Browse Topic: Driver behavior

Items (661)
Find
Recommendation of Adaptive Safe Speed Limit for different driver Profiles using Deep Learning2025-01-8106To be published on 04/01/2025
Personalization and driver profiling have emerged as popular topics within the Advanced Driver Assistance Systems domain. Several features, like seat position adjustment and route selection deliver a customized experience for everyone. The systems often profile the driver and their preferences using Machine Learning algorithms to anticipate the needs of the driver. Within this field, personalization of speed limits is not explored to the fullest. Currently, speed limits are the same for all drivers, irrespective of their driving style. Even when the speed limits are designed to address adverse weather conditions, they do not consider the driver’s capabilities. Thus, we propose a novel idea to recommend a safe speed limit based on the driving style and the surrounding environmental conditions. The architecture consists of Long Short-Term Memory based neural networks that capture the driver’s traits based on risks of the environment. The system identifies if a driver is uncomfortable in
Perumal, Rathapriya, Chouhan, Madhvendra, Rangarajan, Rishi
Technical Paper
Integrated Multimodal System for Real-Time Driver Fatigue Detection and Cognitive Load Assessment2025-01-8076To be published on 04/01/2025
Paying attention to safety while traveling in a vehicle was essential. One of the greatest barriers to travel safety is driver fatigue. In order to tackle this issue, we designed an all-inclusive hardware and software environment for analyzing driver interaction with highly automated vehicles, providing a special emphasis on detection of driver’s cognitive load and providing appropriate alerts in advance. There are three essential types of measurements included in this system. First, the facial features of the driver are measured through the use of Driver Behavior Measurements (DBM) which are made from RGB and IR cameras that capture the eye aspect ratio (EAR), mouth aspect ratio (MAR), pupil circularity (PUC), and mouth to eye aspect ratio (MOE), Most of these measurements have been shown to work under normal as well as more extreme conditions including low light conditions or use of sunglasses by the drivers. Secondly, Vehicle Dynamics Measurements (VDM) is performed by an Inertial
Jirjees, Abdullah, Rahman, Taufiq, Farhani PhD, Ghazal, Singh, Daniel, Charlebois, Dominique
Technical Paper
A Novel Hybrid Approach for Segmenting Driver Based on their Driving Style2025-01-8205To be published on 04/01/2025
Drivers present a diverse landscape with their distinct personalities, preferences, and driving habits influenced by many factors. While drivers exhibit a wide range of behaviors, identifiable patterns in driving styles enable the classification of drivers into discrete segments. Discrete segmentation provides a practical and effective way to categorize and address the differences in driving style. The segmentation approach offers many benefits, including simplification, measurement, proven methodology, customization, and safety. Numerous studies have investigated driving style classification using real-world vehicle data. These studies employed various methods to identify and categorize distinct driving patterns, including naturalist differences in driving and field operational tests. This paper presents a novel hybrid approach for segmenting driver behavior based on their driving patterns. We leverage vehicle acceleration data to create granular driver segments by combining event
Chavan, Shakti Pradeep, Chinnam, Ratna Babu
Technical Paper
A Comparative Analysis of Acceleration and Deceleration Profiles for Aggressive Driving Styles and Fuel Economy Test Cycles2025-01-8605To be published on 04/01/2025
Efficient and sustainable transportation in urban environments depends on understanding driving behaviors, and their implications. This study explores into the distinction between aggressive and non-aggressive driving patterns, leveraging an on-road driving dataset provided by an automotive company. By contrasting this data with established Fuel Economy cycles from United States Environmental Protection Agency (EPA) and employing curve-fitting techniques, the research not only reveals driving patterns but also predicts potential behaviors in unfamiliar scenarios. Results show significantly different acceleration profile patterns between different driving behaviors which has serious impact in fuel economy and environmental wellness. The findings highlights the environmental impact of driving behaviors, paving the way for environmentally responsible policy recommendations and sustainable driving practices
Padmanaban, Gandhimathi, Feng, Fred, Dai, Edward, Saini, Ankit, Hu, Guopeng, Zhao, Yanan
Technical Paper
Driving Under the Influence: A Review of Fitness to Drive, Drug-Induced Impairments, and Simulation Testing2025-01-8666To be published on 04/01/2025
This literature review examines the concept of fitness to drive and how it can be affected by drugs consumption. The Systematic Literature Review (SLR) methodology is used to analyse the Literature, exploiting Scopus, Consensus and Elicit databases. Firstly, the paper presents research across mechanical engineering and related fields to establish a comprehensive and multidisciplinary understanding of how fitness to drive is evaluated. This includes a definition of the term and the identification of the protocols used for its assessment. Secondly, the emphasis is on the impact of drug use on driving performance, excluding alcohol and cannabis. Driving simulators represent a valid possibility for analysing such effects in a safe, controlled and replicable environment. They are presented considering their most relevant characteristics and the measurements collected for the driver's state analysis. Key findings reveal a lack of a comprehensive taxonomy for fitness to drive, resulting in
Uccello, Lorenzo, Mastinu, Gianpiero, Elli, Chiara, Novella, Alessio, Nobili, Alessandro, Pasina, Luca
Technical Paper
Driver Distraction Recognition Based on the Information Bottleneck Theory and Graph Convolutional Networks2025-01-8112To be published on 04/01/2025
