Human Observation-Inspired Trajectory Prediction for Autonomous Driving in Mixed-Autonomy Traffic Environments

TL;DR

This paper introduces a human cognition-inspired trajectory prediction model for autonomous vehicles in mixed traffic, utilizing adaptive attention mechanisms and graph-based spatio-temporal modeling to improve prediction accuracy.

Contribution

It presents a novel interdisciplinary approach combining human observational principles with advanced neural network architectures for trajectory prediction.

Findings

Outperforms state-of-the-art models by at least 15.2% on NGSIM dataset

Achieves 19.4% improvement on HighD dataset

Demonstrates enhanced adaptability and accuracy in mixed-autonomy traffic environments

Abstract

In the burgeoning field of autonomous vehicles (AVs), trajectory prediction remains a formidable challenge, especially in mixed autonomy environments. Traditional approaches often rely on computational methods such as time-series analysis. Our research diverges significantly by adopting an interdisciplinary approach that integrates principles of human cognition and observational behavior into trajectory prediction models for AVs. We introduce a novel "adaptive visual sector" mechanism that mimics the dynamic allocation of attention human drivers exhibit based on factors like spatial orientation, proximity, and driving speed. Additionally, we develop a "dynamic traffic graph" using Convolutional Neural Networks (CNN) and Graph Attention Networks (GAT) to capture spatio-temporal dependencies among agents. Benchmark tests on the NGSIM, HighD, and MoCAD datasets reveal that our model (GAVA) outperforms state-of-the-art baselines by at least 15.2%, 19.4%, and 12.0%, respectively. Our findings underscore the potential of leveraging human cognition principles to enhance the proficiency and adaptability of trajectory prediction algorithms in AVs. The code for the proposed model is available at our Github.