Vehicle Active Safety Systems Research Articles

Research on an Intelligent Vehicle Emergency Avoidance Algorithm Based on User Behaviour Learning

With the development of the Internet of Vehicles and the high-precision lane-level navigation system, vehicles can receive more road details. And the systems will provide conditions for the development of the emergency avoidance function. This paper studies a vehicle automatic emergency avoidance algorithm based on user behaviour learning. The research is based on the Internet of Vehicles to obtain user driving data, generate a user database, and through the analysis of the avoidance track under the user's active operation conditions, generate a track equation or empirical formula, and the vehicle control unit executes the emergency avoidance action according to this. In the algorithm, the emergency avoidance function is defined as based on the vehicle's active safety system to avoid the event of a sudden situation, and the function will briefly disconnect the driver's partial operation when it is intervened, and the trigger conditions are set according to the trigger conditions of the parallel emergency braking function. The track equation is fitted using a sinusoidal signal, and the final output is the vehicle's front wheel angle.

Fixed-time adaptive sliding mode-based active rollover prevention control of automated guided vehicles via improved super-twisting observer

As an important component of automated guided vehicle (AGV) active safety systems, the active rollover prevention (ARP) control has been widely studied. In this paper, a fixed-time adaptive sliding mode (FTASM) control strategy based on nested adaptive law (NAL) and improved super-twisting observer (ISTO) is developed for the AGV. Firstly, the lateral and roll motion dynamics of AGV are established, and the ARP problem is transformed into the yaw stability control with constraints. Subsequently, a faster fixed-time stable system-based FTASM composite controller is proposed to guarantee a fixed and faster convergence time of the yaw rate tracking error, such that the rollover stability will reach a region of permissible risk. The adoption of NAL enables the adaptive controller to automatically search the minimum switching gain satisfying the reaching condition of sliding mode, thus the conservative assumption constraint of the disturbance upper bound is released. In addition, an ISTO is developed to estimate the unknown disturbance to further improve the control robustness and attenuate the control chattering. The closed-loop stability analysis is rigorously given by Lyapunov theory. Finally, the performance of the proposed control strategy is validated by hardware-in-loop simulations with Adams and Matlab software and an actual steer-by-wire plant.

A machine learning-based algorithm for automated detection of frequency-based events in recorded time series of sensor data

Automated event detection methods, vital for monitoring technical systems via sensor data, are highly sought after in the automotive industry for tracing events in time series data. For assessing the active vehicle safety systems, a diverse range of driving scenarios is conducted. These scenarios involve the recording of the vehicle's behavior using external sensors, enabling the evaluation of operational performance. In such setting, automated detection methods not only accelerate but also standardize and objectify the evaluation by avoiding subjective, human-based appraisals in the data inspection. This study introduces a novel method for identifying frequency-based events in time series data. To this aim, the time series data is mapped to representations in the time-frequency domain, known as scalograms. After filtering scalograms to enhance relevant parts of the signal, an object detection model is trained to detect the desired event objects in the scalograms. By leveraging the accuracy of object detection networks in localizing objects, precise time intervals of events are identified. For the analysis of unseen time series data, events can be detected in their scalograms with the trained object detection model and are thereafter mapped back to the time series data to mark the corresponding time interval. The algorithm, evaluated on unseen datasets, achieves a precision rate of 0.97 in event detection, providing sharp time interval boundaries whose accurate indication by human visual inspection is challenging. Incorporating this method into the vehicle development process enhances the accuracy and reliability of event detection, which holds major importance for rapid testing analysis.

Secondary crash mitigation controller after rear-end collisions using reinforcement learning

Rear-end collisions result in a large number of casualties and property losses, and the serious injury risk in multiple impact accidents is much higher than that in single impact accidents. In this paper, we propose a novel controller to facilitate the prevention of secondary crashes after an initial rear-end collision, which expands the operational horizon of conventional vehicle active safety systems from preventive measures to post-event mitigation measures. Considering the complexity of the problem with multi-object synthesis optimization and vehicle nonlinear dynamics, this study combines the pre-collision control and post-collision control to reduce the initial crash loss and the subsequent control difficulty. The rule-based switching control and drift manipulation are embedded into the reinforcement learning algorithm to improve the training efficiency and control performance. The bench test results validate the superiority of the proposed controller over other strategies and algorithms in different rear-end collision scenarios.