Driver distraction remains a leading cause of traffic accidents, making its recognition critical for enhancing road safety. In this paper, we propose a novel method that combines the Information Bottleneck (IB) theory with Graph Convolutional Networks (GCNs) to address the challenge of driver distraction recognition. Our approach introduces a 2D pose estimation-based action recognition network that effectively enhances the retention of relevant information within neural networks, compensating for the limited data typically available in real-world driving scenarios. The network is further refined by integrating the CTR-GCN (Channel-wise Topology Refinement Graph Convolutional Network), which models the dynamic spatial-temporal relationships of human skeletal data. This enables precise detection of distraction behaviors, such as using a mobile phone, drinking water, or adjusting in-vehicle controls, even under constrained input conditions. The IB theory is applied to optimize the trade
Zhang, Ji, Bai, Yakun
Technical Paper
Real-world emissions in a high-altitude city: A comparison between LPG and gasoline- fueled cars2025-01-8494To be published on 04/01/2025
To study the real driving emissions characteristics of light-duty vehicles fueled with liquefied petroleum gas (LPG) and gasoline in the high-altitude city, experimental investigations were performed on two LPG taxis and three gasoline passenger cars in Lhasa using a portable emission measurement system (PEMS). The results reveal that the emission factors of CO2, CO, NOx, and HC of LPG taxis are (159.19±11.81), (18.38±9.73), (1.53±0.46), and (1.27±0.99) g/km, and those of gasoline cars are (223.51±23.1), (1.51±0.68), (0.27±0.16), and (0.06±0.04) g/km, respectively. The emissions show strong relationships with driving modes, which are considerably affected by driving behaviors. Furthermore, as vehicle speeds increase, the emission factors of both LPG taxis and gasoline cars decrease. The emission rates of both types of vehicles are low and change slightly at vehicle specific power (VSP) of 0 kW/t or below; after that, these rates slowly increase initially, and then increase rapidly with
Lyu, Meng, Xu PhD, Yan, Huang, Meihong, Wang, Yunjing
Technical Paper
Research on Dangerous Driving Behavior Recognition Algorithm Based on LSTM2025-01-8204To be published on 04/01/2025
To address the issue of high accident rates in road traffic due to dangerous driving behaviors, this paper proposes a recognition algorithm for dangerous driving behaviors based on Long Short-Term Memory (LSTM) networks. Compared with traditional methods, this algorithm innovatively integrates high-frequency trajectory data, historical accident data, weather data, and features of the road network to accurately extract key temporal features that influence driving behavior. By modeling the behavioral data of high-accident-prone road sections, a comprehensive risk factor is consistent with historical accident-related driving conditions, and assess risks of current driving state. The study indicates that the model, in the conditions of movement track, weather, road network and conditions with other features, can accurately predict the consistent driving states in current and historical with accidents, to achieve an accuracy rate of 85% and F1 score of 0.82. It means the model can
Huang, Yinuo
Technical Paper
A Path Tracking Control Method Considering Vehicle Stability and Road Curvature2025-01-8038To be published on 04/01/2025
The current research on path tracking control focuses on the improvement of tracking accuracy, while ignoring the comfort of the passengers inside the vehicle. Improving comfort can be achieved by improving the algorithm in two aspects: imitating human driving behavior and considering vehicle driving stability. Therefore, this paper proposes a path tracking control method considering vehicle stability indicators and road curvature changes, with the following main content: first, vehicle dynamics modeling is performed, and its dynamics characteristics are analyzed to extract key indicators related to the enhancement of ride comfort in the driving process. This includes combining the human comfort evaluation index of whole-body vibration and the vehicle maneuverability index, and calculating the interval of the relevant vehicle dynamics indexes for the case where the passenger comfort is the highest in the vehicle driving process. Second, the path tracking controller is designed by
lu, jun, Zeng, Dequan, Hu, Yiming, Wang, Xiaoliang, liu, dengcheng, Jiang, Zhiqiang
Technical Paper
Integrated Driver Health Monitoring System With Real-time Alerts Using In-Cabin Sensors and Vehicle Telematics2025-28-0195To be published on 02/07/2025
Automotive industries focus on driver safety leading to raising improvements and advancements in Advanced Driver Assistance Systems (ADAS) to avoid collisions and provide safety and comfort to the drivers. This paper proposes a novel approach toward Driver health and fatigue monitoring systems that uses cabin cameras and biometric sensors communicating continuously with vehicle telematics systems to enhance real-time monitoring and predictive intervention. The data from the camera and biometric sensors is sent to the machine learning algorithm (LSboost) which processes the data and if anything is wrong concerning the driver's behavior then immediately it communicates with vehicle telematics and sends information to the emergency services. This approach enhances driver safety and reduces accidents caused due to health-related driver impairment. This system comprises several sensors and fusion algorithms are applied between different sensors like cabin camera and biometric sensors, all
Bhargav, Matavalam
Technical Paper
Physical and Cognitive Driver Reactions Characterization in Response to Active Safety Systems: A Preliminary Study2024-36-013612/20/2024
Advanced Driver Assistance Systems (ADAS) are technologies that automate, facilitate, and improve the vehicle’s systems. Indeed, these systems directly interfere with braking, acceleration, and drivability of driving operations. Thus, the use of ADAS directly reflects the psychology behind driving a vehicle, which can have an automation level that varies from fully manual (Level 0) to fully autonomous (Level 5). Even though ADAS technologies provide safer driving, it is still a challenge to understand the complexity of human factors that influence and interact with these new technologies. Also, there has been limited exploration of the correlation between the physical and cognitive driver reactions and the characteristics of Brazilian roads and traffic. Therefore, the present work sought to establish a preliminary investigation into a method for evaluating the driving response profile under the influence of ADAS technologies, such as Lane Centering and Forward Collision Warning, on
Castro, Gabriel M., Silva, Rita C., Miosso, Cristiano J., Oliveira, Alessandro B. S.
