Your Selections

Driver behavior
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Data-driven framework for fuel efficiency improvement in extended range electric vehicle used in package delivery applications

University of Minnesota-Pengyue Wang, William Northrop
  • Technical Paper
  • 2020-01-0589
To be published on 2020-04-14 by SAE International in United States
Extended-range electric vehicles (EREVs) are a potential solution for fossil fuel usage mitigation and on-road emissions reduction. EREVs can be shown to yield significant fuel economy improvements when the proper energy management strategies (EMSs) are employed. However, many in-use EREVs achieve only moderate fuel reduction compared to conventional vehicles due to the fact that their EMS is far from optimal. This paper focuses on rule-based optimization methods to improve the fuel efficiency of EREV last-mile delivery vehicles equipped with two-way Vehicle-to-Could (V2C) connectivity. The method uses previous vehicle data collected on actual delivery routes and a machine learning method to improve the fuel economy of future routes. The paper first introduces the main challenges of the project such as inherent uncertainty in human driver behavior and in the roadway environment. Then, the framework of our practical physics-model guided data-driven approach is introduced. For vehicles with small amounts of previous data, a Bayesian method is used to adjust a control parameter in the EMS offline for each vehicle with introduced prior information derived from large numbers…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Effects of training on learning and use of an adaptive cruise control system

Exponent Failure Analysis-Audra Krake, Rachel Jonas, Christian Hoyos, Caroline Crump, Benjamin Lester, David Cades, Ryan Harrington
  • Technical Paper
  • 2020-01-1033
To be published on 2020-04-14 by SAE International in United States
This study examined the effects of formalized training on driver behavior and understanding of an adaptive cruise control (ACC) system with drivers experienced with ACC. Sixteen participants drove an ACC-equipped vehicle while following a lead vehicle around a test track. Participants completed three laps, each featuring different lead vehicle behaviors, such as making a lane change or stopping at a red light, that test the limitations and capabilities of ACC. Immediately before driving, half of the participants watched a training video describing how the ACC system would respond to these lead vehicle behaviors. Braking behavior and use of ACC was recorded by cameras, and participants’ knowledge of the ACC system limitations was assessed by a pre- and post-test questionnaire. Surprisingly, compared to the participants who did not receive training, those who did receive training showed significantly more use of the brake versus allowing the ACC to slow or stop the vehicle for them during certain conditions. We did not observe significant differences between the two groups in time spent using ACC, though participants who did…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driver Distraction Detection with a Two-stream Convolutional Neural Network

Wuhan University of Technology-Yuefeng Ma, Zhishuai Yin, Linzhen Nie
  • Technical Paper
  • 2020-01-1039
To be published on 2020-04-14 by SAE International in United States
Driver distraction detection is crucial to driving safety when autonomous vehicles are co-piloted. Recognizing drivers’ behaviors that are highly related with distraction from real-time video stream is widely acknowledged as an effective approach mainly due to its non-intrusiveness. In recently years, deep learning neural networks have been adopted to by-pass the procedure of designing features artificially, which used to be the major downside of computer-vision based approaches. However, the detection accuracy and generalization ability is still not satisfying since most deep learning models extracts only spatial information contained in images. This research develops a driver distraction model based on a two-stream, spatial and temporal, convolutional neural network (CNN). The CNN in both stream is improved with Batch Normalization-Inception (BN-Inception) modules which increase the sparsity in the inception modules in GoogLeNet, so that the network is further speeded up and also more adapted to features at various-scales. The original RGB image is fed into the spatial stream CNN to extract static information, and the feature map of optical flow field extracted from adjacent image frames is…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Estimation of Fuel Economy on Real-Word Routes for Next-Generation Connected and Automated Hybrid Powertrains

