Multi-entry underpass road tunnels feature long entrance downhill sections and underground merging areas where main and secondary roads converge. These complex driving environments can lead to variations in driver speed and lateral offset, increasing the risk of traffic accidents. Therefore, this study aims to analyze the speed and lateral offset characteristics in different tunnel sections and their impact on traffic safety, providing support for traffic control and safety improvements in multi-entry underpass tunnels. This study conducted real-vehicle natural driving tests using test vehicles equipped with an inertial navigation system and Mobileye. Based on changes in tunnel alignment and road parameters, the study divided the test sections into five segments: tunnel external section, entrance downhill section, entrance internal section, underground merging section, and tunnel internal section. By analyzing the speed variation trends, lateral offset characteristics, and their interrelationships across these sections, a standardized relative deviation fraction was introduced to quantitatively compare driving behavior in key sections, revealing differences in driving patterns and potential safety risks across different road segments. The speed growth rate in the entrance downhill section was the highest at 15.09%. In contrast, drivers in the underground merging section had the lowest average speed at 54.057 km/h and the highest speed dispersion. The underground merging section had the lowest rate of lateral offset change but the highest dispersion in lane offset within this section. Conversely, the entrance downhill section showed the smallest dispersion, with a standard deviation of only 0.111. In addition, research found that the driving distance in each road section is positively correlated with vehicle speed and negatively correlated with lane offset. Through real-vehicle tests, this study analyzed the speed, lateral offset, and driving safety characteristics of different sections in multi-entry tunnels. The results indicate that the entrance downhill section and underground merging section pose higher driving risks, as fluctuations in speed and lateral offset contribute to driving instability. These findings reveal the driving risks associated with specific sections of multi-entry underpass road tunnels and provide important references for tunnel traffic management and safety optimization.
A major research area in discrete geometry is to consider the best way to partition the d-dimensional Euclidean space R d under various quality criteria. In this paper we introduce a new type of space partitioning that is motivated by the problem of rounding noisy measurements from the continuous space R d to a discrete subset of representative values. Specifically, we study partitions of R d into bounded-size tiles colored by one of k colors, such that tiles of the same color have a distance of at least t from each other. Such tilings allow for error-resilient rounding, as two points of the same color and distance less than t from each other are guaranteed to belong to the same tile, and thus, to be rounded to the same point. The main problem we study in this paper is characterizing the achievable tradeoffs between the number of colors k and the distance t, for various dimensions d. On the qualitative side, we show that in R d , using k = d + 1 colors is both sufficient and necessary to achieve t > 0 . On the quantitative side, we achieve numerous upper and lower bounds on t as a function of k. In particular, for d = 3 , 4 , 8 , 24 , we obtain sharp asymptotic bounds on t, as k → ∞ . We obtain our results with a variety of techniques including isoperimetric inequalities, the Brunn-Minkowski theorem, sphere packing bounds, Bapat's connector-free lemma, and Čech cohomology.
Safe autonomous vehicle (AV) operations depend on an accurate perception of the driving environment, which necessitates the use of a variety of sensors. Computational algorithms must then process all of this sensor data, which typically results in a high on-vehicle computational load. For example, existing lane markings are designed for human drivers, can fade over time, and can be contradictory in construction zones, which require specialized sensing and computational processing in an AV. But, this standard process can be avoided if the lane information is simply transmitted directly to the AV. High definition maps and road side units (RSUs) can be used for direct data transmission to the AV, but can be prohibitively expensive to establish and maintain. Additionally, to ensure robust and safe AV operations, more redundancy is beneficial. A cost-effective and passive solution is essential to address this need effectively. In this research, we propose a new infrastructure information source (IIS), chip-enabled raised pavement markers (CERPMs), which provide environmental data to the AV while also decreasing the AV compute load and the associated increase in vehicle energy use. CERPMs are installed in place of traditional ubiquitous raised pavement markers along road lane lines to transmit geospatial information along with the speed limit using long range wide area network (LoRaWAN) protocol directly to nearby vehicles. This information is then compared to the Mobileye commercial off-the-shelf traditional system that uses computer vision processing of lane markings. Our perception subsystem processes the raw data from both CEPRMs and Mobileye to generate a viable path required for a lane centering (LC) application. To evaluate the detection performance of both systems, we consider three test routes with varying conditions. Our results show that the Mobileye system failed to detect lane markings when the road curvature exceeded ±0.016 m-1. For the steep curvature test scenario, it could only detect lane markings on both sides of the road for just 6.7% of the given test route. On the other hand, the CERPMs transmit the programmed geospatial information to the perception subsystem on the vehicle to generate a reference trajectory required for vehicle control. The CERPMs successfully generated the reference trajectory for vehicle control in all test scenarios. Moreover, the CERPMs can be detected up to 340 m from the vehicle's position. Our overall conclusion is that CERPM technology is viable and that it has the potential to address the operational robustness and energy efficiency concerns plaguing the current generation of AVs.
