiments with nontransfer methods indicate that the proposed framework obtains a higher accuracy in recognizing BIL in the car-following scenario, especially when sufficient data are not available. [ABSTRACT FROM AUTHOR]

Most existing driver models focus on predicting driving performance in normal and near-collision situations without considering the impact of collision warning parameters on driver behavior. This study develops a cognitive computational driver model based on the Queueing Network-Model Human Processor (QN-MHP) to quantify the effects of key warning parameters (i.e., warning lead time, warning reliability, and speech warning style) on driver performance in warning responses, in connected vehicle systems (CVSs). The model was validated by comparing its predictions of driver response time, response type, and braking and steering performance with data from thirty-two drivers collected in an experimental study. Once the route choice mechanism had been implemented, the driver model was found to explain the cognitive mechanism underlying how drivers process warnings in CVSs. Indeed, the validation results showed that the model was able to capture major changes in patterns of the experimental data, with R-squared values of 0.88 for warning response time, 0.69 and 0.65 for decision making in response type for the initial trial and across trials, 0.85 for braking performance, and 0.83 for steering performance. The model can be applied to optimize the interface design of CVSs based on driver needs. [ABSTRACT FROM AUTHOR]

The current commercial intelligent driving systems still take the optimal strategy judged by the machine to be the only goal. Therefore, in order to improve the driving experience of the intelligent driving following scene, based on the assumption that environmental factors remain unchanged for a short time, five important parameters affecting the following scene are selected through correlation analysis, and vehicle-following research is carried out. This paper adopts a driver-following model based on a Genetic Algorithm (GA)-optimized Back Propagation (BP) neural network. Based on the data of next-generation simulation (ngsim), this paper selects vehicle 32 (32 represents the ID of the vehicle in the ngsim project) as the main vehicle in order to study short-term driving habits. A BP neural network is built using MATLAB; 60% of the data of vehicles 32 and 29 is used for the training set, 20% is used for the verification set, and 20% for the test set. Because short-term prediction requires high timeliness, the genetic algorithm is used to optimize the initial weights of the neural network, which not only accelerates the convergence speed but also plays a role in avoiding the local optimal solution. The experimental results show that compared with the traditional stimulus-response vehicle-following model, this model has a following ability that is more in line with the driver's driving habits in terms of ensuring following safety. [ABSTRACT FROM AUTHOR]

Safety is a critical aspect of traffic systems. However, traditional crash data-based methods suffer from scalability and generalization issues. Although SSMs offer a proactive alternative for safety evaluation, their validation in simulated settings remains inconsistent, especially with emerging mobility technologies like autonomous driving. Our study critiques existing methodologies in SSM validation and introduces a novel framework integrating micro-level driver models with macro-level traffic states. This approach accounts for diverse external factors, including weather and geographical variations. Utilizing the Caltrans Performance Measurement System (PeMS) data, we conduct a large-scale analysis, merging traffic simulation with real-world data to extract SSMs and correlate them with crash statistics. Our results indicate a significant correlation between SSM counts and crash numbers but no clear trend with varying SSM thresholds. This suggests limitations in current public data for establishing robust links between simulated SSMs and real-world crashes. Our study highlights the need for improved data collection and simulation techniques, paving the way for more accurate and meaningful roadway safety analysis in the era of advanced mobility systems., Competing Interests: Declaration of competing interest none, (Copyright © 2024. Published by Elsevier Ltd.)

To improve the stability and tracking accuracy of intelligent driving vehicle tracking controller, a lateral tracking control strategy based on LQR control algorithm and driver preview model is proposed, and combined with the longitudinal PID control algorithm to achieve lateral and longitudinal control. Firstly, a LQR controller with feed-forward is established, and the weight parameters of the LQR controller are optimized by gradient descent optimization algorithm. On this basis, the preview model of the driver is introduced, and an adaptive controller for preview distance based on experience is designed. Secondly, dual PID longitudinal controllers are established for velocity control. Finally, the test verification is carried out through Carsim and Matlab/Simulink joint simulation and real vehicle. The results show that the maximum lateral deviation of simulation is less than 0.035 m, the maximum heading deviation is less than 0. 09 rad, the overall trend of the planned trajectory can also be well followed under real vehicle test conditions, and the front wheel rotation angle and yaw rate change smoothly. The controller can ensure high-precision and smooth trajectory tracking, and it is more obvious at high velocity. [ABSTRACT FROM AUTHOR]

This paper presents a method to design an integrated path tracking and lateral stability controller for an autonomous electric vehicle with four-wheel independent steering (4WIS) on low friction roads. Recent advances in autonomous driving have led to extensive studies on path tracking control. However, path tracking is difficult on low friction roads. In this paper, path tracking control was converted to the yaw rate tracking one to cope with problems caused by low friction roads. To generate a reference yaw rate for path tracking, we present several methods using a driver model and a target path. For yaw rate tracking, we designed a controller with a two-layer control hierarchy, i.e., upper and lower layers. The control yaw moment was calculated using a direct yaw moment controller in the upper layer. In the low layer, a control allocation method was adopted to allocate the control yaw moment into steering angles of 4WIS. To verify the performance of the proposed controller, we conducted a simulation on vehicle simulation software. From the simulation results, it is shown that the proposed controller is effective for path tracking and lateral stability on low friction roads. To analyze path tracking and lateral stability performance of the proposed controller on low friction roads, the effects of the steady-state yaw rate gain are investigated from the simulation results. [ABSTRACT FROM AUTHOR]