Adaptive autonomous emergency braking model based on weather conditions

Objective Vehicle active safety systems can improve vehicle security by avoiding collisions. An autonomous emergency braking (AEB) system’s safety distance calculation is usually based on normal weather conditions. The AEB system’s early warning capabilities decrease during adverse weather conditions. Methods A multilayer perceptron (MLP) model is used to obtain data from accident and weather data sets. The MLP model is trained and the severity of accidents is predicted. The severity is used as a parameter to build an adaptive AEB system algorithm that considers adverse weather conditions. Results The adaptive AEB system algorithm increases safety and reliability under adverse weather conditions. Prescan and a driver-in-the-loop system are used to test the adaptive AEB model. Both tests show that the adaptive AEB model has better performance under adverse weather than the traditional AEB model. Conclusions The experimental results demonstrate that the adaptive AEB system can increase the safety distance in rainy weather and avoid collisions under hazy conditions.

Tire-Road Peak Adhesion Coefficient Estimation Based on Multisource Information Assessment

The tire-road peak adhesion coefficient (TRPAC) is defined as the ratio of the peak adhesion to the vertical load of the tire, which can characterize the ability of a tire to adhere to the road. Reliable TRPAC estimation can not only benefit the vehicle active safety system, but also serve the intelligent transportation system to improve the safety of traffic participants. Considering the problems of low estimation accuracy and poor real-time performance caused by low-quality sensor information in existing TRPAC estimation methods, a TRPAC fusion estimation framework based on the assessment of multisource information quality is proposed in this paper. Based on the observability theory of nonlinear systems, a quantitative indicator of dynamic information quality denoted as the excitation level is established. The region of effective excitation is defined as the criterion for starting and stopping the proposed dynamics-based fusion estimator for the longitudinal-lateral coupling condition. Considering occupant comfort and vehicle stability, an active enhancement method based on hierarchical model predictive control is designed to actively improve the excitation level. Based on the receding horizon optimization theory, a dynamics-image-based fusion estimator is proposed to make full use of visual and dynamic information. An adaptive fusion estimation strategy is then proposed to apply the proper estimation working mode according to the multisource information quality. The results of the simulation and vehicle test show that the proposed framework can still perform competitively when the quality of multisource information is poor and achieve reliable TRPAC estimation.

Real-Time Center of Gravity Estimation for Intelligent Connected Vehicle Based on HEKF-EKF

The vehicle center of gravity estimation is the key technology to the vehicle active safety system in intelligent connected vehicles. In this study, an integrated estimation approach for center of gravity (CG) combining Huber Extended Kalman Filter and Extended Kalman Filter (HEKF-EKF) is proposed. First, HEKF algorithm is used to estimate the distance between the CG and the front axle at the current time. Then, the CG height obtained by HEKF and EKF algorithms is weighted to obtain the optimal estimate value. Finally, the results show that the algorithm’s estimation convergence time is 2 s, its longitudinal position estimation error is less than 2%, and its center of gravity height estimation error is less than 3%. The longitudinal and vertical positions of the vehicle CG can be accurately estimated using this method. This method can help advance the development of active safety technology.

Retracted: Key Technologies of Vehicle Active Safety System Based on Computer Vision

Retracted: Key Technologies of Vehicle Active Safety System Based on Computer Vision

Multi-Sensor Fusion Based Estimation of Tire-Road Peak Adhesion Coefficient Considering Model Uncertainty

The tire-road peak adhesion coefficient (TRPAC), which cannot be directly measured by on-board sensors, is essential to road traffic safety. Reliable TRPAC estimation can not only serve the vehicle active safety system, but also benefit the safety of other traffic participants. In this paper, a TRPAC fusion estimation method considering model uncertainty is proposed. Based on virtual sensing theory, an image-based fusion estimator considering the uncertainty of the deep-learning model and the kinematic model is designed to realize the accurate classification of the road surface condition on which the vehicle will travel in the future. Then, a dynamics-image-based fusion estimator considering the uncertainty of visual information is proposed based on gain scheduling theory. The results of simulation and real vehicle experiments show that the proposed fusion estimation method can make full use of multisource sensor information, and has significant advantages in estimation accuracy, convergence speed and estimation robustness compared with other single-source-based estimators.