The automobile industry has developed dramatically in recent years, the supply of vehicles has also increased, and thus it has become deeply established in everyday life. Recently, as the supply of vehicles with autonomous driving functions increases, the safety of vehicles is also an emerging issue. Various car-following models for the safe driving of vehicles have long been studied by various people, and recently, a Responsibility-Sensitive Safety (RSS) model has been proposed by Mobileye. However, in existing car-following models or the RSS model, the safe distance between vehicles is presented using only vehicle speed and acceleration information, so there is a limitation in that it cannot respond to changes in road conditions due to the weather. In this paper, in order to ensure safety when the RSS model is applied to a variable focus function camera, an improved RSS model is presented in consideration of the changes in road conditions due to changes in weather, and a safety distance is derived based on the proposed model.
This study examined the optimal sampling durations for in-vehicle data recorder (IVDR) data analysis, focusing on professional bus drivers. Vision-based technology (VBT) from Mobileye Inc. is an emerging technology for monitoring driver behavior and enhancing safety in advanced driver assistance systems (ADASs) and autonomous driving. VBT detects hazardous driving events by assessing distances to vehicles. This naturalistic study of 77 male bus drivers aimed to determine the optimal duration for monitoring professional bus driving patterns and the stabilization point in risky driving events over time using VBT and G-sensor-equipped buses. Of the initial cohort, 61 drivers' VBT data and 66 drivers' G-sensor data were suitable for analysis. Findings indicated that achieving a stable driving pattern required approximately 130 h of VBT data and 170 h of G-sensor data with an expected 10% error rate. Deviating downward from these durations led to higher error rates or unreliable data. The study found that VBT and G-sensor data are both valuable tools for driving assessment. Moreover, it underscored the effective application of VBT technology in driving behavior analysis as a way of assessing interventions and refining autonomous vehicle algorithms. These results provide practical recommendations for IVDR researchers, stressing the importance of adequate monitoring durations for reliable and accurate outcomes.
(1) Background: Due to its high safety potential, one of the most common ADAS technologies is the lane support system (LSS). The main purpose of LSS is to prevent road accidents caused by road departure or entrance in the lane of other vehicles. Such accidents are especially common on rural roads during nighttime. In order for LSS to function properly, road markings should be properly maintained and have an adequate level of visibility. During nighttime, the visibility of road markings is determined by their retroreflectivity. The aim of this study is to investigate how road markings' retroreflectivity influences the detection quality and the view range of LSS. (2) Methods: An on-road investigation comprising measurements using Mobileye and a dynamic retroreflectometer was conducted on four rural roads in Croatia. (3) Results: The results show that, with the increase of markings' retroreflection, the detection quality and the range of view of Mobileye increase. Additionally, it was determined that in "ideal" conditions, the minimal value of retroreflection for a minimum level 2 detection should be above 55 mcd/lx/m2 and 88 mcd/lx/m2 for the best detection quality (level 3). The results of this study are valuable to researchers, road authorities and policymakers.