Delphi Technologies, Inc.-Karim Aggoune, Pete Olin, John Kirwan
The Ohio State University-Shobhit Gupta, Shreshta Rajakumar Deshpande, Marcello Canova, Giorgio Rizzoni
  • Technical Paper
  • 2020-01-0593
To be published on 2020-04-14 by SAE International in United States
The assessment of fuel economy of new vehicles is typically based on regulatory driving cycles, measured in an emissions lab. Although, the regulations built around these standardized cycles have strongly contributed to improved fuel efficiency, they are unable to cover the envelope of operating and environmental conditions the vehicle will be subject to when driving in the “real world”. This discrepancy becomes even more dramatic with the introduction of Connectivity and Automation, which allows for information on future route and traffic conditions to be available to the vehicle and powertrain control system. Furthermore, the huge variability of external conditions, such as vehicle load or driver behavior, can significantly affect the fuel economy on a given route. Such variability poses significant challenges when attempting to compare the performance and fuel economy of different powertrain technologies, vehicle dynamics and powertrain control methods. This paper describes a methodology to properly benchmark the fuel consumption reduction potential of advanced cylinder deactivation and 48V mild hybridization in the presence of Level 1 connectivity and automation, and including accounting for the…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Optimization of Fuel Economy using Optimal Controls on regulatory and real-world driving cycles.

BorgWarner-Sara Mohon, Philip Keller, John Shutty, Nithin Kondipati
Gamma Technologies LLC-Dhaval Lodaya, Jonathan Zeman, Marcin Okarmus
  • Technical Paper
  • 2020-01-1007
To be published on 2020-04-14 by SAE International in United States
In recent years, electrification of vehicle powertrains has become more mainstream to meet regulatory fuel economy and emissions requirements. Amongst the many challenges involved with powertrain electrification, developing supervisory controls and energy management of hybrid electric vehicle powertrains involves significant challenges due to multiple power sources involved. Optimizing energy management for a hybrid electric vehicle largely involves two sets of tasks: component level or low-level control task and supervisory level or high-level control task. In addition to complexity within powertrain controls, advanced driver assistance systems and the associated chassis controls are also continuing to become more complex. However, opportunities exist to optimize energy management when a cohesive interaction between chassis and powertrain controls can be realized. To optimize energy management along a given route, certain information such as the projected vehicle route, driver behavior, and battery charge level should be considered. In this paper, simulation models of a parallel P0P4 hybrid electric vehicle are presented, which optimize powertrain controls using the Dynamic Programming approach. This virtual vehicle model is exercised through the EPA 5-Cycle Fuel…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driver Perception of Lateral Collision Threats

30 Forensic Engineering-Fabian Erazo, Adam Campbell
  • Technical Paper
  • 2020-01-1198
To be published on 2020-04-14 by SAE International in United States
Drivers presented with a collision threat must assess the likelihood of confrontation and determine if the threat warrants evasive action. The nature of the threat’s movement is critical in assessing a collision threat; however, the influence this visual information on driver behaviour is not well understood. A study was conducted to examine driver hazard perception of laterally-intruding vehicles. Seventeen subjects viewed first-person perspective recordings of a simulated vehicle travelling down a two-lane roadway consisting of several intersections with stop-controlled minor roads. Stopped vehicles were located at approximately half of the minor road intersections. Throughout the study, some of the stopped vehicles accelerated into the subject’s lane of travel at 1 of 6 pre-determined acceleration rates. Subjects were instructed to ‘brake’ their vehicle by pressing the space bar on a keyboard as soon as they perceived that a collision was imminent. Subject responses were measured as the elapsed time between the intruder’s first motion and the initiation of ‘braking’. Subject reaction time (determined using a simple reaction test) was deducted from their overall response to establish…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Using Vehicle Specifications to Gain Insights into Different Automotive Market Requirements

Mahindra & Mahindra, Ltd.-Lemuel Paulraj, Saravanan Muthiah
  • Technical Paper
  • 2020-01-1283
To be published on 2020-04-14 by SAE International in United States
Determination of vehicle specifications (for example, powertrain sizing) is one of the fundamental steps in any new vehicle development process. The vehicle system engineer needs to select an optimum combination of vehicle, engine and transmission characteristics based on the product requirements received from Product Planning (PP) and Marketing teams during concept phase of any vehicle program. This process is generally iterative and requires subject matter expertise. For example, accurate powertrain sizing is essential to meet the required fuel economy (FE), performance and emission targets for different vehicle configurations. This paper analyzes existing vehicle specifications (Passenger Cars/SUVs - Gasoline/Diesel) in different automotive markets (India, Europe, US, Japan) and aims to determine underlying trends across them. Scatter band analysis is carried out for specifications such as vehicle kerb weight (WT), vehicle length (L), vehicle width (W), vehicle height (H), footprint area (FPA), engine cubic capacity (CC) and engine power (P). CC/WT vs FE, CC/FPA vs FE, P/WT vs FE, FPA/(LXW), CC/(FPAXH), FPAXH and WXH trends are analyzed amongst others. It is interesting to note that similarities exist…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driver Physiological Drowsiness Behavior Detection and Analysis using Vision-based Multimodal Features for Driving Safety

