Yusheng Yang
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
Yusheng Yang has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Yangmin Xie
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
11 shared publications - Hang Shi
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
3 shared publications - Jinghan Zhang
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
3 shared publications - Yu Song
Delft University of Technology
3 shared publications Hao Geng
School of Mechatronics Engineering and Automation Shanghai University 200444 Shanghai China
2 shared publications- Hongpeng Zhou
University of Manchester
2 shared publications
Latest Publications
- Open Access
- 16 August 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (16) , 1510
Curvature-Coupled Adaptive Vector-Field Integral Line-of-Sight Guidance for Unmanned Surface Vehicle Path Following
Achieving high-accuracy path following remains challenging for an unmanned surface vehicle (USV) in narrow waterways with time-varying curvature and straight–curve transitions; fixed-parameter line-of-sight (LOS) guidance can cause delayed response, overshoot, and steady-state cross-track error. This paper proposes a curvature-coupled adaptive vector-field integral LOS (AVFILOS) guidance law. It incorporates curvature-adaptive guidance: a lookahead distance regulated by curvature and cross-track error and a field-source radius that contracts with curvature to strengthen centripetal correction in high-curvature regions. A fuzzy adaptive proportional–integral–derivative (PID) controller tracks surge speed and heading. A stability analysis establishes local exponential stability for straight and constant-curvature paths and local ISS with local uniform ultimate boundedness for time-varying curvature under a bounded-rate condition. Across six elliptical and sinusoidal cases, AVFILOS achieved an average root mean square error (RMSE()) of 0.1325 m, reducing RMSE() by 90.6%, 63.6%, and 37.2% compared with LOS, time-varying LOS (TLOS), and vector-field integral LOS (VFILOS), respectively. Its average maximum absolute cross-track error (Max()) was 0.3478 m, with reductions of 88.2%, 48.2%, and 30.7%. The ablation and sensitivity results indicate that coupled adaptive mechanisms improve curved-path tracking and reduce overshoot. The simulations indicate that AVFILOS is promising for cross-track-error-sensitive USV navigation.- 16 August 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14 (16) , 1510
Open AccessCurvature-Coupled Adaptive Vector-Field Integral Line-of-Sight Guidance for Unmanned Surface Vehicle Path Following
Achieving high-accuracy path following remains challenging for an unmanned surface vehicle (USV) in narrow waterways with time-varying curvature and straight–curve transitions; fixed-parameter line-of-sight (LOS) guidance can cause delayed response, overshoot, and steady-state cross-track error. This paper proposes a curvature-coupled adaptive vector-field integral LOS (AVFILOS) guidance law. It incorporates curvature-adaptive guidance: a lookahead distance regulated by curvature and cross-track error and a field-source radius that contracts with curvature to strengthen centripetal correction in high-curvature regions. A fuzzy adaptive proportional–integral–derivative (PID) controller tracks surge speed and heading. A stability analysis establishes local exponential stability for straight and constant-curvature paths and local ISS with local uniform ultimate boundedness for time-varying curvature under a bounded-rate condition. Across six elliptical and sinusoidal cases, AVFILOS achieved an average root mean square error (RMSE()) of 0.1325 m, reducing RMSE() by 90.6%, 63.6%, and 37.2% compared with LOS, time-varying LOS (TLOS), and vector-field integral LOS (VFILOS), respectively. Its average maximum absolute cross-track error (Max()) was 0.3478 m, with reductions of 88.2%, 48.2%, and 30.7%. The ablation and sensitivity results indicate that coupled adaptive mechanisms improve curved-path tracking and reduce overshoot. The simulations indicate that AVFILOS is promising for cross-track-error-sensitive USV navigation. - Open Access
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 12412-12429
Air-to-Ground Occlusion Reasoning: 3-D Voxel Map Generation for Ground Traversability Analysis
