Despite the widespread implementation, the Adaptive Cruise Control (ACC) systems still fall short in delivering a satisfactory human-likely experience, primarily due to the heterogeneity in driving experience preferences and the unpredictable, heterogeneous nature of human driving behaviors. To address this critical gap, we introduce an innovative driving style-aware car-following model that effectively captures the varying cut-in tendencies of adjacent vehicles by utilizing the Maximum Entrop Inverse Reinforcement Learning (Max-Ent IRL) method. A distinct reward function is developed to replicate human driving behavior, which can achieve a harmonious equilibrium between efficiency, safety, and comfort. The efficacy of this model is rigorously evaluated through a comprehensive analysis on car-following episodes extracted from the Next Generation Simulation (NGSIM) I-80 dataset. A novel human-likely metric is utilized for evaluating the performance of the proposed model in comparison to standard benchmarks. The results demonstrably favor our approach, showing notable enhancements in efficiency, safety, and comfort. Additionally, the model’s versatility is confirmed by its ability to accommodate a wide spectrum of driving styles, as evidenced by the diverse weights learned from different driving styles. These findings highlight the significant potential of our model in advancing ACC technology for more human-oriented vehicular systems that align closely with the natural driving instincts and preferences of humans.
Driving Style-aware Car-following Considering Cut-in Tendencies of Adjacent Vehicles with Inverse Reinforcement Learning
2024 IEEE Intelligent Vehicles Symposium (IV) ; 1329-1336
2024-06-02
2841079 byte
Conference paper
Electronic Resource
English
Construction method of deep reinforcement learning vehicle following model fused with driving style
European Patent Office | 2022
|