Technical Paper
Trajectory Planning and Tracking Control for Single Lane Changing with Different Driving Styles of Intelligent Vehicles Based on Seventh-Degree Polynomial12-08-03-002812/14/2024
Single lane changing is one of the typical scenarios in vehicle driving. Planning an appropriate lane change trajectory is crucial in autonomous and semi-autonomous vehicle research. Existing polynomial trajectory planning mostly uses cubic or quintic polynomials, neglecting the lateral jerk constraints during lane changes. This study uses seventh-degree polynomials for lane change trajectory planning by considering the vehicle lateral jerk constraints. Simulation results show that the utilization of the seventh-degree method results in a 41% reduction in jerk compared to the fifth-degree polynomial. Furthermore, this study also proposes lane change trajectory schemes that can cater to different driving styles (e.g., safety, efficiency, comfort, and balanced performance). Depending on the driving style, the planned lane change trajectory ensures that the vehicle achieves optimal performance in one or more aspects during the lane change process. For example, with the trajectory that
Lai, Fei, Huang, Chaoqun
Journal Article
Human-like Behavior Strategy for Autonomous Vehicles Considering Driving Styles2024-01-704612/13/2024
Autonomous driving technology plays a crucial role in enhancing driving safety and efficiency, with the decision-making module being at its core. To achieve more human-like decision-making and accommodate drivers with diverse styles, we propose a method based on deep reinforcement learning. A driving simulator is utilized to collect driver data, which is then classified into three driving styles—aggressive, moderate, and conservative—using the K-means algorithm. A driving style recognition model is developed using the labeled data. We then design distinct reward functions for the Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and Soft Actor-Critic (SAC) algorithms based on the driving data of the three styles. Through comparative analysis, the SAC algorithm is selected for its superior performance in balancing comfort and driving efficiency. The decision-making models for different styles are trained and evaluated in the SUMO simulation environment. The results indicate that
Shen, Chuanliang, Zhang, Longxu, Shi, Bowen, Ma, Xiaoyuan, Li, Yi, Hu, Hongyu
Technical Paper
Interaction-Aware Deep Reinforcement Learning Approach Based on Hybrid Parameterized Action Space for Autonomous Driving2024-01-703512/13/2024
Learning-based motion planning methods such as reinforcement learning (RL) have shown great potential of improving the performance of autonomous driving. However, comprehensively ensuring safety and efficiency remain a challenge for motion planning technology. Most current RL methods output discrete behavioral action or continuous control action, which lack an intuitive representation of the future motion and then face the problems with unstable or reckless driving behavior. To address these issues, this work proposes an interaction-aware reinforcement learning approach based on hybrid parameterized action space for autonomous driving in lane change scenario. The proposed method can output high-level feasible trajectory and low-level actuator control command to control the vehicle’s motion together. Meanwhile, the reward functions for the local traffic environment are designed to evaluate the effect of the interaction between ego vehicle and surrounding vehicles. The contributions of
Li, Zhuoren, Jin, Guizhe, Yu, Ran, Leng, Bo, Xiong, Lu
Technical Paper
A Driving Behavior Decision Method Based on Gradient Boosting Tree Algorithm2024-01-703012/13/2024
In order to reduce the incidence of traffic accidents and improve passengers’ driving experience, intelligent driving technology has attracted more and more attention. The core content of intelligent driving technology includes environment perception, behavior decision-making and control follow-up. Simulating driver’s behavior decision-making based on multi-source heterogeneous environment information is the key to liberate drivers and become the focus and difficulty of intelligent driving technology. Aiming at this key problem, this paper presents a design method of driving behavior decision maker based on machine learning after fuzzy classification of historical data. Firstly, 1000 sets of driving environment-decision results database are generated randomly according to driving rules and driving state. A fuzzy classification rule is established to classify driving environment information such as speed and relative distance. Then, a driving behavior decision maker is designed based on
Li, Hongluo, Xia, Hongyang, Huang, Yongxian, Xu, You, Xu, Wei
Technical Paper
Driving Behavior Modeling Based on Inverse Reinforcement Learning2024-01-702912/13/2024
With the advancement of intelligent driving technology, today’s smart vehicles must not only make accurate and safe driving decisions but also exhibit high human-likeness to ensure better acceptance from people. Developing vehicle behavior models with increased human-likeness has become a significant industry focus. However, existing vehicle behavior models often struggle to balance human-likeness and interpretability. While some researchers use inverse reinforcement learning (IRL) to model vehicle behavior, ensuring both human-likeness and a degree of interpretability, challenges such as reward function design difficulties and low human-likeness in background vehicle modeling persist. This study addresses these issues by focusing on highway scenarios without on-ramps, specifically following and lane-changing behaviors, using the CitySim dataset. IRL is employed to create a vehicle behavior model with improved human-likeness, utilizing a linear reward function to capture driver
Xu, Xiaobin, Han, Wei, Leng, Bo, Xiong, Lu
Technical Paper
Validation Methodology of Different Driver Monitoring Systems Using a Modular Motion Drive Simulator2024-28-026312/05/2024
In India, Driver Drowsiness and Attention Warning (DDAW) system-based technologies are rising due to anticipation on mandatory regulation for DDAW. However, readiness of the system to introduce to Indian market requires validations to meet standard (Automotive Industry Standard 184) for the system are complex and sometimes subjective in nature. Furthermore, the evaluation procedure to map the system accuracy with the Karolinska sleepiness scale (KSS) requirement involves manual interpretation which can lead to false reading. In certain scenarios, KSS validation may entail to fatal risks also. Currently, there is no effective mechanism so far available to compare the performance of different DDAW systems which are coming up in Indian market. This lack of comparative investigation channel can be a concerning factor for the automotive manufactures as well as for the end-customers. In this paper, a robust validation setup using motion drive simulator with 3 degree of freedom (DOF) is
Raj, Prem raj Anand, Selvam, Dinesh Kumar, Thanikachalam, Ganesh, Sivakumar, Vishnu
Technical Paper
Customized Vehicle Feature Control through Driver Recognition Technology2024-28-021912/05/2024
