Chuan Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chuan Hu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Biao Yang
1 shared publication- Biao Yang
Changzhou University
1 shared publication - Chao Wei
School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China
1 shared publication - Chaoyang Jiang
School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China
1 shared publication Chongfeng Wei
1 shared publicationGuofa Li
1 shared publication
Latest Publications
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (9) , 1-13
Graph Attention Transformer with Multi-Task Learning for Motion Prediction in Autonomous Driving
The motion prediction of surrounding vehicles is crucial for autonomous driving. As it can effectively guide the planning and decision-making of the autonomous vehicle. Although many methods have been proposed to predict the future motion of vehicles, but they failed capture the essense of multitask learning for vehicle motion prediction and lacked effective semantic and interaction information fusion. In this paper, we propose a novel model, Graph Attention Transformer with Multi- Task Learning (GATran), to predict the future motion of the target vehicle by modeling motion prediction task as a multi-task learning problem of trajectory prediction and driving intention estimation. The model consists of three modules: Feature Fusion, Spatio-Temporal Interaction, and Motion Decoder. The Feature Fusion module is used to effectively fuse the semantic and dynamic information of the target vehicle. The Spatial Interaction module is used to model the interaction between vehicles. The Motion Decoder module decouples the motion prediction into multi-task learning for trajectory prediction and driving intention estimation in a parallel manner. Extensive experiments on real-world datasets, with average improvement of 50% in NGSIM and 40% in HighD, demonstrate that the proposed model achieves superior performance.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (9) , 1-13
Graph Attention Transformer with Multi-Task Learning for Motion Prediction in Autonomous Driving
The motion prediction of surrounding vehicles is crucial for autonomous driving. As it can effectively guide the planning and decision-making of the autonomous vehicle. Although many methods have been proposed to predict the future motion of vehicles, but they failed capture the essense of multitask learning for vehicle motion prediction and lacked effective semantic and interaction information fusion. In this paper, we propose a novel model, Graph Attention Transformer with Multi- Task Learning (GATran), to predict the future motion of the target vehicle by modeling motion prediction task as a multi-task learning problem of trajectory prediction and driving intention estimation. The model consists of three modules: Feature Fusion, Spatio-Temporal Interaction, and Motion Decoder. The Feature Fusion module is used to effectively fuse the semantic and dynamic information of the target vehicle. The Spatial Interaction module is used to model the interaction between vehicles. The Motion Decoder module decouples the motion prediction into multi-task learning for trajectory prediction and driving intention estimation in a parallel manner. Extensive experiments on real-world datasets, with average improvement of 50% in NGSIM and 40% in HighD, demonstrate that the proposed model achieves superior performance.
- 25 December 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 142
Asymmetric multimodal guidance fusion network for realtime visible and thermal semantic segmentation
- 25 December 2024
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 142
Asymmetric multimodal guidance fusion network for realtime visible and thermal semantic segmentation
- 22 November 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 63
Adaptive risk tendency in uncertainty-aware motion planning using risk-sensitive Reinforcement Learning
- 22 November 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 63
Adaptive risk tendency in uncertainty-aware motion planning using risk-sensitive Reinforcement Learning
- 16 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (12) , 18571-18583
Path-Tracking and Lateral Stabilization for Automated Vehicles via Learning-Based Robust Model Predictive Control
It is a great challenge to guarantee both path-tracking performance and vehicle stability when suffering from aggressive uncertainties and severe disturbances. We design a novel learning-based robust model predictive path-tracking controller to alleviate the influence of disturbances, avoid over-conservative steering actions, and mediate the conflict between path-tracking and vehicle stability. Specifically, we firstly utilize the friction limits of tires and define an enveloped stable zone in the phase portrait which is used as safety constraints. Secondly, two approaches under the model predictive control (MPC) framework are employed to tackle the severe uncertainties and disturbances: 1) a deep neural network (DNN) dynamics model is employed to estimate the predictive error and attenuate the mismatch between the nominal model and actual plant; and 2) a local feedback linear quadratic regulator (LQR) is used to stabilize the system matrix, calculate invariant tube, and thus guarantee all state and control constraints are satisfied. Finally, real vehicle experiments indicate that the proposed controller can achieve an over 18% improvement in path-tracking performance and guarantee vehicle stability, even for cases with severe uncertainties and disturbances.
- 16 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 73 (12) , 18571-18583
Path-Tracking and Lateral Stabilization for Automated Vehicles via Learning-Based Robust Model Predictive Control
It is a great challenge to guarantee both path-tracking performance and vehicle stability when suffering from aggressive uncertainties and severe disturbances. We design a novel learning-based robust model predictive path-tracking controller to alleviate the influence of disturbances, avoid over-conservative steering actions, and mediate the conflict between path-tracking and vehicle stability. Specifically, we firstly utilize the friction limits of tires and define an enveloped stable zone in the phase portrait which is used as safety constraints. Secondly, two approaches under the model predictive control (MPC) framework are employed to tackle the severe uncertainties and disturbances: 1) a deep neural network (DNN) dynamics model is employed to estimate the predictive error and attenuate the mismatch between the nominal model and actual plant; and 2) a local feedback linear quadratic regulator (LQR) is used to stabilize the system matrix, calculate invariant tube, and thus guarantee all state and control constraints are satisfied. Finally, real vehicle experiments indicate that the proposed controller can achieve an over 18% improvement in path-tracking performance and guarantee vehicle stability, even for cases with severe uncertainties and disturbances.
- Open Access
- 22 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 298-302
A Hybrid Approach for Efficient Traffic Sign Detection Using Yolov8 And SAM
In this study, we present an innovative hybrid approach for traffic sign detection in autonomous driving, combining YOLOv8’s real-time detection capabilities with the Segment Anything Model (SAM), enhanced through Visual Prompt Tuning. This methodology addresses the challenge of accurately identifying diverse traffic signs, particularly those that are less common or visually complex. After the initial detection by YOLOv8, the SAM (Segment Anything Model), enhanced with Visual Prompt Tuning, is then applied to refine and improve the accuracy of these detections, especially for signs that are less common or have complex visual features. This two-step process, combining the quick detection capabilities of YOLOv8 with the detailed segmentation ability of SAM, aims to achieve high accuracy in traffic sign recognition, which is essential for the safe operation of autonomous vehicles.
- 22 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 298-302
Open AccessA Hybrid Approach for Efficient Traffic Sign Detection Using Yolov8 And SAM
In this study, we present an innovative hybrid approach for traffic sign detection in autonomous driving, combining YOLOv8’s real-time detection capabilities with the Segment Anything Model (SAM), enhanced through Visual Prompt Tuning. This methodology addresses the challenge of accurately identifying diverse traffic signs, particularly those that are less common or visually complex. After the initial detection by YOLOv8, the SAM (Segment Anything Model), enhanced with Visual Prompt Tuning, is then applied to refine and improve the accuracy of these detections, especially for signs that are less common or have complex visual features. This two-step process, combining the quick detection capabilities of YOLOv8 with the detailed segmentation ability of SAM, aims to achieve high accuracy in traffic sign recognition, which is essential for the safe operation of autonomous vehicles.