Lane Change Warning Research Articles

Developing a new integrated advanced driver assistance system in a connected vehicle environment

Advanced driver assistance systems (ADASs) can effectively enhance driving and safety performance. Due to the inherent limitations of in-vehicle technologies concerning information sharing, existing studies mainly focus on demonstrating the effectiveness of onboard sensor-based individual ADAS functions rather than their collaborative effectiveness. Thanks to the emerging connected vehicle (CV) technologies, it is viable to physically realize the collaboration and coordination between different ADAS functions. This study aims to synthesize seven ADAS functions into an integrated advanced driving assistance system (iADAS) in a CV environment. The seven ADAS functions include omni-directional collision warning, lane-change warning, curve speed warning, emergency event notification, car-following guidance, identification of variable speed limits, and information services. The activation indicators and activation conditions of these ADAS functions are derived based on a single local coordinate system. This derivation has considered the real-time motion states of the ego and surrounding vehicles. Different ADAS functions are classified based on their roles in accident reduction, traffic efficiency enhancement, and driver convenience improvement. Afterwards, their priority of releasing information is set by considering the classification and primary functionality. Finally, the effectiveness of the iADAS is validated in field tests. Testing results reveal that the iADAS helps reduce rear-end collisions and prevent rollovers or sideslips on curved roads. Furthermore, younger drivers respond faster with higher driving stability regarding lateral collision warnings. Young, well-educated, and low-risk taking drivers maintain a short but safe time headway to the leading vehicle.

A comprehensive pseudonym changing scheme for improving location privacy in vehicular networks

In an Intelligent Transportation System (ITS), many applications, such as collision avoidance and lane change warning, require real-time information from vehicles on the road. This typically includes detailed status information such as location, speed, heading and a vehicle identifier, which can be used to infer precise movement patterns leading to long-term driver profiling and vehicle tracking. The use of pseudonyms, instead of actual vehicle IDs, allows vehicles to protect their privacy while sharing relevant information. A pseudonym changing scheme (PCS) determines when and how a vehicle should change its pseudonyms to maintain an appropriate privacy level. In this paper, we propose a new comprehensive PCS that utilizes vehicle context and current traffic patterns to leverage the optimum situation for changing pseudonyms. Simulation results indicate that the proposed PCS outperforms existing approaches both in terms of user-centric and adversary-centric performance metrics.

XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway

This study is conducted on a real live highway to investigate the driver’s performance in estimating the speed and distance of vehicles behind the target lane during lane changes. Data on the participants’ estimated and actual data on the rear car were collected in the experiment. Ridge regression is used to analyze the effects of both the driver’s features, as well as the relative and absolute motion characteristics between the target vehicle and the subject vehicle, on the driver’s estimation outcomes. Finally, a mixed algorithm of extreme gradient boosting (XGBoost) and deep neural network (DNN) was proposed in this paper for establishing driver’s speed estimation and distance prediction models. Compared with other machine learning models, the XGBoost-DNN prediction model performs more accurate prediction performance in both classification scenarios. It is worth mentioning that the XGBoost-DNN mixed model exhibits a prediction accuracy approximately two percentage points higher than that of the XGBoost model. In the two-classification scenarios, the accuracy estimations of XGBoost-DNN speed and distance prediction models are 91.03% and 92.46%, respectively. In the three-classification scenarios, the accuracy estimations of XGBoost-DNN speed and distance prediction models are 87.18% and 87.59%, respectively. This study can provide a theoretical basis for the development of warning rules for lane-change warning systems as well as insights for understanding lane-change decision failures.

Research on Vehicle Lane Change Warning Method Based on Deep Learning Image Processing.

In order to improve vehicle driving safety in a low-cost manner, we used a monocular camera to study a lane-changing warning algorithm for highway vehicles based on deep learning image processing technology. We improved the mask region-based convolutional neural network for vehicle target detection. Suitable anchor frame ratios were obtained by means of K-means++ method clustering for 66,389 vehicle targets with the width/height ratio, which is one more set of anchor frames than the original setting, so as to ensure that the generation accuracy of candidate frames can be improved without sacrificing more network performance. Using the vehicle target annotation set, we trained the vehicle targets. Through the analysis of indicators for mean average precision, a new set of anchor frames was added to improve the accuracy of vehicle target detection. Based on the improved vehicle detection network and an end-to-end lane detection network in series, we proposed an algorithm for the detection of highway vehicle lane-changing behavior with the first-person perspective by summing the inter-frame change rates in the vehicle lane-changing data pool. After the identification and verification of the marked lane-changing picture sequences, a lane-changing detection accuracy rate of 94.5% was achieved.