This paper presents a novel approach for customizing vehicle features through driver recognition technology. The system combines Cultural Adaptive Face Recognition (CAFR) using FaceNet and Contrastive Language-Image Pretraining (CLIP) models, along with OpenCV, to recognize drivers and customize vehicle feature control. To identify a driver, the system compares their features against a pre-existing database using FaceNet, which generates efficient face embeddings. The driver image and contextual information collected is processed by OpenAI’s CLIP to generate CLIP embeddings which leverages multimodal learning. FaceNet and CLIP embeddings’ fusion is done and are stored in the Qdrant search database for efficient retrieval and similarity searches. Once the driver is recognized, the system adjusts vehicle features such as temperature settings, music selections, and seat adjustments according to the driver's preferences. Additionally, the system implements optical character recognition
Marimuthu, Ranjithkumar
Technical Paper
EFFECTS OF AUGMENTED SITUATIONAL AWARENESS ON DRIVER TRUST IN SEMI-AUTONOMOUS VEHICLE OPERATION2024-01-365411/15/2024
ABSTRACT Although autonomy has the potential to help military drivers travel safely while performing other tasks, many drivers refuse to rely on the technology. Military drivers sometimes fail to leverage a vehicle’s autonomy because of a lack of trust. To address this issue, the current study examines whether augmenting the driver’s situational awareness will promote their trust in the autonomy. Results of this study are expected to provide new insights into promoting trust and acceptance of autonomy in military settings
Petersen, Luke, Tilbury, Dawn, Robert, Lionel, Yang, Xi Jessie
Technical Paper
MODELING OFF-ROAD ROLLOVER USING TERRAMECHANICS FOR REAL TIME DRIVING SIMULATOR2024-01-348711/15/2024
ABSTRACT There have been several hundred rollovers in military vehicles in the last decade of deployment, of which approximately fifty percent are fall-based that occur during off-road operations. Off-road fall-based rollovers occur at lower speeds when the soft road gives way underneath the vehicle on one side as the soil is unable to support the vehicle load. During these sudden events, drivers, who are generally not prepared, often make impromptu driving decisions that quickly lead to rollover situations. A real-time driving simulator can be instrumental in reducing rollover incidents when used as a training tool. The current research takes a comprehensive approach in understanding this rollover phenomenon, and develops a novel real-time terramechanics approach with a vehicle dynamics model validated on the N-post shaker. TARDEC’s Ride Motion Simulator is then used to examine rollover performance in response to various driving styles under various soil conditions. The results are
Singh, Amandeep, Holtz, Dale A, Megiveron, Michael, Paul, Victor
Technical Paper
THE INFLUENCE OF RISK ON DRIVER TRUST IN AUTONOMOUS DRIVING SYSTEMS2024-01-374811/15/2024
ABSTRACT Autonomous driving systems (ADS) in autonomous and semi-autonomous vehicles have the potential to improve driving safety and enable drivers to perform non-driving tasks concurrently. Drivers sometimes fail to fully leverage a vehicle’s autonomy because of a lack of trust. To address this issue, the present study examined the influence of risk on drivers’ trust. Subject tests were conducted to evaluate the effects of combined internal and external risk, where participants drove a simulated semi-autonomous vehicle and completed a secondary task at the same time. Results of this study are expected to provide new insights into promoting trust and acceptance of autonomy in both military and civilian settings
Petersen, Luke, Zhao, Huajing, Tilbury, Dawn M., Yang, X. Jessie, Robert, Lionel P.
Technical Paper
FAST INCREMENTAL LEARNING FOR AUTONOMOUS GROUND NAVIGATION2024-01-355611/15/2024
ABSTRACT A promising approach to autonomous driving is machine learning. In machine learning systems, training datasets are created that capture the sensory input to a vehicle as well as the desired response. One disadvantage of using a learned navigation system is that the learning process itself may require both a huge number of training examples and a large amount of computing. To avoid the need to collect a large training set of driving examples, we describe a system that takes advantage of the immense number of training examples provided by ImageNet, but at the same time is able to adapt quickly using a small training set for the driving environment
Provodin, Artem, Torabi, Liila, Muller, Urs, Flepp, Beat, Sergio, Michael, Žbontar, Jure, LeCun, Yann, Jackel, L. D.
Technical Paper
A HUMAN FACTORS ALERTNESS MODULE STUDY VIA BRAIN TOMOGRAPHY2024-01-309111/15/2024
ABSTRACT This study investigated the effect of an innovative chilling device that intends to make subjects more alert and less sleepy. Tests were conducted using a variety of methods including electric-encephalography (EEG) brain tomography. A series of behavioral tests showed an increase in alertness, changes of body temperatures, and performance indicators after usage of this device. The device chills specific areas of the body and disrupts the body’s ability to self-regulate core body temperature. The induced temperature shifts may reduce the body’s capability to go to sleep. Physiological changes and brain wave indicators of alertness were also reviewed in this paper. A full study of alertness indicators in expanded driver simulations is recommended. As for future application of this device to Human Factors aspects, this device may have the potential to enhance alertness in the human dimension of machine operation of manned and unmanned assets with further improvement
Hsieh, Li, Ranalli, RJ
Technical Paper
Evaluating the Impact of Velocity Advisory Systems on Fuel Economy of Passenger Vehicles: A Driver Simulator Study2024-01-427511/05/2024
With increasing emphasis on sustainable mobility and efficient energy use, advanced driver assistance systems (ADAS) may potentially be utilized to improve vehicles’ energy efficiency by influencing driver behavior. Despite the growing adoption of such systems in passenger vehicles for active safety and driver comfort, systematic studies examining the effects of ADAS on human driving, in the context of vehicle energy use, remain scarce. This study investigates the impacts of a driver speed advisory system on energy use in a plug-in hybrid electric vehicle (PHEV) through a controlled experiment using a driving simulator. A mixed urban highway driving environment was reconstructed from digitalizing a real-world route to observe the human driver’s behavior with and without driving assistance. The advisory system provided drivers with an optimized speed profile, pre-calculated for the simulated route to achieve maximum energy efficiency. Participants were instructed to navigate the
Telloni, Marcello, Farrell, James, Mendez, Luis, Ozkan, Mehmet Fatih, Chrstos, Jeffrey, Canova, Marcello, Stockar, Stephanie
Technical Paper
A Driver Safety System Using Raspberry Pi and Computer Vision2024-28-003010/17/2024
