Kai Cao
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
Kai Cao has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Yanding Yang
Research Development Institute of Dongfeng Motor Group Company Ltd., Wuhan, China
3 shared publications Dongpu Cao
State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China
2 shared publications- Tantan Zhang
College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China
2 shared publications - Wen Hu
School of Vehicle and Mobility, Tsinghua University, Beijing, China
2 shared publications - Zejian Deng
Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON, Canada
2 shared publications Bangji Zhang
Intelligent Transportation System Research Center, Hangzhou City University, Hangzhou, China
1 shared publication
Latest Publications
- Top Cited Papers
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (11) , 17005-17018
Socially Game-Theoretic Lane-Change for Autonomous Heavy Vehicle Based on Asymmetric Driving Aggressiveness
The existing autonomous driving systems present poor performance for heavy vehicles, and face challenges gaining acceptance from surrounding vehicles in the interactive scenarios due to the deficiency of sociality. Therefore, a socially game-theoretic decision-making method is proposed in this study. Firstly, the concept of asymmetric driving aggressiveness is introduced to construct the decision-making model, ensuring driving safety and sociality across different vehicle types. Secondly, a socialized lane-change model for autonomous heavy vehicles is proposed based on the asymmetric aggressiveness and game theory with incomplete information. Subsequently, the cooperativeness of the interactive vehicle is estimated to eliminate the uncertainty through the combination of trajectory prediction and driving environment assessment. Finally, two conventional decisionmaking models are used as benchmarks to validate the effectiveness and robustness of the proposed method using naturalistic driving data. The results demonstrate that the socially game-theoretic lane-change model can generate safe and socialized decisions by estimating the cooperativeness of interactive vehicle. Besides, the proposed method exhibits enhanced social-friendliness with minimal impact on other vehicles and excellent robustness in navigating dynamic and complex traffic environment. Despite a slight reduction in driving efficiency, it still demonstrates a better adaptability and compatibility for autonomous heavy vehicles because the depressed performances are not the primary concerns.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (11) , 17005-17018
Top Cited PapersSocially Game-Theoretic Lane-Change for Autonomous Heavy Vehicle Based on Asymmetric Driving Aggressiveness
The existing autonomous driving systems present poor performance for heavy vehicles, and face challenges gaining acceptance from surrounding vehicles in the interactive scenarios due to the deficiency of sociality. Therefore, a socially game-theoretic decision-making method is proposed in this study. Firstly, the concept of asymmetric driving aggressiveness is introduced to construct the decision-making model, ensuring driving safety and sociality across different vehicle types. Secondly, a socialized lane-change model for autonomous heavy vehicles is proposed based on the asymmetric aggressiveness and game theory with incomplete information. Subsequently, the cooperativeness of the interactive vehicle is estimated to eliminate the uncertainty through the combination of trajectory prediction and driving environment assessment. Finally, two conventional decisionmaking models are used as benchmarks to validate the effectiveness and robustness of the proposed method using naturalistic driving data. The results demonstrate that the socially game-theoretic lane-change model can generate safe and socialized decisions by estimating the cooperativeness of interactive vehicle. Besides, the proposed method exhibits enhanced social-friendliness with minimal impact on other vehicles and excellent robustness in navigating dynamic and complex traffic environment. Despite a slight reduction in driving efficiency, it still demonstrates a better adaptability and compatibility for autonomous heavy vehicles because the depressed performances are not the primary concerns.
- 6 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 8772-8783
An Anytime Trajectory Optimizer for Accurately Parking an Autonomous Vehicle in Tiny Spaces
Parking in tiny and cluttered slots is a critical challenge for automated parking systems, where the planning module serves as a core component responsible for generating collision-free and kinematically feasible trajectories. However, existing methods face significant limitations, such as geometric-based approaches generating paths rather than trajectories, mass point models failing in tiny berths, and full-dimensional models with large-scale constraints lead to time-intensive computations. To address these issues, this paper proposes an anytime trajectory optimizer for accurately parking an autonomous vehicle in tiny spaces cluttered with obstacles. The proposed method incorporates differentiable collision-avoidance constraints and a trust region strategy to improve computational efficiency. It can also iteratively refine the solution, enabling the optimizer to converge to a new minimum by breaking previous constraints and establishing new ones. Extensive simulations show the proposed method outperforms mainstream planners, effectively handling cluttered environments and tiny parking slots where others fail, or outperforming them in speed when they succeed. It reduces runtime by 90.19% compared to the baseline, while ensuring feasibility and continuous optimization.
