TY - GEN
T1 - Intelligent Architecture for Car-following Behaviour Observing Lane-changer
T2 - 10th International Conference on Computer and Knowledge Engineering, ICCKE 2020
AU - Tajdari, Farzam
AU - Toulkani, Naeim Ebrahimi
AU - Nourimand, Maral
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/29
Y1 - 2020/10/29
N2 - During motorway driving behaviour, the car-following behaviour is the most popular among the rest of behaviours e.g., lane-changing and overtaking. However, a few research has been done on the effect of lane change behaviour on car-following behaviour. The effect is a highly complex transient state among the car-following models and makes the car follower exit the previous ones, which are known as conventional models, for a limited time. Accordingly, in this paper, an intelligent model includes anticipation of interaction behaviour regarding the micro-structure of drivers is proposed, when Lane Changer (LC) exits the lane is studied. Continuously, a fuzzy controller is designed based on the criteria of detecting the complex behaviour in the model. Both the model and the controller aim to regulate the Follower Vehicle (FV) acceleration which simulates the behaviour of a real driver. Afterward, its performance is compared with the database of human drivers. The results assert that the model is capable to estimate the behaviour of the real drivers perfectly. Also, the controller provides a safer and smoother drive comparing to a real driver, in addition to less traveling time.
AB - During motorway driving behaviour, the car-following behaviour is the most popular among the rest of behaviours e.g., lane-changing and overtaking. However, a few research has been done on the effect of lane change behaviour on car-following behaviour. The effect is a highly complex transient state among the car-following models and makes the car follower exit the previous ones, which are known as conventional models, for a limited time. Accordingly, in this paper, an intelligent model includes anticipation of interaction behaviour regarding the micro-structure of drivers is proposed, when Lane Changer (LC) exits the lane is studied. Continuously, a fuzzy controller is designed based on the criteria of detecting the complex behaviour in the model. Both the model and the controller aim to regulate the Follower Vehicle (FV) acceleration which simulates the behaviour of a real driver. Afterward, its performance is compared with the database of human drivers. The results assert that the model is capable to estimate the behaviour of the real drivers perfectly. Also, the controller provides a safer and smoother drive comparing to a real driver, in addition to less traveling time.
KW - anticipation
KW - car-following
KW - fuzzy controller
KW - intelligent model
KW - lane-changing
U2 - 10.1109/ICCKE50421.2020.9303652
DO - 10.1109/ICCKE50421.2020.9303652
M3 - Conference contribution
AN - SCOPUS:85101431775
T3 - 2020 10h International Conference on Computer and Knowledge Engineering, ICCKE 2020
SP - 579
EP - 584
BT - 2020 10h International Conference on Computer and Knowledge Engineering, ICCKE 2020
PB - IEEE
Y2 - 29 October 2020 through 30 October 2020
ER -