Road safety remains a critical concern globally, with millions of lives lost annually due to road accidents. In India alone, the year 2021 witnessed over 4,12,432 road accidents resulting in 1,53,972 fatalities and 3,84,448 injuries. The age group most affected by these accidents is 18-45 years, constituting approximately 67% of total deaths. Factors such as speeding, distracted driving, and neglect to use safety gear increases the severity of these incidents. This paper presents a novel approach to address these challenges by introducing a driver safety system aimed at promoting good driving etiquette and mitigating distractions and fatigue. Leveraging Raspberry Pi and computer vision techniques, the system monitors driver behavior in real-time, including head position, eye blinks, mouth opening and closing, hand position, and internal audio levels to detect signs of distraction and drowsiness. The system operates in both passive and active modes, providing alerts and alarms to the
Ganesh, Katta, Prasad, Gvl
Technical Paper
Solutions for Making Group Travel More Connected and Easy2024-28-002910/17/2024
The integration of Vehicle-to-Everything (V2X) communication technologies holds immense potential to revolutionize the automotive industry by enabling vehicles to communicate with each other (V2V) and with infrastructure (V2I). This paper investigates the feasibility of V2X and V2I communication, exploring available communication methods for vehicles to communicate. Many a times people like to travel together and it involves more than one vehicle travelling together, in such cases they often get lost the information about fellow vehicles due to the traffic condition and different driving behaviors of the individual driver. In such cases they communicate over phones to get to know the location of fellow vehicle or keep sharing their live locations. In such cases they don’t just follow the destination in maps also they should be continuously monitoring their fellow vehicles position. It is important for vehicles travelling in group to have communication and be connected so that they know
Barre, Deva Harshitha
Technical Paper
Personalized Design of Variable Transmission Ratio and Selection Switching Strategies Considering Drivers’ Steering Characteristics10-08-04-002809/14/2024
In order to meet the driving characteristics and needs of different types of drivers and to improve driving comfort and safety, this article designs personalized variable transmission ratio schemes based on the classification results of drivers’ steering characteristics and proposes a switching strategy for selecting variable transmission ratio schemes in response to changes in driver types. First, data collected from driving simulator experiments are used to classify drivers into three categories using the fuzzy C-means clustering algorithm, and the steering characteristics of each category are analyzed. Subsequently, based on the steering characteristics of each type of driver, suitable speed ranges, steering wheel travel, and yaw rate gain values are selected to design the variable transmission ratio, forming personalized variable transmission ratio schemes. Then, a switching strategy for variable transmission ratio schemes is designed, using a support vector machine to build a
Chen, Chen, Zheng, Hongyu, Zong, Changfu
Journal Article
Comprehensive Study on Challenges to Introduce Autonomous Emergency Braking (AEBS) Feature in Indian Perspective2024-01-305009/08/2024
India is a diverse country in terms of road conditions, road maintenance, traffic conditions, traffic density, quality of traffic which implies presence of agricultural tractors, bullock carts, autos, motor bikes, oncoming traffic in same lane, vulnerable road users (VRU) walking in the same lanes as vehicles, VRU’s crossing roads without using zebra crossings etc. as additional traffic quality deterrents in comparison to developed countries. The braking capacity of such vivid road users may not be at par with global standards due to their maintenance, loading beyond specifications, driver behavior which includes the tendency to maintain a close gap between the preceding vehicle etc. which may lead to incidents specifically of rear collisions due to the front vehicle going through an emergency braking event. The following paper provides a comprehensive study of the special considerations or intricacies in implementation of Autonomous Emergency Braking (AEBS) feature into Indian traffic
Kartheek, Nedunuri, Khare, Rashmita, Sathyamurthy, Sainathan, Manickam, Praveenkumar, Kuchipudi, Venkata Sai Pavan
Technical Paper
Virtual Identification of Driver-Specific Characteristics for Assisted Lateral Control2024-01-509009/02/2024
Advanced driver assistance systems (ADAS) have become an integral part of today’s vehicle development. These systems are designed to provide secondary support to the driver, but the driver is primarily responsible for the driving task, e.g., lane-keeping assist (LKA). The driving setup and testing of these LKA systems is very time-consuming and usually applied in the car, based on experiences and subjective evaluation. This results in a cost-intensive calibration of the system. An objective-based calibration procedure can increase efficiency. For a targeted calibration of the system, it is necessary to define and identify key performance indicators (KPIs), which are able to describe the secondary support in sufficient detail. Usually, subjective feelings are used to derive KPIs. Vice versa, there are no results on how to design an LKA without any subjective assessment, before the calibration. With this in mind, this paper is focused on filling this unknown aspect by using virtual
Baumann, Benjamin, Iatropolous, Jannes, Panzer, Anna, Henze, Roman
Technical Paper
Driving Intention Recognition Model for Highway Ramp-Merging Scene12-08-02-001607/24/2024
Driving safety in the mixed traffic state of autonomous vehicles and conventional vehicles has always been an important research topic, especially on highways where autonomous driving technology is being more widely adopted. The merging scenario at highway ramps poses high risks with frequent vehicle conflicts, often stemming from misperceived intentions [1]. This study focuses on autonomous and conventional vehicles in merging scenarios, where timely recognition of lane-changing intentions can enhance merging efficiency and reduce accidents. First, trajectory data of merging vehicles and their conflicting vehicles were extracted from the NGSIM open-source database in the I-80 section. The segmented cubic polynomial interpolation method and Savitzky–Golay filtering are utilized for data outlier removal and noise reduction. Second, the processed trajectory data were used as input to a hybrid Gaussian hidden Markov (GMM-HMM) model for driving intention classification, specifically lane
Ren, You, Wang, Xiyao, Song, Jiaqi, Lu, Wenyang, Li, Penglong, Li, Shangke
Journal Article
Driver–Steering Wheel Interaction during Cornering10-08-03-002407/24/2024
