Huizhao Tu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Huizhao Tu has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Hao Li
Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, Shanghai 201804, China
13 shared publications Hao Li
12 shared publicationsLijun Sun
College of Transportation Engineering, Tongji University, Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Shanghai, P. R. China
9 shared publications- Henk. J. van Zuylen
Delft University of Technology, the Netherlands
6 shared publications - Zhicheng Jin
College of Transportation Engineering, Tongji University, Shanghai, China
5 shared publications - Kun Gao
Chalmers University of Technology
4 shared publications
Latest Publications
- Open Access
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Safety-aware eVTOL Trajectory Planning in Urban Canyon Environments: A Knowledge-Guided Fuzzy Double DQN Approach
Safety-aware electric vertical takeoff and landing (eVTOL) aircraft trajectory planning in dense urban canyon environments is challenging due to complex geometric constraints and limited maneuvering space. Traditional heuristic and sampling-based planners struggle with high-dimensional 3-D environments, while purely data-driven reinforcement learning methods often lack a structured way to incorporate explicit geometric safety information. To bridge this gap, this paper proposes a Knowledge-Guided Fuzzy Double DQN (KF-DDQN) approach for voxel-level eVTOL trajectory planning with clearance-based fuzzy guidance. In the proposed method, Double Deep Q-Network (DDQN) serves as the reward-driven value-learning backbone, coupled with a fuzzy inference module that maps building-clearance constraints into action-wise safety guidance values. By integrating these guidance values into action selection and target-value formulation, the planner balances the long-term task performance with local obstacle avoidance. Experiments in procedurally generated 3-D voxel urban canyon environments show that KF-DDQN enhances the mission success rate from 0.797 to 0.938 and reduces collision attempts by approximately 44% compared with standard DDQN, and increases the average safety clearance from 2.779 to 3.221 voxels, while maintaining comparable path efficiency. The parameter sensitivity analysis further confirms that the knowledge-weighting factor λ_fuzzy controls the trade-off between safety clearance and path efficiency. These results indicate that incorporating building-clearance-based fuzzy guidance into DDQN can improve safety-related trajectory metrics in voxelized urban canyon environments.
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSafety-aware eVTOL Trajectory Planning in Urban Canyon Environments: A Knowledge-Guided Fuzzy Double DQN Approach
Safety-aware electric vertical takeoff and landing (eVTOL) aircraft trajectory planning in dense urban canyon environments is challenging due to complex geometric constraints and limited maneuvering space. Traditional heuristic and sampling-based planners struggle with high-dimensional 3-D environments, while purely data-driven reinforcement learning methods often lack a structured way to incorporate explicit geometric safety information. To bridge this gap, this paper proposes a Knowledge-Guided Fuzzy Double DQN (KF-DDQN) approach for voxel-level eVTOL trajectory planning with clearance-based fuzzy guidance. In the proposed method, Double Deep Q-Network (DDQN) serves as the reward-driven value-learning backbone, coupled with a fuzzy inference module that maps building-clearance constraints into action-wise safety guidance values. By integrating these guidance values into action selection and target-value formulation, the planner balances the long-term task performance with local obstacle avoidance. Experiments in procedurally generated 3-D voxel urban canyon environments show that KF-DDQN enhances the mission success rate from 0.797 to 0.938 and reduces collision attempts by approximately 44% compared with standard DDQN, and increases the average safety clearance from 2.779 to 3.221 voxels, while maintaining comparable path efficiency. The parameter sensitivity analysis further confirms that the knowledge-weighting factor λ_fuzzy controls the trade-off between safety clearance and path efficiency. These results indicate that incorporating building-clearance-based fuzzy guidance into DDQN can improve safety-related trajectory metrics in voxelized urban canyon environments.
- 17 December 2025
- Published by Elsevier in Measurement
- Vol. 263
μ-FINO: A friction-informed neural operator for cross-scale tire/road friction prediction using vehicle-mounted 3D lasers
- 17 December 2025
- Published by Elsevier in Measurement
- Vol. 263
μ-FINO: A friction-informed neural operator for cross-scale tire/road friction prediction using vehicle-mounted 3D lasers
- 20 November 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 225, 108313
Multi-factor coupled friction coefficient map spatiotemporal modeling and driving risk fusion for rainy roads
- 20 November 2025
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 225, 108313
Multi-factor coupled friction coefficient map spatiotemporal modeling and driving risk fusion for rainy roads
- 5 August 2025
- Published by Elsevier in Travel Behaviour and Society
- Vol. 41
The impact of ride experience on car travelers’ adoption of private and shared autonomous vehicles
- 5 August 2025
- Published by Elsevier in Travel Behaviour and Society
- Vol. 41
The impact of ride experience on car travelers’ adoption of private and shared autonomous vehicles
- Open Access
- 26 November 2024
- Published by Elsevier in Communications in Transportation Research
- Vol. 4
Multi-objective optimization model of autonomous minibus considering passenger arrival reliability and travel risk
- 26 November 2024
- Published by Elsevier in Communications in Transportation Research
- Vol. 4
Open AccessMulti-objective optimization model of autonomous minibus considering passenger arrival reliability and travel risk
- 23 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19605-19618
Risk-Anticipatory Autonomous Driving Strategies Considering Vehicles’ Weights Based on Hierarchical Deep Reinforcement Learning
Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers’ errors and reduce road traffic risks. Due to the nature of heavy vehicles, whose collisions cause more serious crashes, the weights of vehicles need to be considered when making driving strategies aimed at reducing the potential risks and their consequences in the context of autonomous driving. This study develops an autonomous driving strategy based on risk anticipation, considering the weights of surrounding vehicles and using hierarchical deep reinforcement learning. A risk indicator integrating surrounding vehicles’ weights, based on the risk field theory, is proposed and incorporated into autonomous driving decisions. A hybrid action space is designed to allow for left lane changes, right lane changes and car-following, which enables AVs to act more freely and realistically whenever possible. To solve the above hybrid decision-making problem, a hierarchical proximal policy optimization (HPPO) algorithm with an attention mechanism (AT-HPPO) is developed, providing great advantages in maintaining stable performance with high robustness and generalization. An indicator, potential collision energy in conflicts (PCEC), is newly proposed to evaluate the performance of the developed AV driving strategy from the perspective of the consequences of potential accidents. The performance evaluation results in simulation and dataset demonstrate that our model provides driving strategies that reduce both the likelihood and consequences of potential accidents, at the same time maintaining driving efficiency. The developed method is especially meaningful for AVs driving on highways, where heavy vehicles make up a high proportion of the traffic.
