Risk-anticipatory attention-based SAC approach for vehicle decision-making at unsignalized intersections

Abstract

The dynamic unsignalized intersection environment has long been one of the most challenging scenarios for autonomous driving tasks. The crux of the research lies in how to safely and efficiently complete decision-making tasks in such uncertain scenarios. In order to solve the above problems, this paper proposes a decision-making strategy based on risk anticipation and attention mechanisms. The strategy is mainly composed of risk anticipation and attention module. In the risk anticipation module, we consider the distribution of vehicle shapes and motion risk diffusion areas, incorporating these factors into safety considerations, and propose a new risk anticipation index based on the risk anticipation theory, the risk anticipation index is composed of the risk values of road points along the vehicle’s route. Using this risk diffusion model, we can effectively calculate the degree of impact that surrounding risk diffusion zones have on the vehicle itself, thereby effectively preventing dangerous driving behaviors from occurring. In the attention module, we introduce an attention mechanism to enhance the strategy’s ability to extract scene information, improving the vehicle’s understanding of the current scene and allowing it to more effectively focus on potential risks. In practical operation, the attention mechanism and risk prediction module form a tightly integrated system. Based on the road point information along the current vehicle’s route, the risk anticipation module outputs a risk sequence indicator. This sequence serves as the risk anticipation metric and, together with other information, constitutes the current vehicle’s state. The risk sequence indicators output by the risk expectation module serve as network inputs, functioning as the basis for weight adjustment in the attention mechanism. When high-risk scenarios are detected, the attention mechanism dynamically adjusts the weights of each attention head, allocating more resources to feature extraction related to high-risk factors. Finally, the performance of our strategy is validated in an unsignalized intersection scenario using the simulation software CARLA. The proposed method achieves a 12%–35% reduction in collision rate, a 5%–20% decrease in average speed, and a 10%–17% increase in average reward compared to the baseline model for the left-turn task at unsignalized intersections. Although average speed slightly decreased, core safety performance significantly improved. Convergence characteristics also showed superiority: compared to other baseline algorithms, convergence began gradually after training for 400 episodes, with stable performance maintained post-convergence. This demonstrates that the proposed DA-SAC algorithm effectively reduces decision risks and enhances traffic safety.