Design of lane changing warning system for high speed vehicle based on fuzzy adaptive PID

In order to overcome the low precision and efficiency of the traditional lane changing warning system for high-speed vehicles, a new lane changing warning system based on fuzzy adaptive PID is proposed in this paper. Firstly, the hardware structure of the control system is designed. The hardware mainly includes the early warning system control module and the fuzzy adaptive PID controller module to achieve high-precision early warning. In the software part of the system, in order to improve the turning sensitivity of the car, the fuzzy adaptive PID control algorithm is used for yaw rate feedback control, and the lane change warning algorithm is constructed. The experimental results show that, compared with the traditional lane changing early warning system, the early warning accuracy and efficiency of the designed system are significantly improved, and the maximum early warning accuracy reaches 96%.

A new method of temporal and spatial risk estimation for lane change considering conventional recognition defects

Risky lane change behavior of drivers normally will pose some negative impacts on traffic safety. To ensure a lane change safe and prevent potential accidents, it is important to recognize some lane-changing conditions with potential risks in advance. Despite the researches on traffic safety assessment have been developed for decades, most of the existing researches are mainly interesting in how to estimate the overall safety of the lane-changing process based on historical data. These methods tend to ignore the interactive impacts between lane-changing vehicle and its surrounding vehicles, and have the disadvantages of the long-term evaluation period and single evaluation index. To address these gaps, this study presents a temporal and spatial risk estimation (TSRE) to recognize lane-changing risk in real-time. However, this study concentrates on the instantaneous risk for a lane change event, considering temporal and spatial dimensions for the current lane change circumstance on the highway. After processing the realistic vehicle trajectory dataset, this study extracted 1444 groups of lane change samples, and then incorporates the temporal risk level (TRL) and spatial risk level (SRL) into a comprehensive risk index by applying fault tree analysis. Furthermore, SRL and comprehensive risk index are both used to determine whether the traffic condition of a lane change is safe, and it can effectively overcome the conventional recognition defects that existed in other methods. To achieve a better evaluation effect, the sensitivity tests of recognition accuracy for various risk threshold combinations were carried out. Ultimately, experimental results showed that the proposed TSRE model achieved 97.45 %, 97.79 %, 84.1 % and 85.05 % accuracy rate in terms of classifying the risky lane change samples, traffic conflicts, risky frames and safe frames, when an appropriate risk threshold combination was selected. This encouraging finding can provide the basis for algorithm design of the lane change warning system for connected vehicles.

How many crashes can connected vehicle and automated vehicle technologies prevent: A meta-analysis

The connected and automated vehicle (CAV) technologies have made great progresses. It has been commonly accepted that CV or AV technologies would reduce human errors in driving and benefit traffic safety. However, the answer of how many crashes can be prevented because of CV or AV technologies has not reached a consistent conclusion. In order to quantitatively answer this question, this study used meta-analysis to evaluate the safety effectiveness of nine common and important CV or AV technologies, and tested the safety effectiveness of these technologies for six countries. First, 73 studies about the safety impact of CV or AV technologies were filtered out from 826 CAV-related papers or reports. Second, the safety impacts of these technologies with regard to assistant types and triggering times have been compared. It shows AV technologies can play a more significant role than CV technologies, and the technologies with closer triggering time to collision time have greater safety effectiveness. Third, in the meta-analysis, the random effect model was used to evaluate the safety effectiveness, and the funnel plots and trim-and-fill method were used to evaluate and adjust publication bias, so as to objectively evaluate the safety effectiveness of each technology. Then, according to the crash data of six countries, the comprehensive safety effectiveness and compilation of safety effectiveness of the above technologies were calculated. The results show that if all of technologies were implemented in the six countries, the average number of crashes could be reduced by 3.40 million, among which the India would reduce the most (54.24%). Additionally, different countries should develop different development strategies, e.g., USA should prioritize the development of the lane change warning and intersection warning, the UK should prioritize applications related to intersection warning and rear-end warning. Overall, this study provides comprehensive and quantitative understating of the safety effectiveness of CA or AV technologies and would contribute to government, vehicle companies, and agencies in deciding the development priority of CA or AV technologies.