This research aims at understanding how the driver interacts with the steering wheel, in order to detect driving strategies. Such driving strategies will allow in the future to derive accurate holistic driver models for enhancing both safety and comfort of vehicles. The use of an original instrumented steering wheel (ISW) allows to measure at each hand, three forces, three moments, and the grip force. Experiments have been performed with 10 nonprofessional drivers in a high-end dynamic driving simulator. Three aspects of driving strategy were analyzed, namely the amplitudes of the forces and moments applied to the steering wheel, the correlations among the different signals of forces and moments, and the order of activation of the forces and moments. The results obtained on a road test have been compared with the ones coming from a driving simulator, with satisfactory results. Two different strategies for actuating the steering wheel have been identified. In the first strategy, the
Previati, Giorgio, Mastinu, Gianpiero, Gobbi, Massimiliano
Journal Article
Research on Driver Style Recognition Based on GA-K-Means and PSO-SVM12-07-04-002607/22/2024
This article aims to address the challenge of recognizing driving styles, a task that has become increasingly complex due to the high dimensionality of driving data. To tackle this problem, a novel method for driver style clustering, which leverages the principal component analysis (PCA) for dimensionality reduction and an improved GA-K-means algorithm for clustering, is proposed. In order to distill low-dimensional features from the original dataset, PCA algorithm is employed for feature extraction and dimensionality reduction. Subsequently, an enhanced GA-K-means algorithm is utilized to cluster the extracted driving features. The incorporation of the genetic algorithm circumvents the issue of the model falling into local optima, thereby facilitating effective driver style recognition. The clustering results are evaluated using the silhouette coefficient, Calinski–Harabasz (CH) index, and GAP value, demonstrating that this method yields more stable classification results compared to
Chen, Yinghao, Wu, Guangqiang, Wu, Jian, Wang, Hao
Journal Article
Exploring User Acceptance of Autonomous Vehicles: Impact of Driver and Vehicle Styles12-08-02-001507/18/2024
Autonomous vehicles (AVs) provide an effective solution for enhancing traffic safety. In the last few years, there have been significant efforts and progress in the development of AVs. However, the public acceptance has not fully kept up with technological advancements. Public acceptance can restrict the growth of AVs. This study focuses on investigating the acceptance and takeover behavior of drivers when interacting with AVs of different styles in various scenarios. Manual and autonomous driving experiments were designed based on the driving simulation platform. To avoid subjective bias, principal component analysis (PCA) and the Gaussian mixture model (GMM) were used to classify driving styles. A total of 34 young participants (male-dominated) were recruited for this study. And they were classified into three driving styles (aggressive, moderate, and conservative). And AV styles were designed into three corresponding categories according to the different driving behavior
Li, Guanyu, Yu, Wenlin, Chen, Xizheng, Wang, Wuhong, Guo, Hongwei, Jiang, Xiaobei
Journal Article
SAE TOMORROW TODAY UNPLUGGED: Can Autonomous Vehicles Eliminate Distracted Driving1346507/10/2024
Distracted driving is an epidemic that shows no signs of slowing down. But autonomous vehicles could be the cure. As NHTSA gets ready to publish new data on distracted driving, hear from Grayson Brulte, Host of SAE Tomorrow Today, on why the addiction to our smart phones must be dealt with--and how AVs can help. Have your own thoughts on this topic? We'd love to hear from you! Share your comments, questions or ideas for future topics with Grayson on Twitter or send them to podcast@sae.org
Hineman, Marcie
Podcast
Set-Up of an In-Car System for Investigating Driving Style on the Basis of the 3D-Method2024-01-300107/02/2024
Investigating human driver behavior enhances the acceptance of the autonomous driving and increases road safety in heterogeneous environments with human-operated and autonomous vehicles. The previously established driver fingerprint model, focuses on the classification of driving styles based on CAN bus signals. However, driving styles are inherently complex and influenced by multiple factors, including changing driving environments and driver states. To comprehensively create a driver profile, an in-car measurement system based on the Driver-Driven vehicle-Driving environment (3D) framework is developed. The measurement system records emotional and physiological signals from the driver, including the ECG signal and heart rate. A Raspberry Pi camera is utilized on the dashboard to capture the driver's facial expressions and a trained convolutional neural network (CNN) recognizes emotion. To conduct unobtrusive ECG measurements, an ECG sensor is integrated into the steering wheel
Ji, Dejie, Flormann, Maximilian, Warnecke, Joana M., Henze, Roman, Deserno, Thomas M.
Technical Paper
A Novel Approach for the Safety Validation of Emergency Intervention Functions Using Extreme Value Estimation2024-01-299307/02/2024
As part of the safety validation of advanced driver assistance systems (ADAS) and automated driving (AD) functions, it is necessary to demonstrate that the frequency at which the system exhibits hazardous behavior (HB) in the field is below an acceptable threshold. This is typically tested by observation of the system behavior in a field operational test (FOT). For situations in which the system under test (SUT) actively intervenes in the dynamic driving behavior of the vehicle, it is assessed whether the SUT exhibits HB. Since the accepted threshold values are generally small, the amount of data required for this strategy is usually very large. This publication proposes an approach to reduce the amount of data required for the evaluation of emergency intervention systems with a state machine based intervention logic by including the time periods between intervention events in the validation process. For this purpose, a proximity measure that indicates how close the system is to an
Schrimpf, Malte, Betschinske, Daniel, Peters, Steven
Technical Paper
Analysis of Human Driving behavior with Focus on Vehicle Lateral Control2024-01-299707/02/2024
The optimization and further development of automated driving functions offers great potential to relieve the driver in various driving situations and increase road safety. Simulative testing in particular is an indispensable tool in this process, allowing conclusions to be drawn about the design of automated driving functions at a very early stage of development. In this context, the use of driving simulators provides support so that the driving functions of tomorrow can be experienced in a very safe and reproducible environment. The focus of the acceptance and optimization of automated driving functions is particularly on vehicle lateral control functions. As part of this paper, a test person study was carried out regarding manual vehicle lateral control on the dynamic vehicle road simulator at the Institute of Automotive Engineering. The basis for this is the route generation as a result of the evaluation of curve radii from several hundred thousand kilometers of real measurement