A new preprocessment method for road peak adhesion coefficient fusion estimation

Accurate estimation of road peak adhesion coefficient is of great significance in vehicle active safety systems. In order to prevent the vehicle from running out of control in actual driving process, the estimation algorithm should be able to adapt to various working conditions, and transmit estimated information of road peak adhesion coefficient to Electronic Control Unit (ECU) of the vehicle timely and accurately. Therefore, a new preprocessment method for the fusion estimation algorithm of road adhesion coefficient is proposed. The core of this method is the equal ratio relationship between the longitudinal, lateral peak adhesion coefficients and the utilization adhesion coefficient under adjacent typical roads. According to this relationship, this method accomplishes normalization of the tyre model in the form of introducing parameters from the outside, so that the tyre model can be combined with the filtering algorithm to be applied to estimation, which solves the problem that the precise tyre model cannot be used for road adhesion coefficient estimation due to its complex construction. This method can adapt to most of tyre models in the field of vehicle dynamics. In addition, the existing estimation algorithms need sufficient excitation (when the comprehensive slip ratio is 0.15–0.20) to estimate the accurate road peak adhesion coefficient. This method can greatly reduce the system error caused by insufficient road excitation, and can also obtain accurate estimation results when the excitation is insufficient. Finally, in order to verify the preprocessment method, the magic formula tyre model is used to describe the tyre characteristics. After processing by the preprocessment method, the road peak adhesion coefficient is estimated in combination with Unscented Kalman Filter (UKF). The high accuracy and timeliness of the estimated results in simulation and real vehicle tests verify the effectiveness of the preprocessment method.

Разработка методики обоснования конструкции и рабочих параметров рычажно–электромагнитной системы стабилизации поперечной устойчивости грузовых фургонов

The work is devoted to the issue of increasing the lateral stability, handling and safety of a car with a lever-electromagnetic system of transverse stabilization. The road safety of vehicles should improve with the rapid development of vehicle dynamics. Knowledge of vehicle roll stability data is important for the development of vehicle stability systems that will improve road safety. As a result of a review of trucks and passenger vehicles, it was found that the normal anti-roll bars are used to increase lateral stability. At present, higher-class passenger cars have begun to use active stabilizers (anti-roll bars), which provide more efficient alignment of the car when cornering. The main disadvantage of a conventional anti-roll bar is the reduction in suspension travel and does not provide the necessary smoothness when cornering and when maneuvering. These movements can lead to dangerous traffic situations. Thus, unfavorable driving conditions are manifested in terms of vehicle stability and controllability, as well as a smooth ride, which determines the level of comfort during heavy cornering and maneuvering. A new vehicle active safety system has been proposed, which makes it possible to increase lateral stability. The given method of substantiating the design and operating parameters of the lever-electromagnetic lateral stabilization system, which increase the lateral stability of light-duty vans, and the results of a study on the example of a GAZelle NEXT cargo van when cornering and maneuvering are given.

Key Technologies of Vehicle Active Safety System Based on Computer Vision

Due to the increase in the number of urban vehicles and the irregular driving behavior of drivers, urban accidents frequently occur, causing serious casualties and economic losses. Active vehicle safety systems can monitor vehicle status and driver status online in real time. Computer vision technology simulates biological vision and can analyze, identify, detect, and track the data and information in the captured images. In terms of driving accident warning and vehicle status warning, the vehicle active safety system has the potential to enhance the driver’s ability to detect abnormal situations, prolong the processing time, and reduce the risk of safety accidents. In this paper, an active safety system is developed according to the existing vehicle electronic system framework, and the early warning decision is made by evaluating the relationship between the minimum early warning distance and the actual vehicle distance, speed, and other factors. In this paper, the kinematics model established by the vehicle active safety early warning system is designed. The results found that, within 400 ms of the driver’s judgment time, for the driver with the reaction time of 0.6 s and 0.9 s, the following distance of 20 m does not constitute a safety threat and no braking operation is required.