Lane Detection and Lane Change Warning as Advanced Driver Assistance Systems using Computer Vision

Road ways are the life line of any economy, for a country like India where economy isgrowing rapidly it is putting its toll on every sector for meeting the needs of the growing economy. Good’s and personal transport are becoming vital with time and money aspects and the roads and vehicles on the roads are expected to perform optimally drastically increasing the speed on the road network and constantly increasing and modifying the infrastructure needed to meet the demands. As the speed of the vehicle increases the accident rate and the damage caused by the collision will also increase. Safety of the road network is not to be compromised and proper systems to ensure the safe passage of the vehicle and proper warning systems are to be implemented. This system should be viable in all the condition and should be cost-effective. In this paper we are implementing a vision based system to identify the lane and other vehicles from the video it captures from a properly calibrated camera mounted on the front side of the vehicle. The system is designed to automatically and continuously detect the lines exploiting the new processing techniques and warning the driver if any other is in the breaking distance of the vehicle or if the vehicle is moving out of the lane. Cost effectiveness of the system is a major aspect as many of the available systems use equipment which very good at performing their task but are not affordable. Effort is put in making the system cost effective and not compromising with the reaction time and accuracy..

Lane change identification and prediction with roadside LiDAR data

Lane change identification and lane change prediction are important tasks for the Connected-Vehicle (CV) technologies. Since both connected vehicles and non-connected vehicles may exist on the roads for a long time, the real-time information of the unconnected traffic could not be obtained by the current CV network. Therefore, lane change identification and lane change prediction could not be achieved with the missing traffic information of the unconnected vehicles. The roadside Light Detection and Ranging (LiDAR) provides a solution to fill the data gap under the mixed traffic situation. This paper developed the methods of lane change identification and prediction based on the vehicle trajectories extracted from the roadside LiDAR data. Lane boundaries were used to enhance the accuracy of lane change identification. The proposed method was evaluated using real-world data. The results showed that the proposed method can achieve the relatively high accuracy. The lane change information can be used to develop the lane-change warning system for the CV network.

Improving the User Acceptability of Advanced Driver Assistance Systems Based on Different Driving Styles: A Case Study of Lane Change Warning Systems

The low user acceptability of advanced driver assistance systems (ADASs) is one of the fundamental problems limiting their wider adoption. One of the key factors affecting the frequency of warning signals is the standard warning thresholds set in ADASs, which may not be compatible with all drivers owing to various driver characteristics affecting their cognition of risk, such as comfort, skill, and experience. The present study focuses on the lane change warning (LCW) system to evaluate driving styles according to the perception of lane change risk, and determine appropriate warning thresholds corresponding to the different driving styles. A theoretical lane change warning model is established to calculate the deceleration required for the rear approaching vehicle in the target lane. The results of risk assessment experiments conducted on an actual expressway using 15 proficient drivers are employed to evaluate the risk cognitions of the participants, where the participants are divided into four different driving styles according to their adaptive warning thresholds, which are denoted as very low threshold, low threshold, medium threshold, and high threshold driving styles. Signal detection theory is then employed to determine lane change warning thresholds appropriate to the different driving styles. Our results clearly demonstrate the disparate perceptions of lane change risk for the different drivers. Therefore, the LCW system should adopt different warning thresholds for different drivers according to their driving style. The findings provide evidence supporting the exploitation of driving styles for adopting different warning thresholds in the LCW system to enhance its user acceptability.

Robust control of connected vehicles via V2V communication

AbstractThis paper introduces a robust controller for connected vehicles which are communicating through dedicated short‐range communication (DSRC) protocol to avoid collision and improve safety. By a comprehensive analysis on both longitudinal and lateral dynamics of the vehicles, the controller covers a wide range of collision avoidance scenarios, such as: Intersection Movement Assistant (IMA), Automatic Emergency Brake (AEB) and Lane Change Warning (LCW). By implementing an advanced Sliding Mode Controller (SMC), the effect of uncertainties will be mitigated for a variety of path plans. It turns out that the proposed control scheme can robustly improve the safety. Finally, we optimize the performance of vehicles in tracking the paths by an MPC controller.

Research on Safety Lane Change Warning Method Based on Potential Angle Collision Point

In order to ensure safe lane change and avoid traffic accidents, an effective lane change assist system is required. In a lane change assist system, it is very important to obtain the following elements in time, such as actual distance between vehicles, minimum safety distance, and warning signal. To this end, this paper analyzed four kinds of lane change angle collision scenes. Initial position, initial velocity, acceleration, heading angle, and kinematics of vehicles were used to calculate the position of potential angle collision points between lane change vehicle and obstacle vehicles. Then, actual distance model was constructed based on potential angular collision points. The minimum safety distance model was also established under the two most unfavorable conditions. In order to achieve the lane change warning, three early warning rules were formulated. We verified the validity of models and early warning rules using vehicle driving video data of Interstate 80 in California. Models and early warning rules constructed in our research can be applied to the advanced active safety systems of vehicle, such as vehicle lane change assist system and active collision early warning system, which can improve the active safety and reduce traffic accidents.