- 6 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (6) , 8772-8783
An Anytime Trajectory Optimizer for Accurately Parking an Autonomous Vehicle in Tiny Spaces
Parking in tiny and cluttered slots is a critical challenge for automated parking systems, where the planning module serves as a core component responsible for generating collision-free and kinematically feasible trajectories. However, existing methods face significant limitations, such as geometric-based approaches generating paths rather than trajectories, mass point models failing in tiny berths, and full-dimensional models with large-scale constraints lead to time-intensive computations. To address these issues, this paper proposes an anytime trajectory optimizer for accurately parking an autonomous vehicle in tiny spaces cluttered with obstacles. The proposed method incorporates differentiable collision-avoidance constraints and a trust region strategy to improve computational efficiency. It can also iteratively refine the solution, enabling the optimizer to converge to a new minimum by breaking previous constraints and establishing new ones. Extensive simulations show the proposed method outperforms mainstream planners, effectively handling cluttered environments and tiny parking slots where others fail, or outperforming them in speed when they succeed. It reduces runtime by 90.19% compared to the baseline, while ensuring feasibility and continuous optimization.
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (3) , 4432-4444
Uncertainty-Aware Decision Making and Planning for ICV Based on Asymmetric Driving Aggressiveness
Precisely assessing driving threat of road segments could significantly enhance the driving efficiency of intelligent connected vehicles (ICV) within mixed traffic scenarios. Existing methods primarily concentrate on collision probabilities, resulting in an insufficient appraisal of asymmetrical hazard levels attributed to the various interactions. Meanwhile, the uncertainty and communication delay have great influence on ICV, and it is an issue that must be addressed when designing decision-making and planning model. Thus, this study proposes and formulates a new driving aggressiveness model after analyzing asymmetric interactions behaviors among vehicles with different types. Subsequently, aims to verify the capability of generating asymmetric interaction, the driving aggressiveness model is applied on lane-change decision-making and planning. Concretely, the aggressiveness-sensitive lanes-selection model is designed based on game theory, and the uncertainty-aware trajectory planning is developed by utilizing stochastic model predictive control (MPC) and the asymmetric driving aggressiveness. Finally, two naturalistic driving scenarios are utilized to verify the performance of the decision-making and planning model. The outcomes of simulations illustrate that the driving aggressiveness model introduces a novel perspective to assess the asymmetric driving threat. Meanwhile, the uncertainty-aware decision making and planning model can reduce the influence on interactive vehicles, and it has superior adaptability for dynamic and connected traffic environments.
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (3) , 4432-4444
Uncertainty-Aware Decision Making and Planning for ICV Based on Asymmetric Driving Aggressiveness
Precisely assessing driving threat of road segments could significantly enhance the driving efficiency of intelligent connected vehicles (ICV) within mixed traffic scenarios. Existing methods primarily concentrate on collision probabilities, resulting in an insufficient appraisal of asymmetrical hazard levels attributed to the various interactions. Meanwhile, the uncertainty and communication delay have great influence on ICV, and it is an issue that must be addressed when designing decision-making and planning model. Thus, this study proposes and formulates a new driving aggressiveness model after analyzing asymmetric interactions behaviors among vehicles with different types. Subsequently, aims to verify the capability of generating asymmetric interaction, the driving aggressiveness model is applied on lane-change decision-making and planning. Concretely, the aggressiveness-sensitive lanes-selection model is designed based on game theory, and the uncertainty-aware trajectory planning is developed by utilizing stochastic model predictive control (MPC) and the asymmetric driving aggressiveness. Finally, two naturalistic driving scenarios are utilized to verify the performance of the decision-making and planning model. The outcomes of simulations illustrate that the driving aggressiveness model introduces a novel perspective to assess the asymmetric driving threat. Meanwhile, the uncertainty-aware decision making and planning model can reduce the influence on interactive vehicles, and it has superior adaptability for dynamic and connected traffic environments.