An Obstacle Detection and Distance Measurement Method for Sloped Roads Based on VIDAR

Environmental perception systems can provide information on the environment around a vehicle, which is key to active vehicle safety systems. However, these systems underperform in cases of sloped roads. Real-time obstacle detection using monocular vision is a challenging problem in this situation. In this study, an obstacle detection and distance measurement method for sloped roads based on Vision-IMU based detection and range method (VIDAR) is proposed. First, the road images are collected and processed. Then, the road distance and slope information provided by a digital map is input into the VIDAR to detect and eliminate false obstacles (i.e., those for which no height can be calculated). The movement state of the obstacle is determined by tracking its lowest point. Finally, experimental analysis is carried out through simulation and real-vehicle experiments. The results show that the proposed method has higher detection accuracy than YOLO v5s in a sloped road environment and is not susceptible to interference from false obstacles. The most prominent contribution of this research work is to describe a sloped road obstacle detection method, which is capable of detecting all types of obstacles without prior knowledge to meet the needs of real-time and accurate detection of slope road obstacles.

Development and Validation of AEBS Anti-slip Control Model for In-wheel Motor Drive EV in AMESim Co-simulation with Matlab/Simulink

Abstract The Advanced Emergency Braking System (AEBS) is an intelligent vehicle active safety system to avoid certain sorts of collisions. Recent researches on AEBS emphasized radar, lasers and video camera technologies mostly, also controller developments were studied from Vehicle to Vehicle (V2V) to Vehicle to Pedestrian(V2P) and other aspects with different scenarios, aiming to enhance the active safety of the vehicle. However, most of the current systems focus little on braking performance of AEBS, especially for EV with distributed drive system, like in-wheel motors. In this paper, A 15 Degree of Freedom (DOF) distributed drive Electric Vehicle (EV) model was created and an Anti-slip Controller of AEBS based on the logic threshold method was built. To validate this control strategy, a co-simulation platform between Simulink and AMESim was established and vehicle braking dynamic of four in-wheel motor drive EV was evaluated. Results display that the designed controller not only enhanced the braking performance of AEBS under sudden braking on slippery surface condition, but also meet the requirement of UNECE braking regulation which has practical meanings in boosting active safety of a four in-wheel motor drive EV and development of industrialization.

Road Adhesion Coefficient Identification Method Based on Vehicle Dynamics Model and Multi-Algorithm Fusion

<div class="section abstract"><div class="htmlview paragraph">As an important input parameter of intelligent vehicle active safety technology, road adhesion coefficient is of great significance in autonomous collision avoidance, emergency braking and collision avoidance, and variable adhesion road motion control. Traditional recognition methods based on vehicle dynamics require large data volume and low solution accuracy. This paper proposes an adhesion coefficient recognition method based on Elman neural network and Kalman filter. By establishing a seven-degree-of-freedom vehicle dynamics model, dynamic parameters such as yaw angular velocity, longitudinal velocity, lateral velocity, and angular velocity of each wheel, which are easy to measure and strongly related to the road adhesion coefficient, are analyzed as the input of the neural network model. The square root cubature Kalman filter algorithm is used to remove the noise of the input of the neural network model, and Q-learning is used to strengthen learning, and the weight coefficient and bias coefficient of the model are continuously rewarded and punished, so that the predicted value does not exceed the normal range of values. The algorithm was pre-trained through CarSim/Simulink co-simulation, 9 sets of simulation conditions were established, and 4 sets of verification schemes were designed for identification and inspection. The average error of the simulation process is 4.93%, and the accuracy is 91.23%. Compared with the traditional Elman neural network, the average recognition error of this method is reduced by 2.23%, and the accuracy rate is increased by 9.83%. Real vehicle experiments were carried out on wet asphalt pavement and dry asphalt pavement, verifying the feasibility of the method. This paper proposes a road adhesion coefficient recognition method, which can improve the applicability of intelligent vehicle active safety systems to complex scenarios.</div></div>

