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

TL;DR

This paper introduces a cognitive-informed transformer model for autonomous driving trajectory prediction, integrating driver decision-making insights to improve long-term accuracy and robustness in mixed traffic environments.

Contribution

It proposes a novel Cognitive-Informed Transformer that incorporates perceived safety and driver behavior profiling, enhancing trajectory prediction by understanding human decision-making processes.

Findings

Achieves 12.0% improvement on NGSIM dataset

Achieves 28.2% improvement on HighD dataset

Outperforms state-of-the-art methods in scenarios with limited data

Abstract

In mixed autonomous driving environments, accurately predicting the future trajectories of surrounding vehicles is crucial for the safe operation of autonomous vehicles (AVs). 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. To address this limitation, we introduce a Cognitive-Informed Transformer (CITF) that incorporates a cognitive concept, Perceived Safety, to interpret drivers' decision-making mechanisms. Perceived Safety encapsulates the varying risk tolerances across drivers with different driving behaviors. 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. In terms of long-term prediction, it surpasses existing benchmarks by 12.0% on the NGSIM, 28.2% on the HighD, and 20.8% on the MoCAD dataset. Additionally, its robustness in scenarios with limited or missing data is evident, surpassing most state-of-the-art (SOTA) baselines, and paving the way for real-world applications.