HLHuanxin Luo

Huanxin Luo

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huanxin Luo has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Personalized Trajectory Planning Approach for Exoskeleton Robots Using GPR and Fourier Series

    by Guiyang Xin, Chengbao Li, Kairong Qin, Chen Liu, Yu Wang, Huanxin Luo, Yan Zhuang, Kaijun Zhou

    To address the unique gait characteristics of individuals, this paper proposes a personalized trajectory planning method for exoskeleton robots. Gait trajectory data is collected using an inertial motion capture system, and personalized musculoskeletal models are built via OpenSim 4.5 to calculate joint angle data. The Trainable Time Warping (TTW) algorithm is used to align data from different time series, followed by Gaussian Mixture Model and Gaussian Mixture Regression (GMM-GMR) to fit multiple data sequences. The fitted joint angle curves are expanded using Fourier series to obtain Fourier coefficients. A Gaussian Process Regression (GPR) model is then established to map anthropometric parameters (thigh length, calf length, weight) to Fourier coefficients, which are used to plan gait trajectories. Experiments conducted with a lower limb exoskeleton robot demonstrate that this trajectory planning method achieves accurate trajectory tracking, with a root mean square error (RMSE) of 1.82° for the hip joint and 1.89° for the knee joint. The method also yielded a high user satisfaction rate of 90%, confirming its effectiveness in generating personalized and comfortable gait patterns.


  • Open Access

    ADEmono-SLAM: Absolute Depth Estimation for Monocular Visual Simultaneous Localization and Mapping in Complex Environments

    by Kaijun Zhou, Zifei Yu, Xiancheng Zhou, Ping Tan, Yunpeng Yin, Huanxin Luo

    Aiming to address the problems of scale uncertainty and dynamic object interference in monocular visual simultaneous localization and mapping (SLAM), this paper proposes an absolute depth estimation network-based monocular visual SLAM method, namely, ADEmono-SLAM. Firstly, some detail features including oriented fast and rotated brief (ORB) features of input image are extracted. An object depth map is obtained through an absolute depth estimation network, and some reliable feature points are obtained by a dynamic interference filtering algorithm. Through these operations, the potential dynamic interference points are eliminated. Secondly, the absolute depth image is obtained by using the monocular depth estimation network, in which a dynamic point elimination algorithm using target detection is designed to eliminate dynamic interference points. Finally, the camera poses and map information are obtained by static feature point matching optimization. Thus, the remote points are randomly filtered by combining the depth values of the feature points. Experiments on the karlsruhe institute of technology and toyota technological institute (KITTI) dataset, technical university of munich (TUM) dataset, and mobile robot platform show that the proposed method can obtain sparse maps with absolute scale and improve the pose estimation accuracy of monocular SLAM in various scenarios. Compared with existing methods, the maximum error is reduced by about 80%, which provides an effective method or idea for the application of monocular SLAM in the complex environment.