The severity of vehicle-pedestrian crashes has prompted authorities worldwide to concentrate on improving pedestrian safety. The situation has only become more urgent with the approach of automated driving scenarios. The Responsibility-Sensitive Safety (RSS) model, introduced by Mobileye®, is a rigorous mathematical model developed to facilitate the safe operation of automated vehicles. The RSS model has been calibrated for several vehicle conflict scenarios; however, it has not yet been tested for pedestrian safety. Therefore, this study calibrates and evaluates the RSS model for pedestrian safety using data from the Shanghai Naturalistic Driving Study. Nearly 400 vehicle-pedestrian conflicts were extracted from 8,000 trips by the threshold and manual check method, and then divided into 16 basic scenarios in three categories. Because crossing conflicts were the most serious and frequent, they were reproduced in MATLAB's Simulink with each vehicle replaced with a virtual automated vehicle loaded with the RSS controller module. With the objectives of maximizing safety and minimizing conservativeness, the non-dominated sorting genetic algorithm II was applied to calibrate the RSS model for vehicle-pedestrian conflicts. The safety performance of the RSS model was then compared with that of the commonly used active safety function, autonomous emergency braking (AEB), and with human driving. Findings verified that the RSS model was safer in vehicle-pedestrian conflicts than both the AEB model and human driving. Its performance also yielded the best test results in producing smooth and stable driving. This study provides a reliable reference for the safe control of automated vehicles with respect to pedestrians.
The prevailing assumption is that following kidney transplantation the pattern of kidney function decline is consistent. Nevertheless, numerous factors leading to graft loss may emerge, altering the trajectory of kidney function. In this study, we aim to assess alterations in estimated glomerular filtration rate (eGFR) trajectory over an extended period of follow-up and examine its correlation with graft survival. We calculated eGFR using all creatinine values available from 1-year post transplantation to the end of follow-up. For pattern analysis, we used a piecewise linear model. Nine hundred eighty-eight patients were included in the study. After a median follow-up of 5.2 years, 297 (30.1%) patients had a multi-phasic eGFR trajectory. Change in eGFR trajectory was associated with increased risk for graft failure (HR 7.15, 95% CI 5.17-9.89, p < .001), longer follow-up time, younger age, longer cold ischemia time, high prevalence of acute rejection, longer hospitalization and a lower initial eGFR. Of the 988 patients included in the study, 494 (50.0%) had a mono-phasic stable trajectory, 197 (19.9%) had a mono-phasic decreasing trajectory, 184 (18.6%) had bi-phasic decreasing trajectory (initial stability and then decline, 46(4.7%) had a bi-phasic stabilized (initial decline and then stabilization) and 67(6.8%) had a more complex trajectory (tri-phasic). Out of the total 144 patients who experienced graft loss, the predominant pattern was a bi-phasic decline characterized by a bi-linear trajectory (66 events, 45.8%). Changes in eGFR trajectory during long-term follow-up can serve as a valuable tool for assessing the underlying mechanisms contributing to graft loss.
To determine whether data-driven family histories (DDFH) derived from linked EHRs of patients and their parents can improve prediction of patients' 10-year risk of diabetes and atherosclerotic cardiovascular disease (ASCVD). A retrospective cohort study using data from Israel's largest healthcare organization. A random sample of 200 000 subjects aged 40-60 years on the index date (January 1, 2010) was included. Subjects with insufficient history (<1 year) or insufficient follow-up (<10 years) were excluded. Two separate XGBoost models were developed-1 for diabetes and 1 for ASCVD-to predict the 10-year risk for each outcome based on data available prior to the index date of January 1, 2010. Overall, the study included 110 734 subject-father-mother triplets. There were 22 153 cases of diabetes (20%) and 11 715 cases of ASCVD (10.6%). The addition of parental information significantly improved prediction of diabetes risk (P < .001), but not ASCVD risk. For both outcomes, maternal medical history was more predictive than paternal medical history. A binary variable summarizing parental disease state delivered similar predictive results to the full parental EHR. The increasing availability of EHRs for multiple family generations makes DDFH possible and can assist in delivering more personalized and precise medicine to patients. Consent frameworks must be established to enable sharing of information across generations, and the results suggest that sharing the full records may not be necessary. DDFH can address limitations of patient self-reported family history, and it improves clinical predictions for some conditions, but not for all, and particularly among younger adults.