Advanced driving assistance systems (ADAS) such as adaptive cruise control (ACC), traffic jam assistance, and collision warning have been developed to enhance driving comfort and reduce the driving burden in car-following situations. Although these systems provide automated driving to ensure safety, those do not harmonize the intentions of the driver by reflecting individual drivers' characteristics. To ensure that system reflects driver intention, we propose a personalized longitudinal speed planning algorithm in car-following situations, which system mimics personal driving styles. Individual driving styles were characterized by designing a pedal behavior prediction model and time headway distribution prediction model. The pedal behavior prediction model is an ensemble tree-based classifier that estimates the driver's current driving state, i.e., accelerating, cruising, or braking. Then, the driver-specific time headway distribution is estimated based on the polynomial model. These two prediction models were applied to the existing sampling-based speed planning algorithm and implemented with MATLAB/Simulink. The entire speed planning algorithm was simulated using vehicle simulation software. The simulation results showed that the actual driver's driving style was successfully reproduced. [ABSTRACT FROM AUTHOR]

The uncertainty of driver behavior is an important factor affecting the safety of human–machine co-driving vehicles. Traditional rule-based models often fail to capture the nonlinear and complex characteristics of human steering behavior. To overcome this, we propose a data network-driven approach utilizing gated recurrent unit (GRU) neural networks to accurately predict driver steering behavior. The GRU-based driver model is integrated with vehicle dynamics to construct a control-oriented driver–vehicle model. Considering that human–machine conflict may cause vehicle instability, an exponential function combining proportional–integral–derivative is proposed to quantify the human–machine conflict level based on steering difference. To reasonably allocate human–computer permissions based on human–machine interaction, a hierarchical authority allocation framework is proposed. The upper layer provides a reference authority allocation via an exponential function, while the lower layer employs a real-time model predictive control (MPC) optimizer to track this reference, ensuring optimal vehicle path tracking and stability. The proposed system's effectiveness is validated through driver-in-the-loop testing, demonstrating significant improvements in safety and performance. The results show that in the human–machine conflict scenario, the proposed authority allocation strategy can still ensure the path tracking and safety of the vehicle. [ABSTRACT FROM AUTHOR]

An eight-degree-of-freedom vehicle dynamic model with electromechanical coupling was established for a four-wheel-independent-drive electric vehicle (4WID-EV). Based on the single-point preview optimal curvature theory, an adaptive fuzzy PID driver model with lateral acceleration feedback was designed, and the control of vehicle trajectory tracking was achieved in the driver-vehicle-road closed-loop coupling model. With the sideslip angle and yaw rate as control variables, the upper layer of a fuzzy sliding mode controller and the lower layer of an optimal distribution controller of the yaw moment were designed. The optimal longitudinal forces of four driving wheels were determined to achieve vehicle-handling stability. J-turn, fishhook, and snake-shaped pile simulations were carried out in MATLAB/Simulink. The results showed that the fuzzy sliding mode controller significantly improved the driving stability of the system, and it had a better anti-chattering ability than the sliding mode control strategy. The established lateral acceleration feedback adaptive fuzzy PID driver model had good trajectory tracking ability. Integration of the two controllers can better achieve both trajectory tracking and driving stability of a 4WID-EV. [ABSTRACT FROM AUTHOR]

This paper aims to find a mathematical justification for the non-linear steady state steering haptic response as a function of driver arm posture. Experiments show that different arm postures, that is, same hands location on the steering wheel but at different initial steering angles, result in a change in maximum driver arm stiffness. This implies the need for different steering torque response as a function of steering angle, which is under investigation. A quasi-static musculoskeletal driver model considering elbow and shoulder joints is developed for posture analysis. The torque acting in the shoulder joint is higher than in the elbow. The relationship between the joint torque and joint angle is linear in the shoulder, whereas the non-linearity occurs in the elbow joint. The simulation results qualitatively indicate a similar pattern as compared to the experimental muscle activity results. Due to increasing muscle non-linearity at high steering angles, the arm stiffness decreases and then the hypothesis suggests that the effective steering stiffness is intentionally reduced for a consistent on-center haptic response.

In order to improve the adaptability and tracking performance of intelligent vehicles under complex driving conditions, and simulate the manipulation characteristics of the real driver in the driver–vehicle–road closed-loop system, a kind of adaptive preview time model for intelligent vehicle driver model is proposed. This article builds the intelligent vehicle driver model based on optimal preview control theory and the basic preview time is identified to minimize path error under various conditions based on particle swarm optimization. Then, the ideal compensation preview time is constructed in various conditions and the appropriate factors affecting compensation preview time are filtered out according to correlation analysis. Moreover, the architecture and training procedure of deep network is specified for compensation preview time prediction. Finally, the adaptive preview time is modeled by combining the basic preview time with the compensation preview time and the validity of adaptive preview time model is verified by the driver–vehicle–road closed-loop system under normal and aggressive driving conditions. The results show that the proposed adaptive preview time model can help intelligent vehicles better adapt complex driving conditions and effectively improve the path-following performance. [ABSTRACT FROM AUTHOR]

Abstract Current research on lane-keeping systems ignores the effect of the driver and external resistance on the accuracy of tracking the lane centerline. To reduce the lateral deviation of the vehicle, a lane-keeping control method based on the fuzzy Takagi-Sugeno (T-S) model is proposed. The method adopts a driver model based on near and far visual angles, and a driver-road-vehicle closed-loop model based on longitudinal nonlinear velocity variation, obtaining the expected assist torque with a robust H∞ controller which is designed based on parallel distributed compensation and linear matrix inequality. Considering the external influences of tire adhesion and aligning torque when the vehicle is steering, a feedforward compensation control is designed. The electric power steering system is adopted as the actuator for lane-keeping, and active steering redressing is realized by a control motor. Simulation results based on Carsim/Simulink and real vehicle test results demonstrate that the method helps to maintain the vehicle in the lane centerline and ensures driving safety.