MSTF: Multiscale Transformer for Incomplete Trajectory Prediction

TL;DR

This paper introduces MSTF, a multiscale transformer framework designed to improve incomplete trajectory prediction in autonomous driving by effectively handling missing data through multiscale attention and adaptive pattern analysis.

Contribution

The paper proposes MSTF, a novel end-to-end model combining multiscale attention and adaptive pattern extraction to address missing data in trajectory prediction.

Findings

MSTF outperforms state-of-the-art models on real-world datasets.

The multiscale attention mechanism effectively captures global motion dependencies.

Adaptive pattern analysis improves prediction accuracy with incomplete data.

Abstract

Motion forecasting plays a pivotal role in autonomous driving systems, enabling vehicles to execute collision warnings and rational local-path planning based on predictions of the surrounding vehicles. However, prevalent methods often assume complete observed trajectories, neglecting the potential impact of missing values induced by object occlusion, scope limitation, and sensor failures. Such oversights inevitably compromise the accuracy of trajectory predictions. To tackle this challenge, we propose an end-to-end framework, termed Multiscale Transformer (MSTF), meticulously crafted for incomplete trajectory prediction. MSTF integrates a Multiscale Attention Head (MAH) and an Information Increment-based Pattern Adaptive (IIPA) module. Specifically, the MAH component concurrently captures multiscale motion representation of trajectory sequence from various temporal granularities, utilizing a multi-head attention mechanism. This approach facilitates the modeling of global dependencies in motion across different scales, thereby mitigating the adverse effects of missing values. Additionally, the IIPA module adaptively extracts continuity representation of motion across time steps by analyzing missing patterns in the data. The continuity representation delineates motion trend at a higher level, guiding MSTF to generate predictions consistent with motion continuity. We evaluate our proposed MSTF model using two large-scale real-world datasets. Experimental results demonstrate that MSTF surpasses state-of-the-art (SOTA) models in the task of incomplete trajectory prediction, showcasing its efficacy in addressing the challenges posed by missing values in motion forecasting for autonomous driving systems.