In complex urban environments, traversable spaces beneath bridges and roadside trees are often obscured in UAV aerial imagery. To address this challenge, we propose a novel end-to-end Occlusion-Informed 3D Terrain Mapping (OI-3DTM) framework that enables accurate voxel-level modeling of hidden structures, providing a refined spatial foundation for traversability analysis. Existing methods largely rely on 2D semantic completion or expensive multi-view and LiDAR-based mapping, which either lack sufficient 3D expressiveness or fail to meet real-time and resource constraints. OI-3DTM integrates self-supervised monocular depth estimation with semantic segmentation and 3D reconstruction to explicitly infer traversable voxel structures in occluded scenes. A unified encoder–decoder network fuses RGB imagery with prior depth features, enhanced by a semantic-partitioned hybrid loss and confidence-ranked depth consistency, thereby improving depth accuracy in textureless or geometrically discontinuous regions. Furthermore, we introduce a geometry prior-informed voxel reasoning module that employs parameterized cavity curves to model the underlying spatial geometry of occluded regions, enabling the reconstruction of invisible structures. We evaluate OI-3DTM on three benchmark datasets for depth estimation and conduct 3D inference experiments on the UAV-LADIS dataset. Experimental results demonstrate that the proposed method consistently outperforms existing approaches in both depth estimation and 3D spatial reasoning, achieving a 61% improvement in IoU and reducing the cross-entropy error to 0.116 in occlusion scenarios. These results indicate that OI-3DTM significantly enhances occlusion-aware spatial perception and exhibits strong potential for practical deployment in UAV-based urban navigation applications.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 12412-12429
Open AccessAir-to-Ground Occlusion Reasoning: 3-D Voxel Map Generation for Ground Traversability Analysis
In complex urban environments, traversable spaces beneath bridges and roadside trees are often obscured in UAV aerial imagery. To address this challenge, we propose a novel end-to-end Occlusion-Informed 3D Terrain Mapping (OI-3DTM) framework that enables accurate voxel-level modeling of hidden structures, providing a refined spatial foundation for traversability analysis. Existing methods largely rely on 2D semantic completion or expensive multi-view and LiDAR-based mapping, which either lack sufficient 3D expressiveness or fail to meet real-time and resource constraints. OI-3DTM integrates self-supervised monocular depth estimation with semantic segmentation and 3D reconstruction to explicitly infer traversable voxel structures in occluded scenes. A unified encoder–decoder network fuses RGB imagery with prior depth features, enhanced by a semantic-partitioned hybrid loss and confidence-ranked depth consistency, thereby improving depth accuracy in textureless or geometrically discontinuous regions. Furthermore, we introduce a geometry prior-informed voxel reasoning module that employs parameterized cavity curves to model the underlying spatial geometry of occluded regions, enabling the reconstruction of invisible structures. We evaluate OI-3DTM on three benchmark datasets for depth estimation and conduct 3D inference experiments on the UAV-LADIS dataset. Experimental results demonstrate that the proposed method consistently outperforms existing approaches in both depth estimation and 3D spatial reasoning, achieving a 61% improvement in IoU and reducing the cross-entropy error to 0.116 in occlusion scenarios. These results indicate that OI-3DTM significantly enhances occlusion-aware spatial perception and exhibits strong potential for practical deployment in UAV-based urban navigation applications.
- Open Access
VLM-Guided and Spatially Consistent Cross-View Matching and Localization of UGVs in UAV-Stitched Map
In Global Navigation Satellite System (GNSS)-denied urban environments, unmanned ground vehicles (UGVs) face significant difficulties in maintaining reliable localization due to occlusion and structural complexity. Unmanned aerial vehicles (UAVs), with their global perspective, provide complementary information for cross-view matching and localization of UGVs. However, robust cross-view matching and localization are hindered by geometric distortions, semantic inconsistencies, and the lack of stable spatial anchors, limiting the effectiveness of conventional methods. To overcome these challenges, we proposed a cross-view matching and localization (CVML) framework that contains two components. The first component is the Vision-Language Model (VLM)-guided and spatially consistent cross-view matching network (VSCM-Net), which integrates two novel attention modules. One is the VLM-guided positional correction module that leverages semantic cues to refine the projected UGV image within the UAV map, and the other is the shape-aware attention module that enforces topological consistency across ground and aerial views. The second component is a ground-to-aerial mapping module that projects cross-view correspondences from the UGV image onto the UAV-stitched map, thereby localizing the capture position of the UGV image and enabling accurate trajectory-level localization and navigation. Extensive experiments on public and self-collected datasets demonstrate that the proposed method achieves superior accuracy, robustness, and real-world applicability compared with state-of-the-art methods in both cross-view image matching and localization.
