Development of a conflict-free unsignalized intersection organization method for multiple connected and autonomous vehicles

Cycle-level traffic conflict prediction at signalized intersections with LiDAR data and Bayesian deep learning

Real-time safety prediction models are vital in proactive road safety management strategies. This study develops models to predict traffic conflicts at signalized intersections at the signal cycle level, using advanced Bayesian deep learning techniques and efficient LiDAR points. The modeling framework contains three phases, which are data preprocessing, base deep learning model development, and Bayesian deep learning model development. The core of the framework is the long short-term memory (LSTM) employed to predict the conflict frequency of a cycle by using traffic features of the previous five cycles (e.g., dynamic traffic parameters, traffic conflict frequency). Four Bayesian deep learning models were developed, including Bayesian-Standard LSTM, Bayesian-Hybrid-LSTM, Bayesian-Stacked-LSTM Encoder-Decoder, and Bayesian-Multi-head Stacked-LSTM Encoder-Decoder. The developed models were applied to traffic conflicts extracted from LiDAR points that were collected from a signalized intersection in Harbin, China with a total duration of seven days. Traffic conflicts, measured by the modified time-to-collision conflict indicator, were identified using the peak over threshold approach. The models were thoroughly evaluated from the aspects of reliability, transferability, sensitivity, and robustness. The results show that the developed four models can predict traffic conflict frequency per cycle per lane simultaneously with its uncertainty. Moreover, the two Bayesian encoder-decoder models perform better than Bayesian-Standard LSTM and Bayesian-Hybrid-LSTM in the four tests. Bayesian-Multi-head Stacked-LSTM Encoder-Decoder is suggested as the optimal model for its high reliability under uncertainty, good transferability in three scenarios, low sensitivity to different parameters, and sound robustness against small noise. The proposed framework could benefit studies on the state-of-the-art data-driven approach for real-time safety prediction.

A novel approach for fine-grained traffic risk characterization and evaluation of urban road intersections

An urban road intersection environment with low traffic risk is an essential component of sustainable cities. Various risk analysis and simulation techniques have been developed to measure and evaluate traffic risks. However, flexible assessment of intersection risk at a fine resolution remains a great challenge. This study proposes a novel approach for characterizing the field distribution of traffic risks at an urban road intersection and assessing traffic risks in multiple dimensions to increase the flexibility of risk assessment. First, we define a new traffic risk metric to quantify the risk of intersection traffic conflict points by combining their frequency and severity. Second, the plume diffusion model is introduced to model the non-linear relationship between traffic conflict points by considering the propagation of the traffic risk in the intersection. In this way, the entire intersection risk distribution map is derived for real-time risk analysis. Finally, a multidimensional hierarchical evaluation system of traffic risk at intersections is designed, including the traffic risk indicators at the intersection, path, and turn mode levels. The results of a case study in Wuhan, China, demonstrate the continuous characterization results of the risk field and provide multidimensional risk assessment index results, which are highly consistent with the cognitive results of manual risk scoring (up to 90% similarity). It also allows for risk assessment in a single path and turn modes through the risk field characterization and reveals the spatiotemporal dynamic risk distribution, thus providing an alternative tool for risk decision-making at urban road intersections.