A survey on robustness in trajectory prediction for autonomous vehicles

TL;DR

This survey reviews the current landscape of robustness in trajectory prediction for autonomous vehicles, highlighting challenges, strategies, and promising methods to enhance safety and reliability.

Contribution

It provides a comprehensive categorization and assessment of existing approaches to evaluate and improve robustness in trajectory prediction models.

Findings

Many promising methods for increasing robustness identified

Robustness strategies include data slicing, perturbation, and model adjustments

Addressing overfitting is crucial for safe autonomous driving

Abstract

Autonomous vehicles rely on accurate trajectory prediction to inform decision-making processes related to navigation and collision avoidance. However, current trajectory prediction models show signs of overfitting, which may lead to unsafe or suboptimal behavior. To address these challenges, this paper presents a comprehensive framework that categorizes and assesses the definitions and strategies used in the literature on evaluating and improving the robustness of trajectory prediction models. This involves a detailed exploration of various approaches, including data slicing methods, perturbation techniques, model architecture changes, and post-training adjustments. In the literature, we see many promising methods for increasing robustness, which are necessary for safe and reliable autonomous driving.