Iatropoulos, Jannes, Panzer, Anna, Henze, Roman
Technical Paper
Deep Learning Algorithms for Longitudinal Driving Behavior Prediction: A Comparative Analysis of Convolutional Neural Network and Long–Short-Term Memory Models12-07-04-002506/13/2024
In the realm of transportation science, the advent of deep learning has propelled advancements in predicting longitudinal driving behavior. This study explores the application of deep neural network architectures, specifically long–short-term memory (LSTM) and convolutional neural networks (CNNs), recognized for their effectiveness in handling sequential data. Using a 3-s temporal window that includes past vehicle progress, speed, and acceleration, the proposed model, a hybrid LSTM–CNN architecture, predicts the vehicle’s speed and progress for the next 6 s. The approach achieves state-of-the-art performance, particularly within a 4 s horizon, but remains competitive even for longer-term predictions. This is achieved despite the simplicity of its input space, which does not include information about vehicles other than the target vehicle. As a result, while its performance may decrease slightly for longer-term predictions due to the lack of environmental information, it still offers
Lucente, Giovanni, Maarssoe, Mikkel Skov, Kahl, Iris, Schindler, Julian
Journal Article
PRODUCT BRIEFS24AUTP06_1306/01/2024
Magazine Article
Advancing HMI development of ADAS and active safety systems24TOFHP06_0306/01/2024
iMotions employs neuroscience and AI-powered analysis tools to enhance the tracking, assessment and design of human-machine interfaces inside vehicles. The advancement of vehicles with enhanced safety and infotainment features has made evaluating human-machine interfaces (HMI) in modern commercial and industrial vehicles crucial. Drivers face a steep learning curve due to the complexities of these new technologies. Additionally, the interaction with advanced driver-assistance systems (ADAS) increases concerns about cognitive impact and driver distraction in both passenger and commercial vehicles. As vehicles incorporate more automation, many clients are turning to biosensor technology to monitor drivers' attention and the effects of various systems and interfaces. Utilizing neuroscientific principles and AI, data from eye-tracking, facial expressions and heart rate are informing more effective system and interface design strategies. This approach ensures that automation advancements
Nguyen, Nam
Magazine Article
Exploration of the Heterogeneity among Elderly Drivers by Analyzing Traffic Crash Data: A Case Study in Pennsylvania, USA09-12-03-000805/07/2024
With population aging and life expectancy increasing, elderly drivers have been increasing quickly in the United States and the heterogeneity among them with age is also increasingly non-ignorable. Based on traffic crash data of Pennsylvania from 2011 to 2019, this study was designed to identify this heterogeneity by quantifying the relationship between age and crash characteristics using linear regression. It is found that for elderly driver-involved crashes, the proportion leading to casualties significantly increases with age. Meanwhile, the proportions at night, on rainy days, on snowy days, and involving driving under the influence (DUI) decrease linearly with age, implying that elderly drivers tend to avoid traveling in risky scenarios. Regarding collision types, elderly driver-involved crashes are mainly composed of angle, rear-end, and hit-fixed-object collisions, proportions of which increase linearly, decrease linearly, and keep consistent with age, respectively. The increase
Zhang, Zihao, Liu, Chenhui
Journal Article
Driving Behavior during Left-Turn Maneuvers at Intersections on Left-Hand Traffic Roads2023-22-000704/17/2024
Understanding left-turn vehicle-pedestrian accident mechanisms is critical for developing accident-prevention systems. This study aims to clarify the features of driver behavior focusing on drivers’ gaze, vehicle speed, and time to collision (TTC) during left turns at intersections on left-hand traffic roads. Herein, experiments with a sedan and light-duty truck (< 7.5 tons GVW) are conducted under four conditions: no pedestrian dummy (No-P), near-side pedestrian dummy (Near-P), far-side pedestrian dummy (Far-P) and near-and-far side pedestrian dummies (NF-P). For NF-P, sedans have a significantly shorter gaze time for left-side mirrors compared with light-duty trucks. The light-duty truck’s average speed at the initial line to the intersection (L1) and pedestrian crossing line (L0) is significantly lower than the sedan’s under No-P, Near-P, and NF-P conditions, without any significant difference between any two conditions. The TTC for sedans is significantly shorter than that for
Matsui, Yasuhiro, Narita, Masashi, Oikawa, Shoko
Journal Article
Modelling and Analysis of a Cooperative Adaptive Cruise Control (CACC) Algorithm for Fuel Economy2024-01-256404/09/2024
Connectivity in ground vehicles allows vehicles to share crucial vehicle data, such as vehicle acceleration and speed, with each other. Using sensors such as radars and lidars, on the other hand, the intravehicular distance between a leader vehicle and a host vehicle can be detected. Cooperative Adaptive Cruise Control (CACC) builds upon ground vehicle connectivity and sensor information to form convoys with automated car following. CACC can also be used to improve fuel economy and mobility performance of vehicles in the said convoy. In this paper, a CACC system is presented, where the acceleration of the lead vehicle is used in the calculation of desired vehicle speed. In addition to the smooth car following abilities, the proposed CACC also has the capability to calculate a speed profile for the ego vehicle that is fuel efficient, making it an Ecological CACC (Eco-CACC) model. Simulations were run to model and test the Eco-CACC algorithms with different lead vehicle driving behaviors
Kavas-Torris, Ozgenur, Guvenc, Levent
Technical Paper
Towards the Interpretation of Customizable Imitation Learning of Human Driving Behavior in Mixed Traffic Scenarios2024-01-200904/09/2024
With further development of autonomous vehicles additional challenges appear. One of these challenges arises in the context of mixed traffic scenarios where automated and autonomous vehicles coexist with manually operated vehicles as well as other road users such as cyclists and pedestrians. In this evolving landscape, understanding, predicting, and mimicking human driving behavior is becoming not only a challenging but also a compelling facet of autonomous driving research. This is necessary not only for safety reasons, but also to promote trust in artificial intelligence (AI), especially in self-driving cars where trust is often compromised by the opacity of neural network models. The central goal of this study is therefore to address this trust issue. A common approach to imitate human driving behavior through expert demonstrations is imitation learning (IL). However, balancing performance and explainability in these models is a major challenge. To efficiently generate training data
