Testing cloud-controlled intelligent connected vehicles (ICVs) requires simulation environments that faithfully emulate both vehicle behavior and realistic communication latencies. This paper proposes a latency-aware co-simulation platform integrating CarMaker and Vissim to evaluate safety and comfort under real-world vehicle-to-cloud (V2C) latency conditions. Three communication latency models, derived from empirical 5G measurements in China and Hungary, are incorporated and statistically modeled using Gamma distributions. A proactive conflict module (PCM) is proposed to dynamically control background vehicles and generate safety-critical scenarios. The platform is validated through experiments involving an exemplary system under test (SUT) across eight testing conditions combining two PCM modes (enabled/disabled) and four latency conditions (none, China, Hungary, abnormal). Safety and comfort are assessed using metrics including collision rate, distance headway, post-encroachment time, and the spectral characteristics of longitudinal acceleration. Results show that the PCM effectively increases driving environment criticality, while V2C latency reduces ride comfort and, under extreme driving conditions, further aggravates safety-critical scenarios. These findings confirm the platform’s effectiveness in systematically evaluating cloud-controlled ICVs under diverse testing conditions.

Deep Reinforcement Learning (DRL) is becoming a prominent method for autonomous driving due to its strong capability to generate complex driving policy. However, DRL motion planning still has limitations in safety performance including learning quality, convergence speed and the safety guarantee. To this end, this work proposes a safety-enhanced deep reinforcement learning method with dynamic safety guidance (DSG-DRL) for lane-change motion planning. It bears the following key features: 1) Able to learn a safer DRL driving policy by additionally including potentially unsafe behaviors; 2) Able to accelerate learning a safe policy by making dangerous driving experiences impressive; 3) Able to further enhance the driving safety by avoiding unexpected reckless action. The proposed DSG-DRL motion planner dares to make mistakes to learn the safe driving policy better and faster. By evaluating anticipated risk, it learns not only from the maneuvers right at the moments of collisions, but also from the dangerous maneuvers leading towards collisions. Besides, risk driving experiences are enhanced with additional memory batches and sampling prioritization. Moreover, reckless actions can be prevented by dynamic constraints both in training and testing, which further improves the safety performance. Simulation validation shows that the proposed method can learn a safer driving policy with faster convergence speed, achieving the high safety performance while keeping the driving efficiency.

D object detection plays a critical role in advancing autonomous driving technology. To improve perception capabilities while maintaining low costs and ensuring performance in adverse weather conditions, 4D radar has emerged as a promising alternative for 3D object detection. However, current methods fail to fully exploit raw data and density information of 4 D radar point clouds to tackle challenges like sparse data and noise. To address these limitations and make use of the unique Doppler velocity information provided by 4D radar, we propose a novel approach called 4DRadDet, which uses cross-attention fusion with cluster-queried techniques for 3D object detection. The 4DRadDet model uses a specially designed incremental clustering method to cluster potential object point clouds, reducing measurement errors from limited radar angular resolution and signal multipath effects. The cross-attention feature fusion (CAFF) module enhances network performance by querying the clustered point cloud feature map, allowing the network to leverage reliable prior information from the clustered point cloud to better detect potential objects. Our experimental evaluations on the View-of-Delft (VoD) dataset demonstrate the effectiveness of 4DRadDet, showcasing state-of-the-art performance. Specifically, 4DRadDet achieves a 3D mean average precision ($\text{mAP}_{3 \mathrm{D}}$) of 51.44 % and a bird'seye view mean average precision ($\mathbf{m A P}_{\text {BEV }}$) of$\mathbf{5 7. 0 7 \%}$. Our proposed method demonstrates impressive inference times and achieves real-time detection capabilities.

