Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving

TL;DR

This paper introduces CRiTIC, a causal attention gating model that enhances the robustness and generalization of trajectory prediction in autonomous driving by identifying and filtering non-causal agent influences.

Contribution

The paper proposes a novel causal discovery and attention mechanism within a Transformer architecture to improve trajectory prediction robustness and cross-domain generalization.

Findings

Robustness improved by up to 54% against non-causal perturbations.

Cross-domain performance increased by up to 29%.

The model outperforms existing methods in robustness and generalization.

Abstract

Trajectory prediction models in autonomous driving are vulnerable to perturbations from non-causal agents whose actions should not affect the ego-agent's behavior. Such perturbations can lead to incorrect predictions of other agents' trajectories, potentially compromising the safety and efficiency of the ego-vehicle's decision-making process. Motivated by this challenge, we propose $\textit{Causal tRajecTory predICtion}$ $\textbf{(CRiTIC)}$, a novel model that utilizes a $\textit{Causal Discovery Network}$ to identify inter-agent causal relations over a window of past time steps. To incorporate discovered causal relationships, we propose a novel $\textit{Causal Attention Gating}$ mechanism to selectively filter information in the proposed Transformer-based architecture. We conduct extensive experiments on two autonomous driving benchmark datasets to evaluate the robustness of our model against non-causal perturbations and its generalization capacity. Our results indicate that the robustness of predictions can be improved by up to $\textbf{54%}$ without a significant detriment to prediction accuracy. Lastly, we demonstrate the superior domain generalizability of the proposed model, which achieves up to $\textbf{29%}$ improvement in cross-domain performance. These results underscore the potential of our model to enhance both robustness and generalization capacity for trajectory prediction in diverse autonomous driving domains. Further details can be found on our project page: https://ehsan-ami.github.io/critic.