Abstract
Conventional autonomous emergency braking (AEB) systems derive the relative distance of a curve using a curvature calculated through an in-vehicle sensor. However, as the AEB system cannot reflect geometric factors of a curve with variable curvature, it does not accurately estimate relative distances, based on which the AEB performance is evaluated. Accordingly, an AEB system reflecting the geometric information of curves needs to be considered and developed to improve the AEB performance for curves. This study proposes a method to improve the performance of AEB systems for curves through curvilinear coordinate conversion, which is used to reflect the geometric information of roads for the navigation of an autonomous vehicle. Both the host and target vehicles are located by means of curvilinear coordinate conversion. The positions thus identified are used to calculate the relative distance and lanes. Finally, the hazard risk criterion—that is, time-to-collision (TTC)—is derived using the proposed AEB system. To demonstrate the effectiveness of the proposed AEB system, this study compares it with the conventional AEB system by analyzing the collision avoidance performance on curves through relative distances and TTC.
Highlights
According to the Korean National Police Agency and the National Highway Traffic SafetyAdministration (NHTSA), the increase of vehicles on roads is accompanied by a proportional increase in traffic accidents caused by careless driving [1,2]
autonomous emergency braking (AEB) system, this study compares it with the conventional AEB system by analyzing the collision avoidance performance on curves through relative distances and TTC
This study aims to improve the performance of an AEB system on curve roads
Summary
According to the Korean National Police Agency and the National Highway Traffic SafetyAdministration (NHTSA), the increase of vehicles on roads is accompanied by a proportional increase in traffic accidents caused by careless driving [1,2]. An AEB system analyzes the collision risk with the preceding vehicle and prevents or avoids a head-on collision, which can occur due to the driver’s carelessness, by operating the automatic control function at a dangerous moment [4]. The existing AEB systems usually detect collision risks using obstacle detection sensors, such as cameras, light detection and ranging (LiDAR), and radio detecting and ranging (RADAR). As these sensors have limitations, many researchers have attempted to integrate multi-sensor data fusion technology with vehicle-to-vehicle (V2V) communication [5]. Since the existing AEB systems do not consider the geometrical shape of winding roads, the relative distance is not very accurate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
