Junzheng Wang

Ni Ou, Zhuo Chen, Xinru Zhang et al.

Accurate camera-LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project LiDAR points into depth maps for feature fusion, which distorts 3D geometry and degrades performance when the extrinsic initialization is far from the ground truth. To address this issue, we propose an extrinsic-aware cross-attention framework that directly aligns image patches and LiDAR point groups in their native domains. The proposed attention mechanism explicitly injects extrinsic parameter hypotheses into the correspondence modeling process, enabling geometry-consistent cross-modal interaction without relying on projected 2D depth maps. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in both accuracy and robustness. Under large extrinsic perturbations, our approach achieves accurate calibration in 88% of KITTI cases and 99% of nuScenes cases, substantially surpassing the second-best baseline. We have open sourced our code on https://github.com/gitouni/ProjFusion to benefit the community.

Hanyu Cai, Ni Ou, Junzheng Wang

This paper presents a novel visual-LiDAR odometry and mapping method with low-drift characteristics. The proposed method is based on two popular approaches, ORB-SLAM and A-LOAM, with monocular scale correction and visual-bootstrapped LiDAR poses initialization modifications. The scale corrector calculates the proportion between the depth of image keypoints recovered by triangulation and that provided by LiDAR, using an outlier rejection process for accuracy improvement. Concerning LiDAR poses initialization, the visual odometry approach gives the initial guesses of LiDAR motions for better performance. This methodology is not only applicable to high-resolution LiDAR but can also adapt to low-resolution LiDAR. To evaluate the proposed SLAM system's robustness and accuracy, we conducted experiments on the KITTI Odometry and S3E datasets. Experimental results illustrate that our method significantly outperforms standalone ORB-SLAM2 and A-LOAM. Furthermore, regarding the accuracy of visual odometry with scale correction, our method performs similarly to the stereo-mode ORB-SLAM2.

Ni Ou, Zhuo Chen, Xinru Zhang et al.

Cameras and LiDAR are essential sensors for autonomous vehicles. The fusion of camera and LiDAR data addresses the limitations of individual sensors but relies on precise extrinsic calibration. Recently, numerous end-to-end calibration methods have been proposed; however, most predict extrinsic parameters in a single step and lack iterative optimization capabilities. To address the increasing demand for higher accuracy, we propose a versatile iterative framework based on surrogate diffusion. This framework can enhance the performance of any calibration method without requiring architectural modifications. Specifically, the initial extrinsic parameters undergo iterative refinement through a denoising process, in which the original calibration method serves as a surrogate denoiser to estimate the final extrinsics at each step. For comparative analysis, we selected four state-of-the-art calibration methods as surrogate denoisers and compared the results of our diffusion process with those of two other iterative approaches. Extensive experiments demonstrate that when integrated with our diffusion model, all calibration methods achieve higher accuracy, improved robustness, and greater stability compared to other iterative techniques and their single-step counterparts.

Ni Ou, Zhuo Chen, Xinru Zhang et al.

Cameras and LiDAR are essential sensors for autonomous vehicles. Camera-LiDAR data fusion compensate for deficiencies of stand-alone sensors but relies on precise extrinsic calibration. Many learning-based calibration methods predict extrinsic parameters in a single step. Driven by the growing demand for higher accuracy, a few approaches utilize multi-range models or integrate multiple methods to improve extrinsic parameter predictions, but these strategies incur extended training times and require additional storage for separate models. To address these issues, we propose a single-model iterative approach based on surrogate diffusion to significantly enhance the capacity of individual calibration methods. By applying a buffering technique proposed by us, the inference time of our surrogate diffusion is 43.7% less than that of multi-range models. Additionally, we create a calibration network as our denoiser, featuring both projection-first and encoding-first branches for effective point feature extraction. Extensive experiments demonstrate that our diffusion model outperforms other single-model iterative methods and delivers competitive results compared to multi-range models. Our denoiser exceeds state-of-the-art calibration methods, reducing the rotation error by 24.5% compared to the second-best method. Furthermore, with the proposed diffusion applied, it achieves 20.4% less rotation error and 9.6% less translation error.

Dongchen Liu, Junzheng Wang, Shoukun Wang

This work presents the coordinated motion control and obstacle-crossing problem for the four wheel-leg independent motor-driven robotic systems via a model predictive control (MPC) approach based on an event-triggering mechanism. The modeling of a wheel-leg robotic control system with a dynamic supporting polygon is organized. The system dynamic model is 3 degrees of freedom (DOF) ignoring the pitch, roll and vertical motions. The single wheel dynamic is analyzed considering the characteristics of motor-driven and the Burckhardt nonlinear tire model. As a result, an over-actuated predictive model is proposed with the motor torques as inputs and the system states as outputs. As the supporting polygon is only adjusted at certain conditions, an event-based triggering mechanism is designed to save hardware resources and energy. The MPC controller is evaluated on a virtual prototype as well as a physical prototype. The simulation results guide the parameter tuning for the controller implementation in the physical prototype. The experimental results on these two prototypes verify the efficiency of the proposed approach.

Dongchen Liu, Junzheng Wang, Shoukun Wang et al.

This work proposes a force control strategy with prescribed transient performance for the legs of a wheel-legged robotic system to realize the posture adjustment on uneven roads. A dynamic model of the robotic system is established with the body postures as inputs and the leg forces as outputs, such that the desired forces for the wheel-legs are calculated by the posture reference and feedback. Based on the funnel control scheme, the legs realize force tracking with prescribed transient performance. To improve the robustness of the force control system, an event-based mechanism is designed for the online segment of the funnel function. As a result, the force tracking error of the wheel-leg evolves inside the performance funnel with proved convergence. The absence of Zeno behavior for the event-triggering condition is also guaranteed. The proposed control scheme is applied to the wheel-legged physical prototype for the performance of force tracking and posture adjustment. Multiple comparative experimental results are presented to validate the stability and effectiveness of the proposed methodology.