Clemson University-Rui Li, Howard Brand, Aditya Gopinath, Srivatsav Kamarajugadda, Bing Li
Montclair State University-Weitian Wang
  • Technical Paper
  • 2020-01-1211
To be published on 2020-04-14 by SAE International in United States
Driving safety has always been a fundamental concern in transportation systems. Driving inattention caused by drowsiness has been a significant reason for vehicle crash accidents according to United States Traffic Safety Culture Index report, and there is an essential need to improve assistance driving safety by understanding the driver behaviors. Towards real-time drowsy driving monitoring, we propose an in-vehicle driver assistant system to monitor driver states for drowsiness behavior recognition and analysis. First, an infrared camera is deployed inside the vehicle to capture the driver’s facial and head information, in which scenarios, the driver is allowed to wear glasses or sunglasses during driving. Second, vision-based multimodal features, facial landmarks and head pose are extracted efficiently by the ensemble of regression trees based facial landmarks estimation method and a convolutional neural network (CNN) recognition model. Finally, an extreme learning machine (ELM) model is proposed to fuse the facial landmark, recognition model and pose orientation for drowsiness detection. The system gives promptly warning to the driver once a drowsiness event is detected. The proposed machine learning recognition…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Evaluation of Methods for Identification of Driving Styles and Simulation-Based Analysis of their Influence on Energy Consumption on the Example of a Hybrid Drive Train

Gregor Pucher
Graz University of Technology-Marko Domijanic, Mario Hirz
  • Technical Paper
  • 2020-01-0443
To be published on 2020-04-14 by SAE International in United States
Due to current progresses in the field of driver assistance systems and the continuously growing electrification of vehicle drive trains, the evaluation of driver behavior has become an important part in the development process of modern vehicles. Findings from driver analyses are used for the creation of individual profiles, which can be permanently adapted due to ongoing data processing. A benefit of data-based, dynamic control systems lies in the possibility to individually configure the vehicle behavior for a specific driver, which can contribute to increasing customer acceptance and satisfaction. In this way, an optimization of the control behavior between driver and vehicle and the resulting mutual learning and adjustment holds great potential for improvements in driving behavior, safety and energy consumption. The submitted paper deals with the analysis of different methods and measurement systems for the identification and classification of driver profiles as well as with their potential to optimize both vehicle driving behavior and energy consumption on the example of a hybrid drive train. A literature research results in a number of different approaches…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

An Improved Probabilistic Threat Assessment Method for Intelligent Vehicles in Critical Rear-End Situations

Chinese Academy of Engineering-Zhihua Zhong
Tsinghua University-Huajian Zhou, Xiaowei Wang, Jin Huang
  • Technical Paper
  • 2020-01-0698
To be published on 2020-04-14 by SAE International in United States
Threat assessment (TA) method is vital in the decision-making process of intelligent vehicles (IVs), especially for ADAS systems. In the research of TA, probabilistic threat assessment (PTA) method is acting an increasing role, which can reduce the uncertainties of driver’s maneuvers. However, the driver behavior model (DBM) used in present PTA methods was mainly constructed by limited data or simple functions, which is not entirely reasonable and may affect the performance of the TA process. This work aims to utilize crash data extracted from Event Data Recorder (EDR) to establish more accurate DBM and improve current PTA method in rear-end situations. EDR data with responsive maneuvers were firstly collected, which were then employed to construct the initial DBM (I-DBM) model by using the multivariate Gaussian distribution (MGD) framework. Besides, the model was further subdivided into six parts by two important risk indicators, TTC and velocity. To accurately represent the driver’s maneuvers in critical situations, unresponsive samples were introduced and the I-DBMs were upgraded by the Gaussian mixture model (GMM). The obtained DBMs were employed to…