Graph-based encoding of curve driving using spatial keypoints

The increasing use of bicycles highlights the need for enhanced road safety measures, particularly in interactions between vehicles and cyclists on rural mixed‐traffic roads. This study investigates the impact of driver age and behavior on the effectiveness of advanced driver assistance systems (ADASs) in improving cyclist safety. Utilizing a driving simulator, the study analyzed the overtaking maneuvers of 300 male participants, categorized by aggressive and passive driving styles, across three age groups: young (20–34), middle‐aged (35–49), and older (50–64) drivers. Results showed that younger drivers exhibited more dynamic and erratic behaviors, with significant variations in lateral control (LC) and time to danger (TTD). Specifically, younger driver’s TTD increased by 20% on average, while older drivers maintained consistent caution with a 10% improvement in LC. Aggressive drivers showed a negligible change in behavior, whereas passive drivers demonstrated a 25% improvement in TTD and a 15% enhancement in LC when using ADAS. The findings suggest that tailored ADAS features are necessary to address the diverse responses of different driver demographics. Future ADAS development should incorporate real‐world testing, consider psychological factors, and conduct longitudinal studies to optimize safety outcomes. This study provides critical insights for enhancing the design and implementation of ADAS to protect vulnerable road users such as cyclists.

Exploratory analysis of injury severity under different levels of driving automation (SAE Levels 2 and 4) using multi-source data

What’s in a name? Drivers’ perceptions of the use of five SAE Level 2 driving automation systems

This paper presents a modified lateral control method for an autonomous vehicle with both look-ahead and look-down sensing systems. To cope with sensor noise and modeling uncertainty in the lateral control of the vehicle, a modified LMI-based H lateral controller was proposed, which uses the look-ahead information of the lateral offset error measured at the front of vehicle and the look-down information of the vehicle yaw angle error between the reference lane and the centerline of the vehicle. To verify the safety and the performance of the lateral control, a scaled-down vehicle was developed, and the positioning of the vehicle was estimated with USAT. The proposed controller, which uses both look-ahead and look-down information, was tested for lane changing and reference lane tracking with both simulation and experiment. The simulation and experimental results show that the proposed controller has better tracking and handling performance compared with a controller that uses only the look-ahead information of the target heading angle error.

Advanced driver assistance systems (ADAS) are developed to increase safety and provide a more efficient and comfortable experience when traveling by car. ADAS are reliant upon sensors to provide the intended assistance for the driver, and the driver is reliant upon an HMI interface to interact with the feature at hand. A prototype ADAS, including a human machine interface (HMI) and enhanced ADAS functionality, was developed and then evaluated on proving ground. The purpose of the study was to evaluate how the enhanced ADAS performed as compared to baseline in terms of trust, acceptance, efficiency, and perceived situation awareness. The evaluation of the full prototype was conducted with 24 participants (13 men and 11 women) who drove a Lincoln MKZ equipped with longitudinal and lateral ADAS support (SAE Level 2) at the AstaZero proving ground facilities in Sweden. In total the participants drove four laps (familiarization lap, baseline lap, gaze-related functionality lap, active ADAS functionality lap) on the proving ground. The gaze-related functionalities tracked the gaze to assure blind spot gaze and correct turning gaze behavior and provided support for this. The active ADAS functionalities included that the system was able to override the time gap setting of the longitudinal control system to provide the driver with more time to react as the feature was triggered in the presence of driver distraction, as well as a system that alerted the driver about upcoming situations in which the longitudinal and lateral assist systems were unable to support the driver due to exceeding of the operational design domain (ODD). Gaze-related functionalities were associated with a significant increase in usefulness and satisfaction compared to baseline, and active ADAS functionalities were associated with a significant increase in satisfaction compared to baseline.