Demand Responsive Transit (DRT) emerges as one of the most promising public transit operating patterns, which operates without fixed stations or routes, aiming to provide flexible and passenger-oriented services. However, the current DRT dispatching hardly achieves a balance between the operating costs and service flexibility, leading to a high failure rate of DRT operation. To address this issue, this research proposes a dispatching method for DRT with passengers’ hidden preference exploitation capability. The proposed DRT dispatching method overcomes the imbalance shortcomings of conventional method and bears the following features: 1) With the capability of exploiting the passengers’ hidden preference; 2) With the capability of making the most of the passengers’ room for compromise. To evaluate the proposed dispatching method, a numerical experiment compared with conventional DRT dispatching model is conducted, and sensitivity analysis is performed for passenger satisfaction level threshold. The evaluation results show that with the capability of exploiting the passengers’ hidden preference, the proposed DRT dispatching method is able to improve the average travel time by 27.8%~47.5% and reduce the average waiting time by 26.4%~47.4%; via making the most of the passengers’ room for compromise, the proposed DRT dispatching method is able to enhance the passenger average satisfaction by 65.3%~85.7%. The benefit range is caused by different values of passenger satisfaction level threshold.

Cooperative Adaptive Cruise Control (CACC) often requires human takeover for tasks such as exiting a freeway. Direct human takeover can pose significant risks, especially given the close-following strategy employed by CACC, which might cause drivers to feel unsafe and execute hard braking, potentially leading to collisions. This research aims to develop a CACC takeover controller that ensures a smooth transition from automated to human control. The proposed CACC takeover maneuver employs an indirect human-machine shared control approach, modeled as a Stackelberg competition where the machine acts as the leader and the human as the follower. The machine guides the human to respond in a manner that aligns with the machine’s expectations, aiding in maintaining following stability. Additionally, the human reaction function is integrated into the machine’s predictive control system, moving beyond a simple “prediction-planning” pipeline to enhance planning optimality. The controller has been verified to 1) enable a smooth takeover maneuver of CACC; 2) ensure string stability in the condition that the platoon has less than 6 CAVs and human control authority is less than 40%; 3) enhance both perceived and actual safety through machine interventions; and 4) reduce the impact on upstream traffic by up to 60%.

Controller models are crucial in maintaining stability, safety, and efficiency in dynamic systems. Adaptive Cruise Control (ACC), a common feature in modern vehicles, adjusts the vehicle’s speed to maintain a safe following distance from the preceding vehicle. This paper presents a new approach to designing an ACC controller, utilizing a Model Predictive Control (MPC) to obtain multiple objectives. The model is tested on the one hand with co-simulation between IPG CarMarker (i.e., a high-fidelity vehicle dynamics and testing software) and Matlab/Simulink on a Model-in-the-Loop (MiL) Level and on the other hand on a Hardware-in-the-Loop (HiL) to prove the real-time capability of the controller. The results show the performance of the MPC controller and the gap between MiL and HiL in the case the target car cuts in the lane of the ego car and the ego car approaches the target car.

The advent of Large Language Models (LLM) provides new insights to validate Automated Driving Systems (ADS). In the herein-introduced work, a novel approach to extracting scenarios from naturalistic driving datasets is presented. A framework called Chat2Scenario is proposed leveraging the advanced Natural Language Processing (NLP) capabilities of LLM to understand and identify different driving scenarios. By inputting descriptive texts of driving conditions and specifying the criticality metric thresholds, the framework efficiently searches for desired scenarios and converts them into ASAM OpenSCENARIO1and IPG CarMaker text files2. This methodology streamlines the scenario extraction process and enhances efficiency. Simulations are executed to validate the efficiency of the approach. The framework is presented based on a user-friendly web app and is accessible via the following link: https://github.com/ftgTUGraz/Chat2Scenario.

As the driving is shifting towards automation, the maximization of related benefits would profit from improved user acceptance of the new technology. Studies suggest a strong connection between acceptance and trust in technical solutions. We investigate the improvement of user trust to driving automation through demonstrations carried out in a sophisticated driving simulator. The study correlates subjective data with objective psychophysiological measurements. The multi-factorial and multivariate analysis of variance investigates the influence of learning effects and pre-experience with advanced driver assistance systems on trust. Results show improvement in trust through user interaction with a human-machine interface of the demonstrated AD system, hence illustrating the relevance of human-centered development processes. The conclusion is supported by the observation of driver cardiac signals.