Due to the relative rarity of crashes, researchers use traffic offenses, police records, public complaints, and In-Vehicle Data Recorder (IVDR) data as proxies for assessing crash risk. In this study, a unique IVDR system, called Vision-Based Technology [(VBT), (Mobileye Inc.)] was used to monitor perilous naturalistic driving events, such as insufficient distance from other vehicles and pedestrian or bicycle rider near-misses. The study aimed to test the convergent validity of VBT as an indicator of crash involvement risk. Data from 61 professional drivers working for a large bus company were analyzed (16 of 77 in the original data cohort were excluded for insufficient VBT data). Data included: recorded VBT data, objective data collected from official records (crash records provided by the bus company, and public complaints of reckless driving), self-report data regarding crash involvement, and police tickets. The correlation between VBT, objective and self-reported data was analyzed. Binary-logistic regression modeling (BLM) was used to calculate the odds ratio (OR) for participants involved in a car crash. Correlations were found between the total VBT risk score and official crash records, public complaints, and self-reports of crash involvement. The BLM correctly classified 90% of those who were involved in a crash (sensitivity) and 60% of those who were "crash-free" (specificity). The VBT total risk score was the only significant contributing factor to crash risk, and for each point of increase, the odds of being involved in a crash increased by a factor of 1.55. It is the first study to provide empirical evidence validating the VBT as an indicator of crash involvement and driver safety among professional bus drivers. VBT technology can provide researchers and clinicians a better understanding of bus drivers' risky driving behaviors- a valuable contribution to road safety interventions for this target group.
Commercialization of autonomous vehicle technology is a major goal of the automotive industry, thus research in this space is rapidly expanding across the world. However, despite this high level of research activity, literature detailing a straightforward and cost-effective approach to the development of an AV research platform is sparse. To address this need, we present the methodology and results regarding the AV instrumentation and controls of a 2019 Kia Niro which was developed for a local AV pilot program. This platform includes a drive-by-wire actuation kit, Aptiv electronically scanning radar, stereo camera, MobilEye computer vision system, LiDAR, inertial measurement unit, two global positioning system receivers to provide heading information, and an in-vehicle computer for driving environment perception and path planning. Robotic Operating System software is used as the system middleware between the instruments and the autonomous application algorithms. After selection, installation, and integration of these components, our results show successful utilization of all sensors, drive-by-wire functionality, a total additional power* consumption of 242.8 Watts (*Typical), and an overall cost of $118,189 USD, which is a significant saving compared to other commercially available systems with similar functionality. This vehicle continues to serve as our primary AV research and development platform.
The Responsibility-Sensitive Safety (RSS) model was proposed by Mobileye as a mathematical model that defines the real-time safety distance that the automated vehicle (AV) needs to maintain from surrounding vehicles. However, RSS strategy tends to be overly conservative. This research made modifications to the RSS safe distance to reduce its conservativeness without affecting safety, and evaluated the modified (RSS_X) and original RSS (RSS_O) in freeway car-following scenarios extracted from the Shanghai Naturalistic Driving Study (SH-NDS). The modifications were replacing the maximum acceleration with the positive previous time-step acceleration and adding standstill gap. In this study, 6,146 car-following scenarios were extracted and divided into two groups, normal scenarios (5,923) and safety-critical events (SCEs, near crashes) (223), to evaluate the efficiency and safety performance of RSS. The RSS_O and RSS_X were then embedded into the intelligent driver model (IDM) and model predictive control (MPC), but because the RSS modifications caused a few acceleration stability problems, the IDM and MPC were also modified to accommodate the RSS_X. The efficiency performance results showed that the modified models (IDM + RSS_X, MPC + RSS_X) performed better than the originals (IDM + RSS_O, MPC + RSS_O) in that they had higher average speeds, more comfortable acceleration pattern, and smaller longitudinal clearance between vehicles, which leads to less conservativeness. To evaluate safety, human drivers were compared with the original and modified models. RSS reduced the severity of at least 80 % of the human driver SCEs. MPC + RSS_X increased the mean minimum time to collision (TTC) for the majority of SCEs from 1.65 s to 4.08 s, and IDM + RSS_X increased the mean minimum TTC for the majority of SCEs from 1.53 s to 3.44 s.
