XDXiaolin Ding

Xiaolin Ding

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaolin Ding has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • AnchorSED: A Segmentation Enhanced Detection Framework Based on Sparse Anchor for Multi-View 3D Object Detection

    by Shuhui Cheng, Lei Zhang, Xiaolin Ding, Jizheng Liu

    Existing 3D detection methods typically exploit 2D image information through region-level feature extraction and auxiliary semantic supervision. However, these strategies do not explicitly establish a correspondence between 3D candidates and corresponding 2D instance-level representations, which limits the ability to handle objects with complex shapes or severe occlusions. To address this limitation, we propose an anchorbased framework that establishes an anchor-conditioned 2D-3D interaction for jointly exploiting 2D and 3D annotations. Specifically, each 3D anchor and its sampled points are projected onto multiple image planes to identify anchor-associated regions of interest (ROIs), from which view-specific instance segmentation masks are predicted. These 2D representations are subsequently mapped back to their corresponding 3D anchors and aggregated through geometry-aware cross-modal feature alignment. Our approach extends conventional sparse detectors by introducing three components: (1) multi-view ROIs prediction, which maps 3D anchors and sampled points onto multi-view image planes to predict regions of interest (ROIs); (2) multi-view instance segmentation, generating pixel-accurate masks corresponding to predicted ROIs; and (3) cross-modal feature alignment, which fuses geometrically consistent 2D segmentation features with their associated 3D anchors. Furthermore, to bridge the geometric discrepancy between 2D images and 3D objects, we distill multi-scale visual knowledge from a pretrained large-scale self-supervised vision model into our detector, enhancing geometric consistency. Evaluated on the nuScenes benchmark, our framework achieves state-of-the-art performance while maintaining computational efficiency. The code and auxiliary supervision data are available at https://github.com/HuiAuto/AnchorSED.

  • Exploring Vehicle Lateral Motion Limit: Neutral Steering Control for Dual-Motor All-Wheel-Drive Electric Vehicles

    by Lei Zhang, Tongliang Xu, Zhenpo Wang, Fengchun Sun, Xiaolin Ding

    Maximizing the utilization of lateral motion limits can significantly enhance vehicle safety under extreme driving conditions. This paper presents a neutral steering chassis coordination control scheme to extend the lateral motion limits of Dual-Motor All-Wheel-Drive Electric Vehicles (DMAWD EVs). First, an optimization model is developed using the tire friction ellipse to determine the maximum lateral force. It is demonstrated that a vehicle can fully exploit its lateral motion limits under neutral steering. Then a driving torque allocation method for the front and rear axles and a sliding mode control method for the electro-hydraulic composite anti-lock braking system are designed to fulfill the driver's driving intentions under normal driving conditions. In extreme driving conditions, a torque vectoring control strategy is proposed to coordinate the motors' driving torques and the hydraulic braking forces, while a Smith predictor-based control scheme is introduced to enhance the hydraulic braking responsiveness. Furthermore, a coordinated pitch and roll attitude controller is developed to maintain neutral steering. Finally, the proposed control scheme is verified through comprehensive testing on a Hardware-in-the-Loop platform. Results indicate that the maximum lateral acceleration increases by 18.14% under the open-loop sine steering scenario. The proposed control scheme renders DMAWD EVs to have comparable performance with four-wheel-independent-drive electric vehicles.


  • Active Front Steering and Four-Wheel Torque Vectoring for Improved Driving and Braking Performance of Distributed Drive Electric Vehicles

    by Lei Zhang, Siyang Li, Xiaolin Ding, Zhenpo Wang, Fengchun Sun

    In this paper, a coordinated control scheme combining Active Front Steering (AFS) and Four-Wheel Torque Vectoring (4WTV) is proposed to enhance vehicle performance in driving, braking, and hill-climbing on split-$\mu$ roads. First, an AFS controller is designed based on a linear time-varying model predictive control approach to compensate for the additional yaw moment generated by torque vectoring. Then anti-lock braking and acceleration slip regulation controllers are developed using robust integral sliding mode control, taking into account the tire-road adhesion limits at each wheel. Finally, a coordination mechanism is formulated to effectively integrate the AFS and 4WTV controllers, considering driver inputs, vehicle states, road friction coefficients, and actuator characteristics. Hardware-in-the-loop test results under three different split-$\mu$ road conditions demonstrate that the proposed control scheme significantly reduces braking distance and acceleration time while improving hill-climbing performance and maintaining lateral stability.


  • Hierarchical Hybrid Steering Control for Four-Wheel-Steering Vehicles Considering System Delays

    by Lei Zhang, Xiaoxuan Yin, Zhenpo Wang, Fengchun Sun, Xiaolin Ding

    This paper proposes a hierarchical hybrid steering control scheme for four-wheel-steering vehicles to deal with steer-by-wire system time delays and vehicle nonlinear characteristics. First, a variable steering ratio is developed considering the influence of the front and rear wheels' angles on the vehicle's steering characteristic. Then a hybrid feedforward control combining with the steady-state control, dynamic compensation, and oblique steering compensation is established to enhance vehicle dynamics stability in extreme driving conditions, taking into account the reference yaw rate and road adhesion constraints. Meanwhile, an adaptive linear quadratic regulator-based feedback controller with a piece-wise affine tire model is put forward to account for the influence of vertical load, road adhesion condition, and yaw rate tracking error. Subsequently, the controller adopts an adaptive weighting coefficient mechanism to satisfy various working conditions based on different steady-state gains of the front and rear wheel angles on the yaw rate. Finally, the effectiveness of the proposed scheme is experimentally verified under comprehensive testing scenarios through Hardware-in-the-Loop tests. The results show that the proposed scheme has superior performance relative to the state-of-the-art methods.