- Open Access
- 9 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3820
Joint Dispatching and Cooperative Trajectory Planning for Multiple Autonomous Forklifts in a Warehouse: A Search-and-Learning-Based Approach
Dispatching and cooperative trajectory planning for multiple autonomous forklifts in a warehouse is a widely applied research topic. The conventional methods in this domain regard dispatching and planning as isolated procedures, which render the overall motion quality of the forklift team imperfect. The dispatching and planning problems should be considered simultaneously to achieve optimal cooperative trajectories. However, this approach renders a large-scale nonconvex problem, which is extremely difficult to solve in real time. A joint dispatching and planning method is proposed to balance solution quality and speed. The proposed method is characterized by its fast runtime, light computational burden, and high solution quality. In particular, the candidate goals of each forklift are enumerated. Each candidate dispatch solution is measured after concrete trajectories are generated via an improved hybrid A* search algorithm, which is incorporated with an artificial neural network to improve the cost evaluation process. The proposed joint dispatching and planning method is computationally cheap, kinematically feasible, avoids collisions with obstacles/forklifts, and finds the global optimum quickly. The presented motion planning strategy demonstrates that the integration of a neural network with the dispatching approach leads to a warehouse filling/emptying mission completion time that is 2% shorter than the most efficient strategy lacking machine-learning integration. Notably, the mission completion times across these strategies vary by approximately 15%.
- 9 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (18) , 3820
Open AccessJoint Dispatching and Cooperative Trajectory Planning for Multiple Autonomous Forklifts in a Warehouse: A Search-and-Learning-Based Approach
Dispatching and cooperative trajectory planning for multiple autonomous forklifts in a warehouse is a widely applied research topic. The conventional methods in this domain regard dispatching and planning as isolated procedures, which render the overall motion quality of the forklift team imperfect. The dispatching and planning problems should be considered simultaneously to achieve optimal cooperative trajectories. However, this approach renders a large-scale nonconvex problem, which is extremely difficult to solve in real time. A joint dispatching and planning method is proposed to balance solution quality and speed. The proposed method is characterized by its fast runtime, light computational burden, and high solution quality. In particular, the candidate goals of each forklift are enumerated. Each candidate dispatch solution is measured after concrete trajectories are generated via an improved hybrid A* search algorithm, which is incorporated with an artificial neural network to improve the cost evaluation process. The proposed joint dispatching and planning method is computationally cheap, kinematically feasible, avoids collisions with obstacles/forklifts, and finds the global optimum quickly. The presented motion planning strategy demonstrates that the integration of a neural network with the dispatching approach leads to a warehouse filling/emptying mission completion time that is 2% shorter than the most efficient strategy lacking machine-learning integration. Notably, the mission completion times across these strategies vary by approximately 15%.
- 21 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 37 (5) , 86-94
Xsickness in Intelligent Mobile Spaces and Metaverses
Motion sickness is known to be a common problem that influences the comfort and work efficiency of human beings during their daily lives. With the proliferation of increasingly intelligent systems, the detection and mitigation of motion sickness will face more opportunities along with bigger challenges. On the one hand, the technology for integrated sensors in the intelligent system will provide more accurate and efficient methods for motion sickness detection. However, on the other hand, since cyber-physical systems have been gaining increasing concerns in the past two decades, the cyber-physical-social systems introduce and augment the social characteristics of such systems. The interactions between physical space and cyber space increase the chance of sensory conflicts when people use intelligent systems, such as traveling in intelligent cockpits or using metaverse-related virtual reality devices. The multimodal interaction methods and larger screens will cause more sensory conflicts. The symptoms will be more severe compared to traditional motion sickness. In this article, the classifications are first introduced based on the causes of motion sickness. A new type of multifactorial motion sickness (Xsickness) is discussed, which is foreseeable to be common with intelligent development. Then, the current state-of-the-art detection methods for motion sickness and cybersickness are summarized and theoretical methods for Xsickness detection are discussed. Finally, the mitigation methods based on motion reduction and four means of human perception are discussed and the innovative mitigation methods based on the intelligent system are also introduced.
