Minds on the Move: Decoding Trajectory Prediction in Autonomous Driving with Cognitive Insights

--In mixed autonomous driving environments, accurately predicting the future trajectories of surrounding vehicles is crucial for the safe operation of autonomous vehicles (A Vs). In driving scenarios, a vehicle's trajectory is determined by the decision-making process of human drivers. However, existing models primarily focus on the inherent statistical patterns in the data, often neglecting the critical aspect of understanding the decision-making processes of human drivers. This oversight results in models that fail to capture the true intentions of human drivers, leading to suboptimal performance in long-term trajectory prediction. T o address this limitation, we introduce a Cognitive-Informed Transformer (CITF) that incorporates a cognitive concept, Perceived Safety, to interpret drivers' decision-making mechanisms. Specifically, we develop a Perceived Safety-aware Module that includes a Quantitative Safety Assessment for measuring the subject risk levels within scenarios, and Driver Behavior Profiling for characterizing driver behaviors. Furthermore, we present a novel module, Leanformer, designed to capture social interactions among vehicles. CITF demonstrates significant performance improvements on three well-established datasets. Additionally, its robustness in scenarios with limited or missing data is evident, surpassing most state-of-the-art (SOT A) baselines, and paving the way for real-world applications. N the evolving landscape of autonomous driving (AD) systems, the complex interactions between autonomous vehicles (A Vs) and human-driven vehicles (HVs) present a significant challenge to achieving accurate trajectory prediction [1], [2]. The future trajectory of human-driven vehicles is essentially the result of the human driver's decision-making process [3], [4]. Corresponding author; * Authors contributed equally. Haicheng Liao, Chengyue Wang, Kaiqun Zhu, Chengzhong Xu, and Zhenning Li are with the State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau. Yilong Ren is with the School of Transportation Science and Engineering, Beihang University, Beijing, China. Bolin Gao and Shengbo Eben Li are with the School of V ehicle and Mobility, Tsinghua University, Beijing, China. This research is supported by the State Key Lab of Intelligent Transportation System under Project (2024-B001), Science and Technology Development Fund of Macau SAR (File no. Nevertheless, long-term prediction necessitates models that accurately estimate the impact of numerous factors on the decision-making process of human drivers, a feat that is particularly challenging to achieve [8].