Open AccessVLM-Guided and Spatially Consistent Cross-View Matching and Localization of UGVs in UAV-Stitched Map
In Global Navigation Satellite System (GNSS)-denied urban environments, unmanned ground vehicles (UGVs) face significant difficulties in maintaining reliable localization due to occlusion and structural complexity. Unmanned aerial vehicles (UAVs), with their global perspective, provide complementary information for cross-view matching and localization of UGVs. However, robust cross-view matching and localization are hindered by geometric distortions, semantic inconsistencies, and the lack of stable spatial anchors, limiting the effectiveness of conventional methods. To overcome these challenges, we proposed a cross-view matching and localization (CVML) framework that contains two components. The first component is the Vision-Language Model (VLM)-guided and spatially consistent cross-view matching network (VSCM-Net), which integrates two novel attention modules. One is the VLM-guided positional correction module that leverages semantic cues to refine the projected UGV image within the UAV map, and the other is the shape-aware attention module that enforces topological consistency across ground and aerial views. The second component is a ground-to-aerial mapping module that projects cross-view correspondences from the UGV image onto the UAV-stitched map, thereby localizing the capture position of the UGV image and enabling accurate trajectory-level localization and navigation. Extensive experiments on public and self-collected datasets demonstrate that the proposed method achieves superior accuracy, robustness, and real-world applicability compared with state-of-the-art methods in both cross-view image matching and localization.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
Hybrid-Feature Geometric Descriptor for Point Clouds Registration in Architectural Scenarios
This paper presents a Hybrid-feature Geometric Descriptor Registration (HGDR) framework to improve point cloud registration accuracy in challenging architectural environments. Traditional methods relying on single feature types—points, lines, or planes—often encounter limitations in accuracy and robustness, especially in noise-prone or low-overlap settings. In contrast, HGDR simultaneously extracts corner, line, and plane features in one step using a lightweight network and a novel Local Curvature Space Descriptor (LCSD). A two-layer graph matching algorithm leverages global geometric relations to improve correspondence reliability, followed by a two-stage non-iterative transformation estimation that avoids initialization sensitivity. HGDR was rigorously evaluated on indoor and outdoor datasets, outperforming eleven state-of-the-art rotation, translation, and RMSE accuracy methods, including uniform-feature-based and learning-based approaches. It achieved centimeter-level precision generally, with statistically lower error (mean rotation error of 0.79° and translation error of 0.173m) and significantly lower standard deviations than the competing methods. The improved robustness of the hybrid feature method is further validated through ablation experiments conducted under various mixed feature conditions.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-18
Hybrid-Feature Geometric Descriptor for Point Clouds Registration in Architectural Scenarios
This paper presents a Hybrid-feature Geometric Descriptor Registration (HGDR) framework to improve point cloud registration accuracy in challenging architectural environments. Traditional methods relying on single feature types—points, lines, or planes—often encounter limitations in accuracy and robustness, especially in noise-prone or low-overlap settings. In contrast, HGDR simultaneously extracts corner, line, and plane features in one step using a lightweight network and a novel Local Curvature Space Descriptor (LCSD). A two-layer graph matching algorithm leverages global geometric relations to improve correspondence reliability, followed by a two-stage non-iterative transformation estimation that avoids initialization sensitivity. HGDR was rigorously evaluated on indoor and outdoor datasets, outperforming eleven state-of-the-art rotation, translation, and RMSE accuracy methods, including uniform-feature-based and learning-based approaches. It achieved centimeter-level precision generally, with statistically lower error (mean rotation error of 0.79° and translation error of 0.173m) and significantly lower standard deviations than the competing methods. The improved robustness of the hybrid feature method is further validated through ablation experiments conducted under various mixed feature conditions.
- Open Access
- 18 June 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (12) , 2089
SMM-POD: Panoramic 3D Object Detection via Spherical Multi-Stage Multi-Modal Fusion
Panoramic 3D object detection is a challenging task due to image distortion, sensor heterogeneity, and the difficulty of combining information from multiple modalities over a wide field-of-view (FoV). To address these issues, we propose SMM-POD, a novel framework that introduces a spherical multi-stage fusion strategy for panoramic 3D detection. Our approach creates a five-channel spherical image aligned with LiDAR data and uses a quasi-uniform Voronoi sphere (UVS) model to reduce projection distortion. A cross-attention-based feature extraction module and a transformer encoder–decoder with spherical positional encoding enable the accurate and efficient fusion of image and point cloud features. For precise 3D localization, we adopt a Frustum PointNet module. Experiments on the DAIR-V2X-I benchmark and our self-collected SHU-3DPOD dataset show that SMM-POD achieves a state-of-the-art performance across all object categories. It significantly improves the detection of small objects like cyclists and pedestrians and maintains stable results under various environmental conditions. These results demonstrate the effectiveness of SMM-POD in panoramic multi-modal 3D perception and establish it as a strong baseline for wide FoV object detection.
