Hybrid Kalman Recurrent Neural Network for Vehicle Trajectory Prediction
- 13 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
Abstract
Accurately forecasting the motion of surrounding vehicles is a crucial prerequisite for achieving safe autonomous driving. Methods for trajectory prediction encompass both physics- and learning-based approaches. Despite the significant advancements made by learning-based methods in enhancing performance, ensuring that predicted trajectories are realistic, interpretable, and physically feasible remains a challenging problem. In this study, we propose a physics-based deep learning framework founded on an encoder-decoder architecture, modeling the historical motion of traffic agents effectively coupled with the surrounding environment information through attention mechanisms. Our model incorporates the vehicle dynamic model to couple with vehicle motion and utilizes the Kalman filter to fuse scene context information for multi-step accurate and feasible multimodal trajectory prediction. Our method leverages the strengths of both learning- and physics-based models. The extensive experiment results on the Lyft l5 dataset demonstrate that our model outperforms various baseline approaches in terms of metrics including prediction errors, feasibility, and explainability.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB2703304)
- Liaoning Revitalization Talents Program
- National Natural Science Foundation of China (52074064, 62273078)
- Natural Science Foundation of Science and Technology Department of Liaoning Province (2021-BS-054)
- Fundamental Research Funds for the Central Universities (N2404013, N2404015)
This publication has 46 references indexed in Scilit:
- A physics-informed Transformer model for vehicle trajectory prediction on highwaysTransportation Research Part C: Emerging Technologies, 2023
- Explainable multimodal trajectory prediction using attention modelsTransportation Research Part C: Emerging Technologies, 2022
- Multimodal Motion Prediction with Stacked Transformers2021
- Hybrid Approach for Vehicle Trajectory Prediction Using Weighted Integration of Multiple ModelsIEEE Access, 2021
- SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints2019
- Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks2018
- Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization2017
- Social LSTM: Human Trajectory Prediction in Crowded Spaces2016
- Deep Residual Learning for Image Recognition2016
- Autonomous driving in urban environments: Boss and the Urban ChallengeJournal of Field Robotics, 2008