10 November 2022 in IEEE Transactions on Intelligent Transportation Systems
Automatic parking systems are increasingly used in daily life, and the restriction of parking spaces will make parking more difficult. This paper proposes parallel parking and forwards vertical parking path planning algorithms considering the park-ing corridor space. First, an anthropomorphic parallel parking path planning using parking space is proposed for the limited space over the length of the parking corridor. Second, a for-ward vertical parking path planning algorithm is proposed con-sidering the width of the parking space corridor. Third, the tar-get line set for parallel parking and vertical parking paths is generated. At the same time, the target line set considers the error factor and then selects the target line. Fourth, the clothoid solves the problem of discontinuous curvature of the parking path. Finally, a driver model is constructed to follow the gener-ated parking path, and the parking planning method proposed in this paper is compared with other methods.
1 April 2020 in Journal of Materials Science & Technology
27 March 2024 in IEEE Transactions on Intelligent Transportation Systems
Overtaking is a common driving behaviour used by human drivers while driving. Therefore, the decision on overtaking is very important in the automatic driving decision. To be able to improve the passing efficiency of intelligent vehicles, it is crucial to be able to interact with oncoming vehicles with different driving styles. An overtaking decision needs to be adapted to the situation where the vehicle being overtaken is potentially stationary or moving. Therefore, this paper proposes an overtaking decision method based on potential conflict area based on the requirements. Firstly, the planning method for each stage is given, and the generation method of the potential conflict area is proposed. Second, the interaction process between the host vehicle and the opposite oncoming vehicle is modelled by a dynamic game based on the potential conflict area. A driving style assessment method for oncoming vehicles based on potential conflict area is proposed. Thirdly, the priority of passing the potential conflict area of multiple oncoming vehicles is divided to correct the speed planning in the waiting and the speed payoff function in the game. Finally, the overtaking decision is simulated and validated by Virtual Test Drive.
3 August 2024 in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
Unsignalized intersections are a common scenario in urban areas. Therefore, it is necessary to consider decisions at unsignalized intersections. Left-turn behavior is used as a representative because there are more cases of interactions with other traffic participants under left-turn behavior. First, the paper proposes a way to improve the efficiency and comfort of the host vehicle when the intersection is obscured. Second, a dynamic game theory is proposed based on the potential conflict area of the intersection, considering safety and traffic efficiency. An estimation of the aggressiveness model based on the potential conflict area is proposed. Thirdly, a driving scheme is proposed by adjusting the passing scheme when the game is yielding. Finally, it was simulated for validation at unsignalized intersections by VTD (Virtual Test Drive). Simulation results show that the proposed method can balance comfort and passing efficiency through unsignalized intersections in the presence of occlusion. The average speed of the proposed method through the intersection is higher when interacting with traffic participants.
1 January 2026 in IEEE Internet of Things Journal
8 January 2025 in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
With the development of intelligent vehicles for different types of drivers, generating different driving styles of driving schemes can improve the comfort of the automatic driving system. This paper proposes a human-like planning method for lane change and intersections. Firstly, in planning for the speed driving scheme to enter the intersection, a planning method is proposed to generate different types of speed schemes after determining the start and end speeds. Secondly, by analyzing the data collected under turning conditions on a driving simulator, we extracted the characteristics of driving behavior for each experiment and calculated the probabilistic statistical properties of turning radius and maximum lateral acceleration. Thirdly, the driving characteristics of lane changes are obtained through the fitting of the lane change dataset, and based on this, the probabilistic statistical properties of lane change behavior are determined. Fourthly, this paper proposes a method for deciding longitudinal acceleration by deep learning, by inputting the motion information of the surrounding traffic participants and the motion information of the host vehicle and outputting the decided acceleration, which has the characteristics of imitating the driving behaviors of the real drivers, and adding a safety limit to the output. Finally, simulations and tests are conducted on the VTD (Virtual Test Drive).