Rebling, Patrick, Kriesten, Reiner, Nenninger, Philipp
Technical Paper
Vehicle Yaw Dynamics Safety Analysis Methodology based on ISO-26262 Controllability Classification2024-01-276604/09/2024
Complex chassis systems operate in various environments such as low-mu surfaces and highly dynamic maneuvers. The existing metrics for lateral motion hazard by Neukum [13] and Amberkar [17] have been developed and correlated to driver behavior against disturbances on straight line driving on a dry surface, but do not cover low-mu surfaces and dynamic driving scenarios which include both linear and nonlinear region of vehicle operation. As a result, an improved methodology for evaluating vehicle yaw dynamics is needed for safety analysis. Vehicle yaw dynamics safety analysis is a methodical evaluation of the overall vehicle controllability with respect to its yaw motion and change of handling characteristic. The yaw dynamics safety analysis is crucial for understanding how a driver-vehicle system responds to disturbances (external forces such as failure modes) in various driving scenarios and maneuvers., and it plays a significant role in evaluating the overall safety and performance of
paik, Scott, Almasri, Hossam, Rao Medidha, Neelakanta, Capobianco, Anthony, Evans, Andrew, Sevillano, Yvette
Technical Paper
Electric vehicle battery health aware DC fast-charging recommendation system2024-01-260404/09/2024
DC fast charging (DCFC) also referred to as L3 charging, is the fastest charging technology to replenish the drivable range of an electric vehicle. DCFC provides the convenience of faster charging time compared to L1 and L2 at the expense of potentially increased battery health degradation. It is known to accelerate battery capacity fade leading to reduced range and lifetime of the EV battery. While there are active efforts and several means to reduce the downsides of DCFC at cell chemistry level, this trade-off is still an important consideration for most battery cells in automotive propulsion applications. Since DCFC is a customer driven technology, informing drivers of the trade-off of each DCFC event can potentially result in better outcomes for the EV battery life. Traditionally, the driver is advised to limit DCFC events without providing quantifiable metrics to inform their decisions during EV charging. A recommendation system for DCFC based on battery health optimization is
Hegde, Bharatkumar, Haskara, Ibrahim
Technical Paper
“FEV’s ‘CogniSafe’: An Innovative Deep Learning-Based AI Driver Monitoring System for the Future of Mobility2024-01-201204/09/2024
Driver state monitoring is a crucial technology for enhancing road safety and preventing human error-caused accidents in the era of autonomous vehicles. This paper presents CogniSafe, a comprehensive driver monitoring system that uses deep learning and computer vision methods to detect various types of driver distractions and fatigue. CogniSafe consists of four modules: Driver anomaly detection and classification: A novel two-phase network that proposes and recognizes driver anomalies, such as texting, drinking, and adjusting radios, using multimodal and multiview input. Gaze estimation: A video-based neural network that jointly learns head pose and gaze dynamics, achieving robust and efficient gaze estimation across different head poses. Eye state analysis: A multi-tasking CNN that encodes features from both eye and mouth regions, predicting the percentage of eye closure (PERCLOS) and the frequency of mouth opening (FOM). Head pose estimation: A CNN-based method that estimates the
Wani, Ankit, Singh, Jyotsana, Kumari, Deepa, Ithape, Avinash, Rapanwad, Govind
Technical Paper
Understand Driving Behaviors Based on Comprehensive Grading System and Unsupervised Learning2024-01-239804/09/2024
Understanding driving behavior is crucial for enhancing traffic safety. While previous studies have primarily explored driving behavior using either statistical or machine learning methods, comprehensive assessments employing both methods under various driving mode are limited. In this study, we employ both machine learning and statistical approaches to model driving behavior. First, we design a comprehensive driver grading system to assess the behavior of drivers under different driving modes. Additionally, we present an extended isolation forest-based model to classify driving behavior using data without labels, saving time and effort. Results illustrate that safe driving is more consistent and stable, while aggressive driving exhibits more intensive changes. They also demonstrate that drivers can exhibit various behaviors under different modes, serving as a benchmark for further driver modeling
Guo, Bin, Hansen, John
Technical Paper
A Naturalistic Driving Study for Lane Change Detection and Personalization2024-01-256804/09/2024
Driver Assistance and Autonomous Driving features are becoming nearly ubiquitous in new vehicles. The intent of the Driver Assistant features is to assist the driver in making safer decisions. The intent of Autonomous Driving features is to execute vehicle maneuvers, without human intervention, in a safe manner. The overall goal of Driver Assistance and Autonomous Driving features is to reduce accidents, injuries, and deaths with a comforting driving experience. However, different drivers can react differently to advanced automated driving technology. It is therefore important to consider and improve the adaptability of these advances based on driver behavior. In this paper, a human-centric approach is adopted to provide an enriching driving experience. We perform data analysis of the naturalistic behavior of drivers when performing lane change maneuvers by extracting features from extensive Second Strategic Highway Research Program (SHRP2) data of over 5,400,000 data files. First, the
Lakhkar, Radhika Anandrao, Talty, Tim
Technical Paper
Enhancing Safety Features of Advanced Driver Assistance System Warnings by Using Head-Up Displays2024-01-205804/09/2024
ADAS (Advanced Driver Assistance Systems) is a growing technology in automotive industry, intended to provide safety and comfort to the passengers with the help of variety of sensors like radar, camera, LIDAR etc. Though ADAS improved safety of passengers comparing to conventional non-ADAS vehicles, still it has some grey areas for safety enhancement and easy assistance to drivers. BSW (Blind Spot Warning) and LCA (Lane Change Assist) are ADAS function which assists the driver for lane changing. BSW alerts the driver about the vehicles which are in blind zone in adjacent lanes and LCA alerts the driver about approaching vehicles at a high velocity in adjacent lanes. In current ADAS systems, BSW and LCA alerts are given as optical and acoustic warnings which is placed in vehicle side mirrors. During lane change the driver must see the side mirrors to take a decision. Due to this, there is a reaction time for taking a decision since driver must divert attention from windshield to side
R, Manjunath, Saddaladinne, Jagadeesh Babu, D, Gopinath
Technical Paper
Items per page:
1 – 50 of 661