Utilization of ADAS for Improving Idle Stop-and-Go Control

2018 ◽  
Author(s):  
Kwangwoo Jeong ◽  
Hoon Lee ◽  
Jaihyun Lee ◽  
Sanghoon Yoo ◽  
Byungho Lee ◽  
...  
Keyword(s):  
Control Algorithm ◽  
Traffic Information ◽  
Test Results ◽  
Driver Assistance ◽  
Control Logic ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Stop Sign ◽  
Stop And Go ◽  
Vehicle Test

Idle Stop and Go (ISG), also known as Automatic Engine Stop/Start, has been widely implemented in production vehicles as one of the “Eco” functions that save fuel, and the application has been promoted to meet stringent fuel economy regulations throughout the world. However, the vibration and the hesitation caused by engine stop and restart often discourage the usage. Because a conventional ISG system usually restarts the engine when it sees the brake pedal release, the driver may perceive a delay in immediate vehicle launch. Furthermore, there are some driving conditions where engine on/off is undesirable or unnecessary. A quick stop-and-go situation such as making a complete stop at a stop sign is one of the conditions where ISG would be inappropriate, and in those cases, ISG may irritate the driver or even end up increasing fuel consumption with too frequent engine stop/start. In order to mitigate aforementioned issues, a utilization of Advanced Driver Assistance System (ADAS) is proposed. With the surrounding traffic information obtained from the ADAS module, ISG control algorithm is able to determine when to turn on or off the engine prior to driver’s input. The applications demonstrated in this paper include the following usage examples: The ISG control logic monitors the movement of the vehicle in front and restarts the engine out of ISG mode before brake release, which eliminates the delay in the following vehicle launch. By employing traffic sign recognition and vehicle location info, the control logic is also able to inhibit engine off when the vehicle stops at stop signs which will avoid unwanted ISG activation. In this paper, the advanced ISG control logic is introduced, and the real-world vehicle test results are provided with the description of prototype vehicle configuration.

Traffic Sign Recognition Using a Synthetic Data Training Approach

2020 ◽  
Vol 29 (05) ◽  
pp. 2050013
Author(s):  
Oualid Araar ◽  
Abdenour Amamra ◽  
Asma Abdeldaim ◽  
Ivan Vitanov
Keyword(s):  
Neural Networks ◽  
Synthetic Data ◽  
Real Data ◽  
Training Data ◽  
Traffic Sign Recognition ◽  
Driver Assistance ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Crucial Component ◽  
Training Approach

Traffic Sign Recognition (TSR) is a crucial component in many automotive applications, such as driver assistance, sign maintenance, and vehicle autonomy. In this paper, we present an efficient approach to training a machine learning-based TSR solution. In our choice of recognition method, we have opted for convolutional neural networks, which have demonstrated best-in-class performance in previous works on TSR. One of the challenges related to training deep neural networks is the requirement for a large amount of training data. To circumvent the tedious process of acquiring and manually labelling real data, we investigate the use of synthetically generated images. Our networks, trained on only synthetic data, are capable of recognising traffic signs in challenging real-world footage. The classification results achieved on the GTSRB benchmark are seen to outperform existing state-of-the-art solutions.

scholarly journals Advanced Driver-Assistance System with Traffic Sign Recognition for Safe and Efficient Driving

2021 ◽  
Vol 9 (9) ◽  
pp. 11-15
Author(s):  
Sithmini Gunasekara ◽  
Dilshan Gunarathna ◽  
Maheshi Dissanayake
Keyword(s):  
Confidence Interval ◽  
Processing Time ◽  
Detection System ◽  
Support Vector ◽  
Testing Time ◽  
Traffic Sign Recognition ◽  
Driver Assistance ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Sign Distribution