- 18 June 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (12) , 2089
Open AccessSMM-POD: Panoramic 3D Object Detection via Spherical Multi-Stage Multi-Modal Fusion
Panoramic 3D object detection is a challenging task due to image distortion, sensor heterogeneity, and the difficulty of combining information from multiple modalities over a wide field-of-view (FoV). To address these issues, we propose SMM-POD, a novel framework that introduces a spherical multi-stage fusion strategy for panoramic 3D detection. Our approach creates a five-channel spherical image aligned with LiDAR data and uses a quasi-uniform Voronoi sphere (UVS) model to reduce projection distortion. A cross-attention-based feature extraction module and a transformer encoder–decoder with spherical positional encoding enable the accurate and efficient fusion of image and point cloud features. For precise 3D localization, we adopt a Frustum PointNet module. Experiments on the DAIR-V2X-I benchmark and our self-collected SHU-3DPOD dataset show that SMM-POD achieves a state-of-the-art performance across all object categories. It significantly improves the detection of small objects like cyclists and pedestrians and maintains stable results under various environmental conditions. These results demonstrate the effectiveness of SMM-POD in panoramic multi-modal 3D perception and establish it as a strong baseline for wide FoV object detection.
- Open Access
Path Planning on Multi-level Point Cloud with a Weighted Traversability Graph
This article proposes a new path planning method for addressing multi-level terrain situations. The proposed method includes innovations in three aspects: 1) the pre-processing of point cloud maps with a multi-level skip-list structure and data-slimming algorithm for well-organized and simplified map formalization and management, 2) the direct acquisition of local traversability indexes through vehicle and point cloud interaction analysis, which saves work in surface fitting, and 3) the assignment of traversability indexes on a multi-level connectivity graph to generate a weighted traversability graph for generally search-based path planning. The A* algorithm is modified to utilize the traversability graph to generate a short and safe path. The effectiveness and reliability of the proposed method are verified through indoor and outdoor experiments conducted in various environments, including multi-floor buildings, woodland, and rugged mountainous regions. The results demonstrate that the proposed method can properly address 3D path planning problems for ground vehicles in a wide range of situations.
Open AccessPath Planning on Multi-level Point Cloud with a Weighted Traversability Graph
This article proposes a new path planning method for addressing multi-level terrain situations. The proposed method includes innovations in three aspects: 1) the pre-processing of point cloud maps with a multi-level skip-list structure and data-slimming algorithm for well-organized and simplified map formalization and management, 2) the direct acquisition of local traversability indexes through vehicle and point cloud interaction analysis, which saves work in surface fitting, and 3) the assignment of traversability indexes on a multi-level connectivity graph to generate a weighted traversability graph for generally search-based path planning. The A* algorithm is modified to utilize the traversability graph to generate a short and safe path. The effectiveness and reliability of the proposed method are verified through indoor and outdoor experiments conducted in various environments, including multi-floor buildings, woodland, and rugged mountainous regions. The results demonstrate that the proposed method can properly address 3D path planning problems for ground vehicles in a wide range of situations.
- Open Access
- 18 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4474
Optical Flow Odometry with Panoramic Image Based on Spherical Congruence Projection
Panoramic images provide distinct advantages in odometry applications, which are largely due to their extensive field of view and higher information density captured in a single frame. Traditional odometry methods often rely on mapping panoramic images onto the planar structure for feature tracking. However, this process introduces uneven distortions of features, which diminish the accuracy of feature tracking and odometry, particularly in scenarios involving large displacements. In this work, we address this challenge by introducing a novel approach, named spherical congruence projection (SCP), that maps panoramic images onto a spherical structure and projects the spherical pixels onto a two-dimensional data format while preserving the spherical pixel topology. SCP effectively eliminates the distortion across the panoramic image. Additionally, we present the optical flow odometry on the panoramic image in the spherical structure and integrate it with the proposed SCP method for the first time. The experimental results in public and custom-built datasets demonstrate that the proposed SCP-based odometry method reliably tracks features and maintains accurate odometry performance, even in fast-moving scenarios.
- 18 April 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (8) , 4474
Open AccessOptical Flow Odometry with Panoramic Image Based on Spherical Congruence Projection
Panoramic images provide distinct advantages in odometry applications, which are largely due to their extensive field of view and higher information density captured in a single frame. Traditional odometry methods often rely on mapping panoramic images onto the planar structure for feature tracking. However, this process introduces uneven distortions of features, which diminish the accuracy of feature tracking and odometry, particularly in scenarios involving large displacements. In this work, we address this challenge by introducing a novel approach, named spherical congruence projection (SCP), that maps panoramic images onto a spherical structure and projects the spherical pixels onto a two-dimensional data format while preserving the spherical pixel topology. SCP effectively eliminates the distortion across the panoramic image. Additionally, we present the optical flow odometry on the panoramic image in the spherical structure and integrate it with the proposed SCP method for the first time. The experimental results in public and custom-built datasets demonstrate that the proposed SCP-based odometry method reliably tracks features and maintains accurate odometry performance, even in fast-moving scenarios.
