A Cognitive-Based Trajectory Prediction Approach for Autonomous Driving

TL;DR

This paper presents a human-inspired trajectory prediction model for autonomous vehicles that leverages a teacher-student knowledge distillation framework to improve prediction accuracy in dynamic driving scenarios.

Contribution

It introduces the HLTP model, integrating cognitive-inspired visual processing and decision-making mechanisms within a knowledge distillation framework for AV trajectory prediction.

Findings

HLTP outperforms existing models on MoCAD, NGSIM, and HighD datasets.

The model effectively handles incomplete data in complex environments.

Incorporates human cognitive processes into trajectory prediction.

Abstract

In autonomous vehicle (AV) technology, the ability to accurately predict the movements of surrounding vehicles is paramount for ensuring safety and operational efficiency. Incorporating human decision-making insights enables AVs to more effectively anticipate the potential actions of other vehicles, significantly improving prediction accuracy and responsiveness in dynamic environments. This paper introduces the Human-Like Trajectory Prediction (HLTP) model, which adopts a teacher-student knowledge distillation framework inspired by human cognitive processes. The HLTP model incorporates a sophisticated teacher-student knowledge distillation framework. The "teacher" model, equipped with an adaptive visual sector, mimics the visual processing of the human brain, particularly the functions of the occipital and temporal lobes. The "student" model focuses on real-time interaction and decision-making, drawing parallels to prefrontal and parietal cortex functions. This approach allows for dynamic adaptation to changing driving scenarios, capturing essential perceptual cues for accurate prediction. Evaluated using the Macao Connected and Autonomous Driving (MoCAD) dataset, along with the NGSIM and HighD benchmarks, HLTP demonstrates superior performance compared to existing models, particularly in challenging environments with incomplete data. The project page is available at Github.