Experimental Characterization of Routing Protocols in Urban Vehicular Communication

Abstract Vehicular communication is a cynosure in automotive industry these days. V2V communication is one of the types of vehicular communication which render lane change warning, emergency vehicle alert, intersection alert, congestion alert, payment at tolls etc. A simulation research on the utilization of vehicle to vehicle connectivity via different routing protocols in VANET, contemplating the instance of a city situation has been introduced in our paper in order to resolve the issue of traffic routing. A routing algorithm is proposed which firstly selects optimal path via carry and forward approach and then transmits information on that path and the proposed algorithm is then compared with contemporary routing protocols based on different QoS parameters like throughput, packet delivery ratio, delay which are measured using NETSIM simulator to evaluate the behaviour of dissimilar routing protocols. The proposed algorithm outperforms most of the simulation cases.

ADAS Acceptability Improvement Based on Self-Learning of Individual Driving Characteristics: A Case Study of Lane Change Warning System

Low user acceptance is one of the fundamental problems for popularizing advanced driver assistance systems (ADAS). Systems that are developed for the majority of drivers have to possess stationary characteristics and be conservative for safety reasons. However, the drivers with disparate driving styles possess different risk cognition of lane change behavior; therefore, such systems with stationary characteristics may cause frequent interference to aggressive drivers or may be perceived as a radical system by conservative drivers. An ADAS that adapts to the characteristics of individual drivers during lane change maneuvers will be more effective and more acceptable to drivers. In this study, we developed an adaptive algorithm that learns the characteristics of individual drivers during lane changes and determines the optimal threshold online to adapt to different drivers. Signal detection theory (SDT) was employed and the results of the accuracy, false negative rate, and false positive rate were used to capture the drivers' lane change behavior characteristics. A learning stage and a threshold fluctuation stage were designed in the adaptive algorithm to determine the optimal warning threshold and amended the optimal warning threshold based on changes in the drivers' behaviors. We evaluated the proposed algorithm by conducting the actual vehicle tests with a total of three participants. The offline statistical analysis results of the participants' lane change characteristics were compared with the online results of the warning threshold adjustments from the adaptive algorithm; the comparison results indicated that the adaptive algorithm could effectively capture the drivers' lane change characteristics and determine an appropriate warning threshold. The findings provide an improvement in the performance of the lane change warning (LCW) system and enhance people's acceptance of intelligent systems.

Lane change warning threshold based on driver perception characteristics

Lane Change Warning system (LCW) is exploited to alleviate driver workload and improve the safety performance of lane changes. Depending on the secure threshold, the lane change warning system could transmit caution to drivers. Although the system possesses substantial benefits, it may perturb the conventional operating of the driver and affect driver judgment if the warning threshold does not conform to the driver perception of safety. Therefore, it is essential to establish an appropriate warning threshold to enhance the accuracy rate and acceptability of the lane change warning system. This research aims to identify the threshold that conforms to the driver perception of the ability to safely change lanes with a rear vehicle fast approaching. We propose a theoretical warning model of lane change based on a safe minimum distance and deceleration of the rear vehicle. For the purpose of acquiring the different safety levels of lane changes, 30 licensed drivers are recruited and we obtain the extreme moments represented by driver perception characteristics from a Front Extremity Test and a Rear Extremity Test implemented on the freeway. The required deceleration of the rear vehicle corresponding to the extreme time is calculated according to the proposed model. In light of discrepancies in the deceleration in these extremity experiments, we determine two levels of a hierarchical warning system. The purpose of the primary warning is to remind drivers of the existence of potentially dangerous vehicles and the second warning is used to warn the driver to stop changing lanes immediately. We use the signal detection theory to analyze the data. Ultimately, we confirm that the first deceleration threshold is 1.5 m/s2 and the second deceleration threshold is 2.7 m/s2. The findings provide the basis for the algorithm design of LCW and enhance the acceptability of the intelligent system.

Safety-Aware Location Privacy in VANET: Evaluation and Comparison

VANET safety applications broadcast cooperative awareness messages (CAM) periodically to provide vehicles with continuous updates about the surrounding traffic. The periodicity and the spatiotemporal information contained in these messages allow a global adversary to track vehicle movements. Many privacy schemes have been proposed for VANET, but only few schemes consider their impact on safety applications. Also, each scheme is evaluated using inconsistent metrics and unrealistic vehicle traces, which makes comparing the actual performance of different schemes in the wild more difficult. In this paper, we aim to fill this gap and compare different privacy schemes not only in terms of the privacy gained, but also their impact on safety applications. A distortion-based privacy metric is initially proposed and compared with other popular privacy metrics showing its effectiveness in measuring privacy. A practical safety metric which is based on Monte Carlo analysis is then proposed to measure the QoS of two safety applications: forward collision warning and lane change warning. Using realistic vehicle traces, six state-of-the-art VANET privacy schemes are evaluated and compared in terms of the proposed privacy and safety metrics. Among the evaluated schemes, it was found that the coordinated silent period scheme achieves the best privacy and QoS levels, but fully synchronized silence among all vehicles is a practical challenge. The CAPS and CADS schemes provide a practical compromise between privacy and safety since they employ only the necessary silence periods to prevent tracking and avoid changing pseudonyms in trivial situations.

