Holistic Transformer: A Joint Neural Network for Trajectory Prediction and Decision-Making of Autonomous Vehicles

TL;DR

This paper introduces a holistic transformer model that jointly predicts trajectories and makes behavioral decisions for autonomous vehicles, leveraging multiple cues and attention mechanisms for improved performance and interpretability.

Contribution

The paper presents a novel joint neural network architecture that combines trajectory prediction and decision-making, utilizing multiple attention mechanisms to better exploit environmental cues.

Findings

Outperforms existing models in trajectory prediction accuracy

Demonstrates robustness to perceptual noise

Enhances interpretability of decision-making processes

Abstract

Trajectory prediction and behavioral decision-making are two important tasks for autonomous vehicles that require good understanding of the environmental context; behavioral decisions are better made by referring to the outputs of trajectory predictions. However, most current solutions perform these two tasks separately. Therefore, a joint neural network that combines multiple cues is proposed and named as the holistic transformer to predict trajectories and make behavioral decisions simultaneously. To better explore the intrinsic relationships between cues, the network uses existing knowledge and adopts three kinds of attention mechanisms: the sparse multi-head type for reducing noise impact, feature selection sparse type for optimally using partial prior knowledge, and multi-head with sigmoid activation type for optimally using posteriori knowledge. Compared with other trajectory prediction models, the proposed model has better comprehensive performance and good interpretability. Perceptual noise robustness experiments demonstrate that the proposed model has good noise robustness. Thus, simultaneous trajectory prediction and behavioral decision-making combining multiple cues can reduce computational costs and enhance semantic relationships between scenes and agents.