In public road tests of autonomous vehicles in California, rear-end crashes have been the most common type of crash. Collision avoidance systems, such as autonomous emergency braking (AEB), have provided an effective way for autonomous vehicles to avoid collisions with the lead vehicle, but to avert false alarms, AEB tends to apply late and hard brake only if a collision becomes unavoidable. Automatic preventive braking (APB) is a new collision avoidance method used in Mobileye's Responsibility-Sensitive Safety (RSS) model that aims to reduce crashes with a milder brake and decreased impact on traffic flow, but APB's safety performance is inferior to that of AEB. This study therefore proposes three safety improvement strategies for APB, the addition of response time, safety buffer, and minimum following distance; and combines them in different ways into four improved APB systems, IP1-IP4. Simulating car-following safety-critical events (SCEs) extracted from the Shanghai Naturalistic Driving Study in MATLAB's Simulink, the safety performance, conservativeness, and driving comfort of the four systems were evaluated and compared with the original APB system, two AEB systems, and human drivers. The results show that 1) IP4, the system that integrated all three strategies, outperformed the baseline APB and IP1-IP3 and prevented all SCEs from becoming crashes; 2) IP4 was slightly more conservative than AEB, but less conservative than RSS; 3) APB's jerk-bounded braking profile improved driving comfort; and 4) higher deceleration was found in the two AEB systems (both 8.1 m/s2) than in IP4 (6.7 m/s2), but they failed to prevent all crashes. Our proposed APB system, IP4, can provide safe, efficient, and comfortable braking for AVs in car-following SCEs, and has the potential to be practically applied in vehicle collision avoidance systems.
Anemia is prevalent following kidney transplantation and is associated with reduced graft survival. The association between temporal changes in hemoglobin (Hb) level at the early post-transplant period and graft survival is unknown. The study cohort included consecutive patients included in a single center transplantation registry between January 2002 and December 2016. Temporal changes in Hb values during the first 90 days after the transplantation were evaluated by piecewise linear regression model. Significant Hb increase rate was defined as an increase of .5 gram/deciliter/month. Patients were divided into groups according to the presence of significant Hb increase. The primary outcome was death-censored graft failure. Of 946 patients included in the study cohort, 831 (87.8%) had at least one interval of Hb increase, and 115 (12.2%) had no Hb increase. The absence of Hb increase was associated with an elevated risk of death censored graft failure by univariate (HR 2.9, 95% CI 1.88-4.49, P < .001) and multivariate (HR 2.47, 95% CI 1.48-4.12, P = .001) analyses. The timing and rate of Hb increase had no association with the main outcome. Lack of Hb increase during the early post-transplant period is associated with an increased risk of graft loss.
ADAS and autonomous technologies in vehicles become more and more complex, which increases development time and expenses. This paper presents a new real-time ADAS multisensory validation system, which can speed up the development and implementation processes while lowering its cost. The proposed test system integrates a high-quality 3D CARLA simulator with a real-time-based automation platform. We present system experimental verifications on several types of sensors and testing system architectures. The first, open-loop experiment explains the real-time capabilities of the system based on the Mobileye 6 camera sensor detections. The second experiment runs a real-time closed-loop test of a lane-keeping algorithm (LKA) based on the Mobileye 6 line detection. The last experiment presents a simulation of Velodyne VLP-16 lidar, which runs a free space detection algorithm. Simulated lidar output is compared with the real lidar performance. We show that the platform generates reproducible results and allows closed-loop operation which, combined with a real-time collection of event information, promises good scalability toward complex ADAS or autonomous functionalities testing.
The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a large measurement campaign on a Hungarian highway to support the development and experimental validation of the new approach. The quality of the model was tested and compared to reference measurements, leading to a pointwise position error of 9.60% in the lateral and 1.57% in the longitudinal direction. Additionally, the modeling of the natural scattering of the sensor model output was satisfying. In particular, the deviations of the position measurements were well modeled with this approach.
Today, a lot of research on autonomous driving technology is being conducted, and various vehicles with autonomous driving functions, such as ACC (adaptive cruise control) are being released. The autonomous vehicle recognizes obstacles ahead by the fusion of data from various sensors, such as lidar and radar sensors, including camera sensors. As the number of vehicles equipped with such autonomous driving functions increases, securing safety and reliability is a big issue. Recently, Mobileye proposed the RSS (responsibility-sensitive safety) model, which is a white box mathematical model, to secure the safety of autonomous vehicles and clarify responsibility in the case of an accident. In this paper, a method of applying the RSS model to a variable focus function camera that can cover the recognition range of a lidar sensor and a radar sensor with a single camera sensor is considered. The variables of the RSS model suitable for the variable focus function camera were defined, the variable values were determined, and the safe distances for each velocity were derived by applying the determined variable values. In addition, as a result of considering the time required to obtain the data, and the time required to change the focal length of the camera, it was confirmed that the response time obtained using the derived safe distance was a valid result.
