Tong Shen

Tong Shen

Auto-generated profile, based on publicly available information

Tong Shen

School of Mechanical Engineering, Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
YYYongjun Yan
Yongjun Yan
LPLin Peng
Lin Peng
TSTong Shen
Tong Shen
JWJinxiang Wang
Jinxiang Wang
Dawei PiDawei Pi
Dawei Pi
Guodong YinGuodong Yin
Guodong Yin
To improve the safety, comfort, and efficiency of the intelligent transportation system, particularly in complex traffic environments where autonomous vehicles (AVs) and human-driven vehicles (HVs) coexist, a game theoretic trajectory planning framework is proposed in this paper. Firstly, the game framework including non-cooperative games between AVs and HVs, as well as partial cooperative games between ego AV and other AVs is constructed. Secondly, a longitudinal game strategy for HVs is established with consideration of the driver's longitudinal handling characteristics and personalized aggressiveness, with which the driving behaviors of HVs can be accurately predicted. Thirdly, the longitudinal game strategies for AVs at different positions are designed, with consideration of the safety constraints of AVs and surrounding vehicles, as well as the objectives of comfort and traffic efficiency. Then, the interactive games of ego AV, HVs, and other AVs in different types of mixed-driving environments are solved based on the Stackelberg game and partial cooperative game methods. Finally, the optimal lane-changing (LC) gaps and longitudinal speed trajectories of AVs are obtained. Human-in-the-loop experiment results demonstrate the effectiveness of the proposed trajectory planning framework in lane-changing scenarios involving HVs with different aggressiveness and response delays.

5 October 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
FWFanxun Wang
Fanxun Wang
TSTong Shen
Tong Shen
MZMingzhuo Zhao
Mingzhuo Zhao
YRYanjun Ren
Yanjun Ren
YLYanbo Lu
Yanbo Lu
Guodong YinGuodong Yin
Guodong Yin
Motion control of lane-change maneuvers under high-speed scenarios creates a great challenge for autonomous vehicles. However, a novel framework of lane-change trajectory planning and control based on the dynamic characteristics of distributed drive electric vehicles (DDEVs) is proposed in this paper to increase the possibility of safe driving in complex traffic conditions. First, a dilatational stability region determined by limits of stable yaw rate and saturated slip angles of each tire is employed to reveal dynamic instantaneous characteristics. On the basis of dilatational stability regions, the expanded envelopes by additional direct yaw moment can be identified by the expressions of irregular hexagons. Then, a series of unconstrained lane-change trajectory clusters can be generated to minimize longitudinal and lateral jerk, which is used to divide the global feasible region determined by the dilatational stability region and three-dimensional collision-free tunnel. Then, the technique for order preference for similarity to the ideal solution (TOPSIS) is utilized to achieve optimization of trajectory candidates from the global feasible region. The tracking controller aims at following the optimal lane-change trajectory, which is designed by the expanded stability boundaries of DDEV. Finally, simulations and experiments are conducted to validate the performance of the proposed planner and controller under high-speed, full-road and multi-vehicle traffic conditions.

15 July 2022 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
TSTong Shen
Tong Shen
Guodong YinGuodong Yin
Guodong Yin
YRYanjun Ren
Yanjun Ren
FWFanxun Wang
Fanxun Wang
BFBin Feng
Bin Feng
JLJinhao Liang
Jinhao Liang
Direct yaw moment (DYC) does increase the maneuverability and controllability of distributed driving electric vehicle. However, the additional DYC could also lead to the instability of vehicle in low friction road. Extensive literatures have proposed various methods to tackle this problem. Nevertheless, the conflict between maneuverability and stability in handling limit is difficult to solve. To this end, a novel multimode torque distribution algorithm is developed in this article. The conception of drive stability region is proposed to describe the feasible operations of the driver. Based on the different regions, we define multitorque distribution modes to handle the varying conditions. A linear matrix inequality based mode decision theorem is developed to estimate the boundaries of the drive stability region as well as determine the optimal mode. Considering that the lateral tire force is important for mode decision, a long short-term memory neural network is adopted to make a precise estimation. Finally, we develop multitorque distribution strategies to meet the requirements of each mode. Processor-in-the-loop test is also implemented to verify the real-time performance of the algorithm. Simulation and experiment indicate that, the multimodes torque distribution strategy show a better performance compared with the single mode, which mitigates the conflict of maneuverability and stability as well as ensures the safety of vehicle in handling limit.