The robust detection of road boundaries is a prerequisite for Advanced Driver Assistant Systems (ADAS), such as Lane Departure Warning and Lane Keeping Assistant Systems. State-of-the-art ADAS rely on lane markings to draw inference about the extent of lanes or the road area. However, on many rural or urban roads markings are worn out or simply not existing. Therefore, this publication proposes a system for vision-based road boundary detection without requiring road markings at the outer side of the road. The fundamental approach is a boundary vicinity classification based on SPatial RAY (SPRAY) features which combines visual and spatial context information going beyond classical image patch analysis. More specifically, the inner road boundary vicinity (IBV), the outer road boundary vicinity (OBV), and the remaining part of the road area (RA) are detected. Because these classes occur in a defined sequence, i.e., a road boundary exhibits a transition from RA to IBV to OBV, this approach extracts the horizontal boundary transition pattern to make inference about possible locations of road boundaries and their direction (left or right road side). The implemented system was evaluated on unmarked urban and rural roads. The results show that the system effectively detects road boundaries such as curbstones and soft shoulders under challenging conditions.

This paper presents a lateral vehicle control algorithm for autonomous valet parking (AVP). Under the assumption that the position and heading angle are provided via vehicle-to-infrastructure (V2I) communication, the lateral controller aims to conduct two different driving maneuvers, i.e., forward driving and backward parking, and to control various types of vehicles in a unified approach. Therefore, it is necessary for the lateral controller to be robust enough to track the desired trajectories for different driving maneuvers, as well as to compensate for the uncertainty caused by the need to consider various vehicle types. With the assumption of operating conditions such as a low speed and small slip angle, a nonlinear kinematic model with kinematic constraints is used for the design of the lateral control. Based on this nonlinear model, a nonlinear control technique called dynamic surface control (DSC) is applied to design the lateral controller, and its stability is analyzed in the framework of linear differential inclusion. Finally, the proposed lateral control algorithm is validated through vehicle simulations and field tests.

Objective: The Vision Zero initiative pursues the goal of eliminating all traffic fatalities and severe injuries. Today’s advanced driver assistance systems (ADAS) are an important part of the strategy toward Vision Zero. In Germany in 2018 more than 26,000 people were killed or severely injured by traffic accidents on motorways and rural roads due to road accidents. Focusing on collision avoidance, a simulative evaluation can be the key to estimating the performance of state-of-the-art ADAS and identifying resulting potentials for system improvements and future systems.This project deals with the effectiveness assessment of a combination of ADAS for longitudinal and lateral intervention based on German accident data. Considered systems are adaptive cruise control (ACC), autonomous emergency braking (AEB), and lane keeping support (LKS).Methods: As an approach for benefit estimation of ADAS, the method of prospective effectiveness assessment is applied. Using the software rateEFFECT, a closed-loop simulation is performed on accident scenario data from the German In-Depth Accident Study (GIDAS) precrash matrix (PCM). To enable projection of results, the simulative assessment is amended with detailed single case studies of all treated cases without PCM data.Results: Three categories among today’s accidents on German rural roads and motorways are reported in this study: Green, grey, and white spots.Green spots identify accidents that can be avoided by state-of-the-art ADAS ACC, AEB, and LKS. Grey spots contain scenarios that require minor system modifications, such as reducing the activation speed or increasing the steering torque. Scenarios in the white category cannot be addressed by state-of-the-art ADAS. Thus, which situations demand future systems are shown. The proportions of green, grey, and white spots are determined related to the considered data set and projected to the entire GIDAS.Conclusions: This article describes a systematic approach for assessing the effectiveness of ADAS using GIDAS PCM data to be able to project results to Germany. The closed-loop simulation run in rateEFFECT covers ACC, AEB, and LKS as well as relevant sensors for environment recognition and actuators for longitudinal and lateral vehicle control.Identification of green spots evaluates safety benefits of state-of-the-art level 0–2 functions as a baseline for further system improvements to address grey spots. Knowing which accidents could be avoided by standard ADAS helps focus the evolution of future driving functions on white spots and thus aim for Vision Zero.

The knowledge about lanes and the exact position on the road is fundamental for many advanced driver assistance systems. In this paper, a novel iterative histogram based approach with occupancy grids for the detection of multiple lanes is proposed. In highway scenarios, our approach is highly suitable to determine the correct number of all existing lanes on the road. Additionally, the output of the laserscannner based lane detection is fused with a production-available vision based system. It is shown that both sensor systems perfectly complement each other to increase the robustness of a lane tracking system. The achieved accuracy of the fusion system, the laserscannner and video based system is evaluated with a highly accurate DGPS to investigate the performance with respect to lateral vehicle control applications.