Considering the recent advances in autonomous driving technology, conventional on-road based testing tools cannot meet the validation requirements with respect to time and cost-efficiency. Scenario-based virtual validation methods offer an efficient virtual testing approach that supports the development and contribute to decreased on-road-testing. X- in-the loop testing methods contribute to stepwise increase in test/validation quality by introducing hardware/software elements starting from the component up to full vehicle level and have been increasingly integrated into the process of design and validation of intelligent vehicle systems. In this paper, a novel framework that includes a highly dynamic vehicle-in-the-loop test bed, a traffic flow simulation method is introduced to precisely assess the impact of specific variables on the performance of an intelligent system with all vehicle components included.

State of the art motion cueing algorithms aim at reproducing a simulated vehicle's motion at maximum accuracy, while respecting the motion constraints of a cueing platform. The consideration of human sensory characteristics for motion perception allows to artificially increase this envelope. Model predictive control based approaches penalize motion deviation for each perception channel and consequently minimize every error individually. However, no effort is made to balance motion cues across different degrees of freedom. In the motorsport environment it is essential to replicate vehicle characteristics precisely and consistently. The latter is of particular interest, as an inconsistent replication of cues could easily cause a perceived change of vehicle characteristics for a professional race car driver. In consequence, the motion cues should generally retain specific characteristics of the vehicle reference. A minimization of each tracking error individually does not meet this requirement which is demonstrated in this work. To overcome this limitation, two novel cost functions for a model predictive control based motion cueing algorithm are introduced which reduce the deviation of visual-vestibular incongruences. Across three degrees of freedom a reduction of up to 33 % is achieved while scaling errors and translational workspace utilization are retained at a similar level.

A well-established Lane Keeping Assist System (LKAS) plays an important role in the field of Automated Driving (AD). An essential issue in LKAS and generally in Advanced Driving Assist Systems (ADAS) is lane detection. Due to the fact that camera systems are inexpensive, most lane detection methods are vision based. To cope with the infinite number of test cases, virtual testing of ADAS has become state of the art. Realistic behavior and analytical models of ADAS components are crucial for reliable simulation results. The focus of this study is performance validation of LKAS applying simulation. High complexity as well as sensitivity to illumination variation, shadows and different weather conditions make it difficult to implement and develop camera or environment models which could map the realistic behavior of LKAS. To avoid these complexities and minimize the modelling efforts, a phenomenological lane detection model (PLDM) is introduced. For that purpose, comprehensive measurements are carried out within the Austrian Light Vehicle Proving Region for Automated Driving (ALP.Lab) using a test vehicle equipped with LKAS. Applying proposed phenomenological model provides the ability to test any LKAS regardless of its controller. The PLDM is implemented and validated with the recorded data in the simulation environment of IPG CarMaker. The results show realistic system performance of the developed and implemented LKAS system.

Reduced alertness due to the drowsy state that impairs driving performance has been reported to be one of the significant causes of road accidents. This paper aims to present a data fusion of vehicle-based and ECG signals for classifying three levels of driver drowsiness, including alert, moderately drowsy, and extremely drowsy. Lateral deviation from the road centerline, steering wheel angle, and lateral acceleration are employed as vehicle-based signals. Two ECG leads are also exploited to collect heart rate variability of drivers. Thirty-nine features from vehicle-based data and ten features from heart rate variability signals are extracted. Finally, k-nearest neighbors and random forest are used as classifiers to classify the level of drowsiness using selected features by the sequential feature selector. Age and gender, as the two most effective human factors, are considered to assess the performance of the method in different age/gender groups. The proposed method is evaluated on experimental data that were collected from 93 manual driving tests using 47 different human volunteers in a driving simulator. Results show that hyperparameter-optimized random forests obtain an accuracy of 82.8% for the detection of drowsiness levels based on vehicle signals only, and an accuracy of 88.5% based on ECG derived data only. Data fusion of ECG signals and vehicle data improves the accuracy of classification to 91.2%. The model performs slightly better on older than on younger drivers, but no gender difference was found.

Automated vehicles require information on the current road condition, i.e. the tire-road friction coefficient (μmax) for trajectory planning and braking or steering interventions. Recursive Total Least Squares (RTLS) is used to estimate μmaxonly utilizing the information from Electric Power System (EPS) and other sensors installed in production vehicles. A new state αf/μmax(front wheel slip angle divided by μmax) is introduced which is observed by a proposed nonlinear observer. This state serves as a measurement for friction estimation and judge when the estimation result is reliable. The proposed method is verified in IPG CarMaker.