Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling
Autonomous vehicles need to continuously analyse the driving context and establish a comprehensive understanding of the dynamic traffic environment. To ensure the safety and efficiency of their operations, it would be beneficial to have accurate predictions of surrounding vehicles’ future...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843350/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540467355451392 |
|---|---|
| author | Yuxiang Feng Qiming Ye Eduardo Candela Jose Javier Escribano-Macias Bo Hu Yiannis Demiris Panagiotis Angeloudis |
| author_facet | Yuxiang Feng Qiming Ye Eduardo Candela Jose Javier Escribano-Macias Bo Hu Yiannis Demiris Panagiotis Angeloudis |
| author_sort | Yuxiang Feng |
| collection | DOAJ |
| description | Autonomous vehicles need to continuously analyse the driving context and establish a comprehensive understanding of the dynamic traffic environment. To ensure the safety and efficiency of their operations, it would be beneficial to have accurate predictions of surrounding vehicles’ future trajectories. AVs can adjust their motions proactively to improve road safety and comfort with such information. This paper proposes a novel approach to predict the future trajectories of interacting vehicles, through a model of potential spatial-temporal interactions. A unique kernel function that emphasises risk-awareness was developed to extract spatial dependencies. The established model was trained and evaluated with the publicly available Highway Drone Dataset and Intersection Drone Dataset. The performance of the developed model was assessed with eight state-of-the-art methods. An ablation study and safety analysis were also conducted to evaluate the proposed risk-awareness kernel function. Results show that the proposed model’s inference speed is over eight times faster than the commonly used LSTM-based models. It also achieves an improvement of over 8% in prediction accuracy when compared with the state-of-the-art model. |
| format | Article |
| id | doaj-art-762cde6260be411db067bb95d37215a1 |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-762cde6260be411db067bb95d37215a12025-02-05T00:01:22ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132025-01-016374810.1109/OJITS.2025.353026810843350Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction ModelingYuxiang Feng0https://orcid.org/0000-0002-5530-2503Qiming Ye1Eduardo Candela2Jose Javier Escribano-Macias3Bo Hu4https://orcid.org/0000-0003-2995-2358Yiannis Demiris5https://orcid.org/0000-0003-4917-3343Panagiotis Angeloudis6https://orcid.org/0000-0002-6778-8264Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modeling, Imperial College London, London, U.K.Future Cities Laboratory Global, Singapore Hub, Singapore-ETH Centre at CREATE, Create Wy, SingaporeDepartment of Civil and Environmental Engineering, Centre for Transport Engineering and Modeling, Imperial College London, London, U.K.Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modeling, Imperial College London, London, U.K.School of Vehicle Engineering, Chongqing University of Technology, Chongqing, ChinaDepartment of Electrical and Electronic Engineering, Personal Robotics Laboratory, Imperial College London, London, U.K.Department of Civil and Environmental Engineering, Centre for Transport Engineering and Modeling, Imperial College London, London, U.K.Autonomous vehicles need to continuously analyse the driving context and establish a comprehensive understanding of the dynamic traffic environment. To ensure the safety and efficiency of their operations, it would be beneficial to have accurate predictions of surrounding vehicles’ future trajectories. AVs can adjust their motions proactively to improve road safety and comfort with such information. This paper proposes a novel approach to predict the future trajectories of interacting vehicles, through a model of potential spatial-temporal interactions. A unique kernel function that emphasises risk-awareness was developed to extract spatial dependencies. The established model was trained and evaluated with the publicly available Highway Drone Dataset and Intersection Drone Dataset. The performance of the developed model was assessed with eight state-of-the-art methods. An ablation study and safety analysis were also conducted to evaluate the proposed risk-awareness kernel function. Results show that the proposed model’s inference speed is over eight times faster than the commonly used LSTM-based models. It also achieves an improvement of over 8% in prediction accuracy when compared with the state-of-the-art model.https://ieeexplore.ieee.org/document/10843350/Stochastic trajectory predictionrisk awarenessspatial-temporal modellingautonomous vehicles |
| spellingShingle | Yuxiang Feng Qiming Ye Eduardo Candela Jose Javier Escribano-Macias Bo Hu Yiannis Demiris Panagiotis Angeloudis Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling IEEE Open Journal of Intelligent Transportation Systems Stochastic trajectory prediction risk awareness spatial-temporal modelling autonomous vehicles |
| title | Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling |
| title_full | Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling |
| title_fullStr | Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling |
| title_full_unstemmed | Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling |
| title_short | Risk-Aware Stochastic Vehicle Trajectory Prediction With Spatial-Temporal Interaction Modeling |
| title_sort | risk aware stochastic vehicle trajectory prediction with spatial temporal interaction modeling |
| topic | Stochastic trajectory prediction risk awareness spatial-temporal modelling autonomous vehicles |
| url | https://ieeexplore.ieee.org/document/10843350/ |
| work_keys_str_mv | AT yuxiangfeng riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT qimingye riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT eduardocandela riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT josejavierescribanomacias riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT bohu riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT yiannisdemiris riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling AT panagiotisangeloudis riskawarestochasticvehicletrajectorypredictionwithspatialtemporalinteractionmodeling |