Development and verification of Advanced Driver Assistance Systems (ADAS) are challenging activities. Since ADAS have to deal with a huge number of possible operational situations happening in the real world and misbehavior can lead to high-severity hazards, it is imperative to test their behavior thoroughly. However, it is not cost-effective to reproduce all the possible operational situations in controlled environments (e.g., icy road, fog, very snowy steep road, ecc.) for testing ADAS through field test, i.e., through test vehicles, and it is unacceptable to demand the test to end-users. Moreover, discovering safety violations during field tests would lead to huge cost in terms of redesign and increased time-to-market, and it is therefore mandatory to anticipate this phase as early as possible. This can be achieved by means of an effective Hazard Analysis and Risk Assessment (HARA) as prescribed by the ISO26262, when the concept of the item, in our case the ADAS, is developed. Commonly recognized problems of this phase are repeatably and objectivity in terms of independence of its results from the involved engineers. This paper proposes an approach to perform HARA through clever use of vehicle-level simulators to test an initial specification of the ADAS behavior against simulated operational situations, considering also corner cases very difficult or too dangerous to be reproduced during field testing. As a proof-of-concept, the approach is applied to an Advanced Emergency Braking System (AEBS).

Recent researches on advanced driver-assistance systems indicate great advances in terms of safety and comfort in automated driving. Advanced driver-assistance systems use control systems to perform most of the maneuvers as performed by the driver in the past. One of the useful advanced driver-assistance systems is automatic lane change system in order to avoid accidents. This study designs the controller of an automatic lane change system for an autonomous vehicle. The control law in this study is adaptive sliding mode control. To avoid chattering in adaptive sliding mode control, fuzzy boundary layer is used. Also, adaptive law is used for sliding-based switching gain. This adaptive controlling law is used to avoid the calculation of upper bound of system uncertainties. In this study, based on the boundary conditions, the vehicle lane change path planning and different maneuver periods are evaluated. To simulate the designed controller, CarSim–Simulink joint simulation model is used. This linkage leads to a full non-linear vehicle model. The results of simulation show excellent tracking for dry road conditions and acceptable tracking in icy and wet roads in some maneuvers of above 4-s long.

In this paper, the lateral motion control of intelligent vehicle is studied and improved. According to the time-varying nonlinear characteristics of intelligent vehicle driving process, the Fuzzy PID control algorithm based on the combination of fuzzy control theory and traditional PID algorithm is adopted. The Fuzzy PID lateral control simulation platform is established by using Matlab / Simulink to verify the control effect of lateral lane change under different longitudinal speeds. The effectiveness of the fuzzy control algorithm is verified by the simulation results; Finally, the test platform is built and the lateral lane change motion control test is carried out. The accuracy of the simulation model and the reliability of the established control algorithm in the real road environment are verified, and the accuracy and dynamic stability of the lateral motion control of the intelligent vehicle are improved.

The lateral motion control is a key element for automated driving vehicle technology. Typically, the front steering system has been used as the primary actuator for vehicle lateral motion control. Alternatively, this paper presents a new method of the lateral motion control using a rear steer. When combined with the front steer actuator, the rear steer can generate more dynamically responsive turning of the vehicle. In addition, the rear steer can be used as a secondary back up actuator when the front steer actuator fails to operate during automated driving mode. Similar to the prior research that has used the front steer actuator for the lateral control, the control methodology presented in this paper maintains the same hierarchical framework, i.e., sensor fusion, path prediction, path planning, and motion control. Since the rear steer is in play for the vehicle lateral motion control, the equations for the path prediction and vehicle dynamics are re-derived with non-zero front steer and rear steer angles. Combined with the rear steering dynamics, the model predictive control (MPC) technique is applied for motion error minimization. This paper describes the theoretical part of the algorithm, and provides simulation results to show effectiveness of the algorithm. Future work will include vehicle implementation, testing, and evaluation.

Driver behavior and the use of automation in real-world driving

Disuse of advanced driver assistance systems (ADAS).