A Hybrid Surrogate Modeling Approach for Vehicle Crash Simulations

Integrated vehicle safety – a combination of active and passive vehicle safety systems has the potential to increase occupant safety dramatically. To adapt the passive safety components such as belt and airbag to a given collision scenario, the system requires a priori knowledge of the collision consequences, i.e. via a camera, radar or lidar system. Therefore, real-time capable surrogate models are needed, that predict the vehicle decelerations during a crash with high accuracy. To combine the strength of both data-driven and physics-based surrogate modeling techniques, a hybrid surrogate model consisting of a machine learning-enhanced spring-damper-mass model, is developed in this work. Thereby, the spring-damper-mass model describes the deformation behavior of the vehicle structure. A neural network is then trained to predict the stiffness and damping parameters of the simplified physical model based on the impact angle, the velocity and the offset of the vehicles.

Calculation of electric vehicle battery system

Designing a vehicle is a complex multi-stage process and involves many factors which required carefully in calculation such as: the vehicle's dynamic, active and passive safety systems, connections on the vehicle, arrangement of devices, etc. The same principles when we design an electric vehicle. In this paper, the researcher showed a method to calculate battery system on an electric vehicle from a vehicle that using an internal combustion engine and still ensure the same output power as the original car. The car only uses Li-ion batteries, the car can travel on a single charge is nearly 300 km. The results have calculated the battery system to satisfy the capacity of the original vehicle. Through the calculated results can be applied on real cars.

The choice of rational complex of active safety systems for smart cars

The problem of ensuring road safety affects all elements of the Driver-Car-Road-Environment system. Smart cars equipped with enough traffic assistants can significantly improve road safety. Active vehicle safety systems, including intelligent driver assistance systems and assistants, perform similar road safety functions. With all the variety of possibilities for equipping cars with systems complexes, the need arises to assess the feasibility and profitability of installing a particular complex of systems. For this, it is proposed to apply the methods of multi-criteria assessment. As a result of calculations, the best options for the sets of systems that most widely cover the road situation have been identified.

A comparative study of the recursive least squares and fuzzy logic estimation methods for the measurement of road adhesion coefficient

ABSTRACT Vehicle active safety system is the hotspot of current research and development, and the road adhesion coefficient is one of the essential parameters in the development of automobile active safety system, which plays a pivotal role in automobile safety. To improve the real-time performance and accuracy of the road adhesion coefficient, this paper proposes different control methods and compares and analyzes them. To accurately estimate the road adhesion coefficient in real-time, an eight-degree-of-freedom vehicle model was adopted in this paper. According to the tire torque and wheel speed, the adhesion coefficient was estimated based on the second-order nonlinear extended state observer. The experimental data, such as slip rate, using the improved tire model, is based on the recursive least squares method with forgetting factor and fuzzy logic algorithm real-time of tire-road friction coefficient estimation. The results show that the observer can effectively observe utilisation adhesion coefficient, and both control algorithms can estimate the road adhesion coefficient in real-time, effectively and quickly. On different roads, the use of the recursive least squares algorithm resulted in higher estimation accuracy, better robustness, and better control effect than using a fuzzy logic algorithm.

Analysis of Vehicle Moving Parameters in Various Road Conditions

The safety of road users is one of the priority issues raised by those involved in vehicle design, latest passive and active safety systems, traffic organization or driver education. Nowadays, an important road safety problem is the behaviour of drivers in emergency situations. In order to measurably estimate the driving quality, parameters such as velocity, acceleration, the way and frequency of using the control pedals are quite often used. This article describes how to assess driver's behaviour based on measurements taken on the road. The frequency of different acceleration ranges during the vehicle drive was determined based on the results obtained. For the arbitrarily adopted acceleration range of - 0.5 - 0.5 m/s2, the driver's working time was over 77 percent on average, with the difference varying significantly between different route sections. Similarly, the study compares the driving times for other ranges of acceleration.