Advanced Driver-Assistance Systems (ADAS) coupled with traffic sign recognition could lead to safer driving environments. This study presents a sophisticated, yet robust and accurate traffic sign detection system using computer vision and ML, for ADAS. Unavailability of large local traffic sign datasets and the unbalances of traffic sign distribution are the key bottlenecks of this research.  Hence, we choose to work with support vector machines (SVM) with a custom-built unbalance dataset, to build a lightweight model with excellent classification accuracy.  The SVM model delivered optimum performance with the radial basis kernel, C=10, and gamma=0.0001. In the proposed method, same priority was given to processing time (testing time) and accuracy, as traffic sign identification is time critical. The final accuracy obtained was 87% (with confidence interval 84%-90%) with a processing time of 0.64s (with confidence interval of 0.57s-0.67s) for correct detection at testing, which emphasizes the effectiveness of the proposed method.

Control of Multi-Plate Torque Converter Clutch With an Aggressive Schedule in an Automatic Transmission

2007 ◽  
Author(s):  
Chunhao Joseph Lee ◽  
Farzad Samie ◽  
Kumaraswamy Hebbale ◽  
Chi-Kuan Kao ◽  
Paul Otanez
Keyword(s):  
Control Algorithm ◽  
Hardware Implementation ◽  
Automatic Transmission ◽  
Torque Converter ◽  
Gear Train ◽  
Test Results ◽  
Environmental Pressures ◽  
Single Plate ◽  
Fluid Coupling ◽  
Vehicle Test

In an automatic transmission, torque converter is the main device that transmits torque from the engine to the gear train. An open converter relies on fluid coupling to transmit torque, which causes energy loss and also causes engine to run at a higher speed. A single-plate locking or slipping clutch has been used between the pump and turbine of a torque converter so that the slip across the converter can be reduced to a level that increases the efficiency of the converter. This slip control, called Electronically Controlled Capacity Clutch (ECCC), also provides necessary damping to the driveline to ensure pleasant driveability similar to an open converter. New legislative and environmental pressures on car makers to improve fuel economy have resulted in aggressive use of ECCC in their automobiles. However, the controllability and heat capacity of the single-plate clutch limit the ability to engage the torque converter clutch (TCC) more aggressively (in earlier gears and lower vehicle speeds). At GM, an experimental multi-plate toque converter was designed, fabricated, and implemented in a RWD transmission. It was demonstrated in a 6-speed vehicle that driving pleaseability can be maintained with a more aggressive ECCC strategy. For this purpose, a control algorithm was developed to control the slip speed of the clutch and allow early ECCC starting in second gear. This paper describes in detail hardware implementation of the multi-plate clutch, development and implementation of the aggressive ECCC control strategy, and some vehicle test results.

scholarly journals Active Safety with Traffic Sign Recognition System in Vehicular Ad-Hoc Network (Vanet) using Classifier Techniques

2019 ◽  
Vol 8 (2) ◽  
pp. 6186-6190
Keyword(s):  
Ad Hoc ◽  
Intelligent Transportation System ◽  
Intelligent Transportation ◽  
Recognition System ◽  
Transportation System ◽  
Driver Assistance ◽  
Traffic Sign ◽  
Vehicle Communication ◽  
Research Areas ◽  
Sign Recognition

Intelligent Transportation System (ITS) is one of the major research areas where the researchers focus on Vehicle traffic prediction, efficient routing algorithms, security in vehicle communication, various QoS parameters and so on..Wireless technology is progressing faster with time. People are doing research these days generally in the field of Wireless communication. VANET is the most developing exploration territory in remote correspondence. With the headway and development of the VANET, there will be an incredible upheaval in the field of telecommunication regarding quick handovers, arrange accessibility, security, wellbeing with the utilization of cutting edge applications and so on. VANET innovation is progressing with the progression of time however there are numerous issues that must be routed to make the system more overwhelming. In perspective of aforementioned, in this paper we have proposed an effective mechanism for object detection in highways using Neural Networking and proving driver assistance to enhance the existing system to the next level as Intelligent Transportation System.

Sign in / Sign up

Export Citation Format

Share Document