- 23 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19605-19618
Risk-Anticipatory Autonomous Driving Strategies Considering Vehicles’ Weights Based on Hierarchical Deep Reinforcement Learning
Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers’ errors and reduce road traffic risks. Due to the nature of heavy vehicles, whose collisions cause more serious crashes, the weights of vehicles need to be considered when making driving strategies aimed at reducing the potential risks and their consequences in the context of autonomous driving. This study develops an autonomous driving strategy based on risk anticipation, considering the weights of surrounding vehicles and using hierarchical deep reinforcement learning. A risk indicator integrating surrounding vehicles’ weights, based on the risk field theory, is proposed and incorporated into autonomous driving decisions. A hybrid action space is designed to allow for left lane changes, right lane changes and car-following, which enables AVs to act more freely and realistically whenever possible. To solve the above hybrid decision-making problem, a hierarchical proximal policy optimization (HPPO) algorithm with an attention mechanism (AT-HPPO) is developed, providing great advantages in maintaining stable performance with high robustness and generalization. An indicator, potential collision energy in conflicts (PCEC), is newly proposed to evaluate the performance of the developed AV driving strategy from the perspective of the consequences of potential accidents. The performance evaluation results in simulation and dataset demonstrate that our model provides driving strategies that reduce both the likelihood and consequences of potential accidents, at the same time maintaining driving efficiency. The developed method is especially meaningful for AVs driving on highways, where heavy vehicles make up a high proportion of the traffic.
- 15 July 2024
- Published by Taylor & Francis in Journal of Transportation Safety & Security
- Vol. 17 (2) , 177-207
Effects of high-speed rail illumination on traffic safety at night in a road-cum-railway section – Implications for the infrastructure design
- 15 July 2024
- Published by Taylor & Francis in Journal of Transportation Safety & Security
- Vol. 17 (2) , 177-207
Effects of high-speed rail illumination on traffic safety at night in a road-cum-railway section – Implications for the infrastructure design
- Open Access
- 1 January 2024
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2024 (1)
Accounting for BEV Users’ Risk Attitudes and Charging Inertia in En Route Charging Choice Behavior
This paper innovatively explores BEV (battery electric vehicle) users’ risk attitudes and charging inertia, examining their effects on en route charging and charging route choice behavior. An attitudinal survey was conducted to explore the two latent variables of risk attitudes and charging inertia in relation to socioeconomic and travel‐related characteristics. ICLV (Integrated choice and latent variable) models are adopted to estimate the latent variables and the charging choice behavior simultaneously. Specifically, uncertainty in energy consumption is first considered in the ICLV model, which is represented by the available range (AR) uncertainty. Multinomial logit (MNL) models directly incorporating socioeconomic attributes are employed as a reference for comparison with ICLV models. Results illustrate that risk attitudes and charging inertia both play significant roles in modeling en route charging choice behavior. Risk‐averse users and users having charging inertia value AR uncertainty more. Battery range, charging frequency, and income emerge as the most crucial factors influencing users’ intention to charge en route. The results show significant heterogeneity of BEV users in attitudes and charging choice behavior, underscoring the importance of accounting for the heterogeneity in en route charging demand estimation and deployment optimization of public charging stations, particularly for medium‐to long‐distance trips.
- 1 January 2024
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2024 (1)
Open AccessAccounting for BEV Users’ Risk Attitudes and Charging Inertia in En Route Charging Choice Behavior
This paper innovatively explores BEV (battery electric vehicle) users’ risk attitudes and charging inertia, examining their effects on en route charging and charging route choice behavior. An attitudinal survey was conducted to explore the two latent variables of risk attitudes and charging inertia in relation to socioeconomic and travel‐related characteristics. ICLV (Integrated choice and latent variable) models are adopted to estimate the latent variables and the charging choice behavior simultaneously. Specifically, uncertainty in energy consumption is first considered in the ICLV model, which is represented by the available range (AR) uncertainty. Multinomial logit (MNL) models directly incorporating socioeconomic attributes are employed as a reference for comparison with ICLV models. Results illustrate that risk attitudes and charging inertia both play significant roles in modeling en route charging choice behavior. Risk‐averse users and users having charging inertia value AR uncertainty more. Battery range, charging frequency, and income emerge as the most crucial factors influencing users’ intention to charge en route. The results show significant heterogeneity of BEV users in attitudes and charging choice behavior, underscoring the importance of accounting for the heterogeneity in en route charging demand estimation and deployment optimization of public charging stations, particularly for medium‐to long‐distance trips.