1 December 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MZMingzhuo Zhao
Mingzhuo Zhao
TSTong Shen
Tong Shen
FWFanxun Wang
Fanxun Wang
Guodong YinGuodong Yin
Guodong Yin
ZLZhiyuan Li
Zhiyuan Li
YZYang Zhang
Yang Zhang
Parking semi-trailer train in extremely narrow environments pose challenges due to high nonholonomic constraints, unstable reversing dynamics, and non-convex obstacle avoidance constraints. This paper presents the APTEN (Autonomous Parking of semi-Trailer train in Extremely Narrow environments) with a three-layer framework to address these challenges. In the first layer, we employ a linearized gain scheduling method to create a stable Cl-RRT planner tailored for simplifying unstable reverse dynamics. This planner is adept at promptly warm starting the following homotopy problems. In the second layer, we introduce a novel “dynamics–full dimensional obstacle avoidance” progressive constraint approach. Modifying the constraints of nonlinear programming in separate homotopy problems not only protects the solver from falling into unfeasible local optima but also significantly enhances computational efficiency. In the third layer, a differentiable approach based on convex set separation is employed to establish full-dimensional obstacle avoidance constraints for semi-trailer train. Leveraging the warm start solutions obtained from the previous two layers, the algorithm identifies the optimal solution that strictly adheres to the obstacle avoidance constraints in an extremely narrow environment. The simulation results demonstrate that APTEN excels in parking motion planning within extremely narrow environments, exhibiting the shortest solution time, the highest trajectory quality, and exceptional adaptability to diverse working conditions.

27 November 2023 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
TSTong Shen
Tong Shen
FWFanxun Wang
Fanxun Wang
YYYongjun Yan
Yongjun Yan
MZMingzhuo Zhao
Mingzhuo Zhao
YRYanjun Ren
Yanjun Ren
Guodong YinGuodong Yin
Guodong Yin
The stability region is an important criterion in the active safety system of vehicle. Extensive literatures have developed various stability regions for the centralized driving vehicle (CDV). However, seldom of them make a thorough analysis of the stability for distributed driving electric vehicle (DDEV). Especially when the direct yaw moment control (DYC) intervenes, the stability region of DDEV shows a huge difference compared with CDV. So far, most researches on the stability control of DDEV are still based on the traditional CDV stability region, which leads to the conservation of controller design. To this end, a dynamic and analytical stability region of DDEV is firstly developed in this paper. By employing sum of square programming (SOSP) algorithm, we choose a high-order Lyapunov function to make a precise estimation of the stability region. A novel DC shape function is proposed to reduce the conservation of estimation when DYC involves. To ensure the real-time performance for control application, Long Short Term Memory (LSTM) neural network is employed to fit the coefficients of Lyapunov function, as well as enable the dynamic shifting with driving conditions. Based on the aforementioned stability region, we develop a MPC controller to ensure the stability and tracking performance during handling limit. Both simulations and road tests demonstrate that the developed stability region could effectively restraint the vehicle states from diverging, which enhances vehicle maneuverability while ensuring vehicle stability. Note to Practitioners —Handling stability is a crucial factor which concerns the safety of vehicle. Almost all vehicles should be equipped with active safety system, such as Electronic Stability Program (ESP) of Bosch and Electronic Stability Controller (ESC) of GM. They collect the real-time vehicle states by the Built-in sensors. Meanwhile, they calculate the current stability margin according to the driver’s control input and analyze the deviation of the vehicle states to decide whether the active control is needed to maintain the stability of vehicle. This system is established well in CDV. However, for DDEV, it has another input of DYC in addition to wheel steering angle, which changes the dynamic characteristic of vehicle. This means that the stability margin of traditional ESP is inaccurate when the DYC intervenes, which will lead to the misjudgment of instability or the unsafety of vehicle. This paper develops an analytic stability region of DDEV and describes the stability margin with different values of DYC, which could adapt to varying conditions. This technology fills the gap of the stability determination of DDEV and has a good application prospect in the active safety system of DDEV.

6 June 2024 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
FWFanxun Wang
Fanxun Wang
MZMingzhuo Zhao
Mingzhuo Zhao
TSTong Shen
Tong Shen
GCGuoshun Cai
Guoshun Cai
Jinhao LiangJinhao Liang
Jinhao Liang
Guodong YinGuodong Yin
Guodong Yin
The accurate estimation of crucial state parameters, such as sideslip angle and tire cornering stiffness, plays a vital role in ensuring the efficacy of active safety technology and motion control for distributed drive electric vehicles. To address the challenges posed by missing measurements from multiple sensors and dynamic model mismatch during the estimation process, this article proposes a novel robust adaptive fault-tolerant estimator (RAFTE). Based on the four-wheel nonlinear vehicle model, the model parameters from the RAFTE are continuously adjusted by adaptive forgetting factor recursive least squares, which provides a more accurate dynamic model. Huber's robust M-estimation theory is integrated into the standard cubature Kalman filter, which adjusts the measurement noise covariance and innovation covariance to mitigate the effects of missing data. Then, an optimal adaptive factor is introduced to alleviate the issues of model mismatch and unmodeled dynamic characteristics that arise from the strong coupling nonlinear system. Finally, simulations and experiments are conducted to validate the estimation accuracy, convergence, and robustness of the proposed algorithm.