With age might come a decline in crucial driving skills. The effect of a collision warning system (CWS) on older drivers' head movements behavior at intersections was examined. Methods: Twenty-six old-adults, between 55 and 64 years of age, and 16 Older drivers between 65 and 83 years of age, participated in the study. A CWS (Mobileye Inc.) and a front-back in-vehicle camera (IVC) were installed in each of the participants' own vehicles for 6 months. The CWS was utilized to identify unsafe events during naturalistic driving situations, and the IVC was used to capture head direction at intersections. The experimental design was conducted in three phases (baseline, intervention, and carryover), 2 months each. Unsafe events were recorded by the CWS during all phases of the study. In the second phase, the CWS feedback was activated to examine its effect on drivers' head movement' behavior at intersections. Results: Older drivers (65+) drove significantly more hours in total during the intervention phase (M = 79.1 h, SE = 10) than the baseline phase (M = 39.1 h, SE = 5.3) and the carryover phase (M = 37.7 h, SE = 5.4). The study revealed no significant differences between the head movements of older and old-adult drivers at intersections. For intersection on the left direction, a significant improvement in drivers' head movements' behavior was found at T-junctions, turns and four-way intersections from phase 1 to phase 3 (p < 0.01), however, two intersection types presented a decrease along the study phases. The head movements' behavior at roundabouts and merges was better at phase 1 compared to phase 3 (p < 0.01). There was no significant reduction of the mean number of CWS unsafe events across the study phases. Conclusions: The immediate feedback provided by the CWS was effective in terms of participants' head movements at certain intersections but was harmful in others. However, older drivers drove many more hours during the active feedback phase, implying that they trusted the system. Therefore, in the light of this complex picture, using the technological feedback with older drivers should be followed with an additional mediation or follow-up to ensure safety.
Lane detection on road segments with complex topologies such as lane merge/split and highway ramps is not yet a solved problem. This paper presents a novel graph-embedded solution. It consists of two key parts, a learning-based low-level lane feature extraction algorithm, and a graph-embedded lane inference algorithm. The former reduces the over-reliance on customized annotated/labeled lane data. We leveraged several open-source semantic segmentation datasets (e.g., Cityscape, Vistas, and Apollo) and designed a dedicated network that can be trained across these heterogeneous datasets to extract lane attributes. The latter algorithm constructs a graph to represent the lane geometry and topology. It does not rely on strong geometric assumptions such as lane lines are a set of parallel polynomials. Instead, it constructs a graph based on detected lane nodes. The lane parameters in the world coordinate are inferred by efficient graph-based searching and calculation. The performance of the proposed method is verified on both open source and our own collected data. On-vehicle experiments were also conducted and the comparison with Mobileye EyeQ2 shows favorable results.
In-vehicle collision avoidance technology (CAT) has the potential to prevent crash involvement. In 2015, Transport for New South Wales undertook a trial of a Mobileye 560 CAT system that was installed in 34 government fleet vehicles for a period of seven months. The system provided headway monitoring, lane departure, forward collision and pedestrian collision warnings, using audio and visual alerts. The purpose of the trial was to determine whether the technology could change the driving behaviour of fleet vehicle drivers and improve their safety. The evaluation consisted of three components: (1) analysis of objective data to examine effects of the technology on driving behaviour, (2) analysis of video footage taken from a sample of the vehicles to examine driving circumstances that trigger headway monitoring and forward collision warnings, and (3) a survey completed by 122 of the 199 individuals who drove the trial vehicles to examine experiences with, and attitudes to, the technology. Analysis of the objective data found that the system resulted in changes in behaviour with increased headway and improved lane keeping, but that these improvements dissipated once the warning alerts were switched off. Therefore, the system is capable of altering behaviour but only when it is actively providing alerts. In-vehicle video footage revealed that over a quarter of forward collision warnings were false alarms, in which a warning event was triggered despite there being no vehicle travelling ahead. The surveyed drivers recognised that the system could improve safety but most did not wish to use it themselves as they found it to be distracting and felt that it would not prevent them from having a crash. The results demonstrate that collision avoidance technology can improve driving behaviour but drivers may need to be educated about the potential benefits for their driving in order to accept the technology.