Advanced Adaptive Cruise Control Based on Operation Characteristic Estimation and Trajectory Prediction

• Published in: Applied sciences 2019-11, Vol.9 (22), p.4875
• Main Authors: Woo, Hanwool, Madokoro, Hirokazu, Sato, Kazuhito, Tamura, Yusuke, Yamashita, Atsushi, Asama, Hajime
• Format: Article
• Language: English
• Subjects: Accuracy; Automatic pilots; Automation; Autonomous vehicles; Change detection; Collision avoidance; Cruise control; Driving ability; Estimates; Human error; Lane changing; Methods; Predictions; Risk assessment; Traffic congestion; Traffic flow; Trajectory analysis
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app9224875

In this paper, we propose an advanced adaptive cruise control to evaluate the collision risk between adjacent vehicles and adjust the distance between them seeking to improve driving safety. As a solution for preventing crashes, an autopilot vehicle has been considered. In the near future, the technique to forecast dangerous situations and automatically adjust the speed to prevent a collision can be implemented to a real vehicle. We have attempted to realize the technique to predict the future positions of adjacent vehicles. Several previous studies have investigated similar approaches; however, these studies ignored the individual characteristics of drivers and changes in driving conditions, even though the prediction performance largely depends on these characteristics. The proposed method allows estimating the operation characteristics of each driver and applying the estimated results to obtain the trajectory prediction. Then, the collision risk is evaluated based on such prediction. A novel advanced adaptive cruise control, proposed in this paper, adjusts its speed and distance from adjacent vehicles accordingly to minimize the collision risk in advance. In evaluation using real traffic data, the proposed method detected lane changes with 99.2% and achieved trajectory prediction error of 0.065 m, on average. In addition, it was demonstrated that almost 35% of the collision risk can be decreased by applying the proposed method compared to that of human drivers.