• Journal of Auto-vehicle Safety Association
• /
• v.11 no.3
• /
• pp.7-12
• /
• 2019

AEB (Autonomous Emergency Braking system), a system in which vehicles automatically recognize forward objects or pedestrians and actively brake when forward collisions are expected, has been mandated by NHTSA (National Highway Traffic Safety Administration) and IIHS (Insurance Institute for Highway Safety) for all vehicles sell in the United States since 2022, and AEB research is also actively underway in korea. In this study, it can be confirmed that the passenger injury is reduced according to the AEB detection distance when it is assumed that the AEB is mounted in the actual event generated from KIDAS (Korea New Car Assessment Program) data through various analysis programs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.57-64
• /
• 2020

The leading technologies of the ADAS (Advanced Driver Assist System) are ACC (Advanced Cruise Control), LKAS (Lane Keeping Assist System), and AEB (Autonomous Emergency Braking). LKAS is a system that uses cameras and infrared sensors to control steering and return to its running lane in the event of unintentional deviations. The actual test is performed for a safety evaluation and verification of the system. On the other hand, research on the system evaluation method is insufficient when an additional steering angle is applied. In this study, a model using Prescan was developed and simulated for the scenarios proposed in the preceding study. Comparative analyses of the simulation and the actual test were performed. As a result, the modeling validity was verified. A difference between the front wheels and the lane occurred due to the return velocity. The results revealed a maximum error of 0.56 m. The error occurred because the lateral velocity of the car was relatively small. On the other hand, the distance from wheels to the lanes displayed a tendency of approximately 0.5 m. This can be verified reliably.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.202-210
• /
• 2019

This paper evaluated the performance of passenger vehicles with an AEB(Autonomous Emergency Braking) for various pedestrian-vehicle collision situations. The experiment was conducted at a speed of 30-60km/h on a 2017 3,000cc vehicle using a range of collision scenarios. The results showed that the test vehicle stopped before crashing a pedestrian dummy under all scenarios at 30km/h. The test vehicle reduced the speed but crashed the pedestrian dummy in all scenarios at 40-60km/h. From the paired t-test, there was a speed difference from the AEB system at a significant level of 0.05. In addition, the percentage of speed reduction was quite different for each scenario tested. It was concluded that the current AEB system can prevent pedestrian collisions at speed of 30km/h, but cannot prevent collisions with pedestrians at speed of 40-60 km/h.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.2
• /
• pp.127-136
• /
• 2016

The camera based object detection systems should satisfy the recognition performance as well as real-time constraints. Particularly, in safety-critical systems such as Autonomous Emergency Braking (AEB), the real-time constraints significantly affects the system performance. Recently, multi-core processors and system-on-chip technologies are widely used to accelerate the object detection algorithm by distributing computational loads. However, due to the advanced hardware, the complexity of system architecture is increased even though additional hardwares improve the real-time performance. The increased complexity also cause difficulty in migration of existing algorithms and development of new algorithms. In this paper, to improve real-time performance and design complexity, a task scheduling strategy is proposed for visual object tracking systems. The real-time performance of the vision algorithm is increased by applying pipelining to task scheduling in a multi-core processor. Finally, the proposed task scheduling algorithm is applied to crosswalk detection and tracking system to prove the effectiveness of the proposed strategy.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.4
• /
• pp.28-38
• /
• 2019

In the world, traffic accidents and environmental pollution caused by the increase of vehicles are becoming a serious social problem. According to the 2016 data published by the Korea Highway Traffic Authority, Korea owns 49.9 vehicles per 100 people. This is the 28th largest number among the 35 OECD member countries. In addition, the number of deaths from traffic accidents in Korea totaled 4,292, of which 1,714 were caused by traffic accidents involving vehicles and pedestrians. To reduce these human casualties, the automotive industry is constantly working on the development and commercialization of Adaptive Driver Assist System (ADAS). ADAS is the system providing convenience and safeness for drivers. In general, ADAS consists of Autonomous Emergency Braking (AEB), Highway Driving Assist (HDA), Adaptive Cruise Control (ACC), Lane Keeping Assist System (LKAS). Among them, the AEB detects the possibility of collision by the vehicle itself and plays a role of avoiding the collision or reducing the damage through active braking. For such AEB, Euro NCAP has been developing test-evaluation methods for the vulnerable since 2017. Therefore, In this paper analyzes the scenario of Euro NCAP VRU Test Protocol v3.0.1, which will be established in 2020, and proposes test conditions according to the Korean road traffic law. In addition, the reliability of the proposed scenario and test conditions was verified by comparing and analyzing the proposed theoretical evaluation formulas and actual test results.