16 May 2023 in IEEE Transactions on Intelligent Transportation Systems
This paper proposes a hierarchical model for cooperative on-ramp merging control (CORMC) in mixed traffic with both connected automated vehicles (CAVs) and connected human-driven vehicles (CHVs). The upper-layer of the CORMC model employs an anticipatory position searching (APS) algorithm to determine the anticipatory positions at which merging vehicles (MVs) should merge from the on-ramp lane to the adjacent mainline lane, and to assign cooperative vehicles (CVs) for each MV. A collaborative utility choice (CUC) model is presented to determine the optimal maneuver of CVs to create proper gaps for MVs. The driver compliance rate is introduced to account for CHVs’ unwillingness to follow the instructions given by the CUC model. The lower-layer comprises a cooperative merging control (CMC) model that ensures safe and smooth merging execution for MVs. Longitudinal and lane changing models are developed for mainline vehicles to facilitate an efficient and safe merging process. Simulation results show that the performance benefits of the CUC model are marginal when the CHV compliance rate is relatively low. However, the performance improvement is significant at higher compliance rates ( $>$ 50%). Furthermore, the CORMC model has the potential to increase merging and mainline throughput by over 75% at sufficiently high CAV penetration rates. Comparison of three control strategies shows that the APS algorithm plays an important role in the CORMC model. A comparison with the Simulation of Urban Mobility (SUMO) indicates that the CORMC model significantly mitigates the propagation of congestion waves across varying levels of CAV penetration and on-ramp flow rates.
6 September 2024 in Accident Analysis & Prevention
18 March 2024 in IEEE Transactions on Vehicular Technology
Deep reinforcement learning (DRL) provides a promising approach for the implementation of autonomous driving. By utilizing a trained DRL model as the longitudinal controller, the automated vehicle (AV) can generate optimal action outputs based on the state within a shorter time compared to traditional model predictive control (MPC) methods. However, the non-interpretability of neural networks poses a potential risk for real-world vehicle operation. This paper focuses on applying the Twin Delayed Deep Deterministic Policy Gradient (TD3), a state-of-the-art (SOTA) DRL algorithm, to train the longitudinal control model for AVs. We confirm the risks associated with the TD3-based longitudinal control model by assessing its violation of the rational driving constraint (RDC), which represents the basic conditions for normal driving behaviors. To mitigate these risks, we propose a novel model that integrates the TD3-based model with the intelligent driver model (IDM) using a new indicator called velocity response time (VRT). This indicator identifies risky outputs of the TD3-based model and calculates the combined weights of both the IDM and TD3-based models. This combination allows us to reduce risks associated with the non-interpretability of the neural network while also capturing the effect of engine time lag. Numerical simulations are conducted to evaluate the performance of the proposed combined model. The results demonstrate that the proposed combined model outperforms the TD3-based model, IDM, and another SOTA approach in terms of disturbance mitigation, safety improvement, and suppression of traffic oscillation. Additionally, the combined model exhibits greater computational efficiency than MPC, making it well-suited for real-time control of AVs.
26 October 2026 in Transportation Research Part B: Methodological