- 21 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 37 (5) , 86-94
Xsickness in Intelligent Mobile Spaces and Metaverses
Motion sickness is known to be a common problem that influences the comfort and work efficiency of human beings during their daily lives. With the proliferation of increasingly intelligent systems, the detection and mitigation of motion sickness will face more opportunities along with bigger challenges. On the one hand, the technology for integrated sensors in the intelligent system will provide more accurate and efficient methods for motion sickness detection. However, on the other hand, since cyber-physical systems have been gaining increasing concerns in the past two decades, the cyber-physical-social systems introduce and augment the social characteristics of such systems. The interactions between physical space and cyber space increase the chance of sensory conflicts when people use intelligent systems, such as traveling in intelligent cockpits or using metaverse-related virtual reality devices. The multimodal interaction methods and larger screens will cause more sensory conflicts. The symptoms will be more severe compared to traditional motion sickness. In this article, the classifications are first introduced based on the causes of motion sickness. A new type of multifactorial motion sickness (Xsickness) is discussed, which is foreseeable to be common with intelligent development. Then, the current state-of-the-art detection methods for motion sickness and cybersickness are summarized and theoretical methods for Xsickness detection are discussed. Finally, the mitigation methods based on motion reduction and four means of human perception are discussed and the innovative mitigation methods based on the intelligent system are also introduced.
- Open Access
An Autonomous Storage Optimization LRM Generation Strategy Based on Cascaded NURBS
Automatic control of intelligent vehicles depends heavily on accurate lane-level location information. The traditional digital map cannot meet the automatic driving requirements, and it is very difficult for lane-level road maps (LRMs) to achieve a good balance between the representation accuracy and data storage volume. To tackle this problem, we obtain the recursive definition of a lane line by analyzing road lanes using the fractal geometry theory. Subsequently, we construct a recursive feedback system and model it. On this basis, an autonomous storage optimization LRM generation strategy based on cascaded NURBS is devised. According to the input data density, this framework generates an LRM with the minimum data storage volume within the error constraint. It is mainly composed of two modules: (1) a random fractal and (2) an adaptive iteration memory optimizer, based on cascaded NURBS error feedback. First, the whole lane is divided into several meta lane line modules. Second, data sampling/interpolation is carried out iteratively according to the NURBS fitting error and symmetry of road geometry. In this way, the storage space used to store lane lines and other information is automatically optimized. Last, a simulation experiment is carried out by using a dataset obtained from a park. The simulation results show that the proposed method can achieve high accuracy and high storage efficiency. Under the constraint of a 0.1 m curve fitting error, the average memory demand of the lane line elements is less than 2.4 bytes/m.
Open AccessAn Autonomous Storage Optimization LRM Generation Strategy Based on Cascaded NURBS
Automatic control of intelligent vehicles depends heavily on accurate lane-level location information. The traditional digital map cannot meet the automatic driving requirements, and it is very difficult for lane-level road maps (LRMs) to achieve a good balance between the representation accuracy and data storage volume. To tackle this problem, we obtain the recursive definition of a lane line by analyzing road lanes using the fractal geometry theory. Subsequently, we construct a recursive feedback system and model it. On this basis, an autonomous storage optimization LRM generation strategy based on cascaded NURBS is devised. According to the input data density, this framework generates an LRM with the minimum data storage volume within the error constraint. It is mainly composed of two modules: (1) a random fractal and (2) an adaptive iteration memory optimizer, based on cascaded NURBS error feedback. First, the whole lane is divided into several meta lane line modules. Second, data sampling/interpolation is carried out iteratively according to the NURBS fitting error and symmetry of road geometry. In this way, the storage space used to store lane lines and other information is automatically optimized. Last, a simulation experiment is carried out by using a dataset obtained from a park. The simulation results show that the proposed method can achieve high accuracy and high storage efficiency. Under the constraint of a 0.1 m curve fitting error, the average memory demand of the lane line elements is less than 2.4 bytes/m.