  • An Enabling Tire-Road Friction Estimation Method for Four-in-Wheel-Motor-Drive Electric Vehicles

    by Lei Zhang, Pengyu Guo, Zhenpo Wang, Xiaolin Ding

    In this paper, a particle filter (PF)-based tire-road friction estimation method is proposed for four-in-wheel-motor-drive electric vehicles by synthetically using the Dual Global Positioning System (DGPS) and three low-cost Inertia Measurement Units (IMUs). In the scheme, two independent PF-based road friction estimators are developed for straight driving and cornering conditions. For straight driving conditions, the longitudinal tire forces are first estimated using the output torque and rotational speed of motor, based on which a tire-road friction estimator is put forward by using a particle filter and the nonlinear relationship between longitudinal tire force and tire-road friction. For cornering conditions, the lateral tire forces and vehicle sideslip angle are estimated by using three IMUs and the DGPS. A PF-based tire-road friction estimator is established based on the nonlinear lateral tire characteristics. An estimation mode decision scheme is developed to determine which of the two PF-based estimators is used to update the tire-road friction estimate by considering both tire dynamics states and tire force characteristics. The accuracy and reliability of the proposed tire-road friction estimation scheme is verified under various maneuvers and road friction conditions through hardware-in-the-loop tests. The results show that the proposed method exhibits high estimation accuracy, robustness, and computational efficiency.


  • Open Access

    A Comprehensive Vehicle Stability Assessment System Based on Enabling Tire Force Estimation

    by Xiaolin Ding, Zhenpo Wang, Lei Zhang, Jizheng Liu

    This paper presents an enabling comprehensive vehicle stability assessment system covering vehicle longitudinal, yaw and roll stability. First, the longitudinal, lateral and vertical tire forces are separately estimated using the strong tracking unscented Kalman filter and the conventional Kalman filter based on low-cost on-board sensors. Then, a comprehensive vehicle longitudinal, yaw and roll stability space is established by utilizing the normalized tire friction ellipse and the Load Transfer Ratio value. Finally, the vehicle stability is determined and predicted based on current driver's inputs. The hardware-in-loop experimental results show that the proposed vehicle stability assessment system can accurately estimate the longitudinal, lateral and vertical tire forces with the normalized root mean square errors of 1.87$\%$, 1.07$\%$ and 1.43$\%$, and exhibits satisfying performance for vehicle longitudinal, yaw and roll stability evaluation and prediction. This bears significance for the efficient functioning of active control systems to improve vehicle safety under critical driving conditions.


  • Event-Triggered Vehicle Sideslip Angle Estimation Based on Low-Cost Sensors

    by Xiaolin Ding, Zhenpo Wang, Lei Zhang

    Accurate vehicle sideslip angle estimation is crucial for vehicle stability control. In this article, an enabling event-triggered sideslip angle estimator is proposed by using the kinematic information from a low-cost global positioning system (GPS) and an on-board inertial measurement unit (IMU). First, a preliminary vehicle sideslip angle is derived using the heading angle of GPS and the yaw rate of IMU, and an event-triggered mechanism is proposed to eliminate the accumulative estimation error. The algorithm convergence is guaranteed through theoretical deduction. Second, a longitudinal and a lateral vehicle velocity are obtained using the preliminary vehicle sideslip angle and the measured GPS velocity and their kinematic relationship, based on which a multisensor fusion and a multistep Kalman filter scheme are, respectively, presented to realize longitudinal and lateral vehicle velocity estimation. By doing this, the update frequency and estimation accuracy of the vehicle sideslip angle estimate can be further improved to meet the requirement of online implementation. Finally, the effectiveness and reliability of the proposed scheme are verified under comprehensive driving conditions through both hardware-in-loop (HIL) and field tests. The results show that the proposed event-triggered sideslip angle estimator has a mean estimation error of 0.029 $^\circ$ and of 0.14 $^\circ$ in the HIL and field tests, exhibiting better estimation accuracy, reliability, and real-time performance compared with other typical estimators.


  • Open Access

    Fault-Tolerant Control for Intelligent Electrified Vehicles Against Front Wheel Steering Angle Sensor Faults During Trajectory Tracking

    by Lei Zhang, Zihao Wang, Xiaolin Ding, Shaohua Li, Zhenpo Wang

    Steer-by-Wire (SBW) systems are an integral and essential component of intelligent electrified vehicles and are critical to ensure safe vehicle operations. In this paper, a fault-tolerant control method for SBW is proposed to mitigate the adverse influence of front wheel steering angle sensor faults based on the Kalman filtering technique. First, a linearized vehicle model is derived based on tire characteristics and is further combined with a steering actuator model to provide the modelling foundation for estimating the front wheel steering angle. Considering multi-source noises and their significant influence on the front wheel steering angle sensor, the Butterworth filter is employed to filter out the high-frequency noises. The front wheel steering angle estimation is realized by incorporating the measurements of the yaw rate and lateral acceleration of vehicle and the current of steering motor. In particular, a dynamic threshold mechanism is adopted to activate the fault diagnosis and fault-tolerant compensation based on the residual theory. Finally, a linear time-varying model predictive controller is presented to execute the trajectory tracking task for an intelligent electrified vehicle. The effectiveness of the proposed scheme is verified under the single lane change and double lane change maneuvers during the trajectory tracking.