On the enhancements to IEEE 802.11 MAC and their suitability for safety‐critical applications in VANET

AbstractVehicular ad hoc network (VANET) or inter‐vehicle communication (IVC) provides many brand new and powerful capabilities for transportation system applications. Safety massaging, as one of the capabilities, supports many potential safety applications such as emergency electronic brake lights, lane change warning, pre‐crash warning. These applications require a low latency and high reliability communication service. In this paper, we first analyze these critical requirements. The under‐development 802.11p for VANET is then discussed with respect to those requirements. An extensive research on the enhancements for 802.11 media access control (MAC) is conducted in order to show their suitability for safety applications. As a conclusion, a realistically feasible MAC enhancement scheme is still needed to achieve the high performance requirements and the compatibility. Copyright © 2008 John Wiley & Sons, Ltd.

Eye Glance Behavior of Van and Passenger Car Drivers During Lane Change Decision Phase

Data are presented on the eye glance behavior of passenger car and van drivers before the start of discretionary lane changes. Thirty-nine volunteers ranging from 20 to 60 years of age served as either van drivers (N = 19) or passenger car drivers (N = 20) in the study. Each driver used an instrumented vehicle and was accompanied by a ride-along observer in daylight and dry pavement conditions. The test route included driving on both public highways at 55 mph or more and city roads at 25 to 35 mph. A total of 549 lane changes (290 for vans, 259 for passenger cars) were analyzed in terms of driver eye glance behavior 10 s before the lane change start. Results indicated that for left-to-right lane changes, the probability of a glance to the center mirror was substantially higher than the probability of a glance to the right side mirror. For right-to-left lane changes, the probability of a glance to the center mirror was substantially less than that for rightward lane changes, and the probability of a glance to the left side mirror was appreciably higher than that for right side mirror use in rightward lane changes. These results held for both van and passenger car drivers. Except for a slightly higher probability of over-the-shoulder glances on city roads, these results hold for both highway and city street driving. These data should be factored into the design of lane change warning system displays and mirror systems.

Eye Glance Behavior of van and Passenger Car Drivers during Lane Change Decision Phase

Data are presented on the eye glance behavior of passenger car and van drivers before the start of discretionary lane changes. Thirty-nine volunteers ranging from 20 to 60 years of age served as either van drivers (N = 19) or passenger car drivers (N = 20) in the study. Each driver used an instrumented vehicle and was accompanied by a ride-along observer in daylight and dry pavement conditions. The test route included driving on both public highways at 55 mph or more and city roads at 25 to 35 mph. A total of 549 lane changes (290 for vans, 259 for passenger cars) were analyzed in terms of driver eye glance behavior 10 s before the lane change start. Results indicated that for left-to-right lane changes, the probability of a glance to the center mirror was substantially higher than the probability of a glance to the right side mirror. For right-to-left lane changes, the probability of a glance to the center mirror was substantially less than that for rightward lane changes, and the probability of a glance to the left side mirror was appreciably higher than that for right side mirror use in rightward lane changes. These results held for both van and passenger car drivers. Except for a slightly higher probability of over-the-shoulder glances on city roads, these results hold for both highway and city street driving. These data should be factored into the design of lane change warning system displays and mirror systems.

The Development and Evaluation of Icons for Side Obstacle Warning Systems

A new class of driver assistance system under development is Side Obstacle Warning (SOW). These systems are designed to alert drivers to the presence of vehicles in adjacent lanes. Two forms of SOW systems being developed are Blind Spot Detection and Lane Change Warning. Both are relatively recent developments, and therefore have few established icons. A production test methodology was employed to develop icons that convey the functionality of the two SOW systems. Thirty drivers were asked to draw icons that conveyed the Blind Spot Detection and Lane Change Warning functions. The illustrations that resulted were categorized according to similarities, from which nine icons were developed for each Blind Spot Detection and Lane Change Warning. Sixty drivers rank ordered those icons in an appropriateness ranking test. The rank orders were analyzed, and the most promising icons for both systems are presented.