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 Multi-scale 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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MSTF: Multiscale Transformer for Incomplete Trajectory Prediction


    Contributors:
    Liu, Zhanwen (author) / Li, Chao (author) / Yang, Nan (author) / Wang, Yang (author) / Ma, Jiaqi (author) / Cheng, Guangliang (author) / Zhao, Xiangmo (author)


    Publication date :

    2024-06-02


    Size :

    2475299 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction

    Liu, Zhanwen / Li, Chao / Wang, Yang et al. | ArXiv | 2024

    Free access

    Egocentric Vulnerable Road Users Trajectory Prediction With Incomplete Observation

    Liu, Hui / Liu, Chunsheng / Chang, Faliang et al. | IEEE | 2024


    Ship trajectory prediction based on transformer model

    Kang, Kaihang / Zhang, Chuang / Guo, Chen | IEEE | 2022


    Ship trajectory prediction model based on transformer

    Li, Na / Huang, Yaoliang / Jiang, Dapeng | SPIE | 2023


    Self-Supervised Transformer for Trajectory Prediction Using Noise Imputed Past Trajectory

    Bharilya, Vibha / Arora, Ashok / Kumar, Neetesh | IEEE | 2025