- 18 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Enhanced Incremental Image Stitching for Low-Altitude UAV Imagery With Depth Estimation
This paper proposes Depth-Aided Incremental Image Stitching (DAIIS), an algorithm tailored for low-altitude UAV images in urban environments. DAIIS integrates single-view depth estimation and plane fitting to identify ground feature points, enabling precise computation of transformation matrices and significantly reducing stitching errors caused by large depth variations. Unlike traditional methods, DAIIS effectively addresses misalignments and artifacts, producing seamless and accurate stitched images that closely resemble the real scene. Evaluated on three distinct datasets, DAIIS demonstrated superior performance, achieving a 70% reduction in Mean Square Error (MSE) and notable improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) compared to other methods. The results validate DAIIS as a robust solution for high-precision image stitching, enhancing accuracy and visual quality in challenging low-altitude scenarios, which offers reliable and high-quality results for various urban applications.
- 18 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Enhanced Incremental Image Stitching for Low-Altitude UAV Imagery With Depth Estimation
This paper proposes Depth-Aided Incremental Image Stitching (DAIIS), an algorithm tailored for low-altitude UAV images in urban environments. DAIIS integrates single-view depth estimation and plane fitting to identify ground feature points, enabling precise computation of transformation matrices and significantly reducing stitching errors caused by large depth variations. Unlike traditional methods, DAIIS effectively addresses misalignments and artifacts, producing seamless and accurate stitched images that closely resemble the real scene. Evaluated on three distinct datasets, DAIIS demonstrated superior performance, achieving a 70% reduction in Mean Square Error (MSE) and notable improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) compared to other methods. The results validate DAIIS as a robust solution for high-precision image stitching, enhancing accuracy and visual quality in challenging low-altitude scenarios, which offers reliable and high-quality results for various urban applications.
- Open Access
RobotSDF: Implicit Morphology Modeling for the Robotic Arm
The expression of robot arm morphology is a critical foundation for achieving effective motion planning and collision avoidance in robotic systems. Traditional geometry-based approaches usually suffer from the contradiction between the high demand for computing resources for fine expression and the insufficient detail expression caused by the pursuit of efficiency. The signed distance function addresses these drawbacks due to its ability to handle complex and arbitrary shapes and lower computational requirements. However, conventional robotic morphology methods based on the signed distance function often face challenges when the robot moves dynamically, since robots with different postures are modeled as independent individuals but the postures of robots are infinite. In this paper, we introduce RobotSDF, an implicit morphology modeling approach that can express the robot shape of arbitrary posture precisely. Instead of depicting a whole model of the robot arm, RobotSDF models the robot morphology as integrated implicit joint models driven by joint configurations. In this approach, the dynamic shape change process of the robot is converted into the coordinate transformations of query points within each joint’s coordinate system. Experimental results with the Elfin robot demonstrate that RobotSDF can accurately depict robot shapes across different postures up to the millimeter level, which exhibits and improvement over the Neural-JSDF and configuration space distance field algorithms, respectively, in representing robot morphology. We further verified the efficiency of RobotSDF through collision avoidance in both simulation and actual human–robot collaboration experiments.Open AccessRobotSDF: Implicit Morphology Modeling for the Robotic Arm
The expression of robot arm morphology is a critical foundation for achieving effective motion planning and collision avoidance in robotic systems. Traditional geometry-based approaches usually suffer from the contradiction between the high demand for computing resources for fine expression and the insufficient detail expression caused by the pursuit of efficiency. The signed distance function addresses these drawbacks due to its ability to handle complex and arbitrary shapes and lower computational requirements. However, conventional robotic morphology methods based on the signed distance function often face challenges when the robot moves dynamically, since robots with different postures are modeled as independent individuals but the postures of robots are infinite. In this paper, we introduce RobotSDF, an implicit morphology modeling approach that can express the robot shape of arbitrary posture precisely. Instead of depicting a whole model of the robot arm, RobotSDF models the robot morphology as integrated implicit joint models driven by joint configurations. In this approach, the dynamic shape change process of the robot is converted into the coordinate transformations of query points within each joint’s coordinate system. Experimental results with the Elfin robot demonstrate that RobotSDF can accurately depict robot shapes across different postures up to the millimeter level, which exhibits and improvement over the Neural-JSDF and configuration space distance field algorithms, respectively, in representing robot morphology. We further verified the efficiency of RobotSDF through collision avoidance in both simulation and actual human–robot collaboration experiments. - 13 October 2023
- Published by Springer Nature
- p. 254-266
Autonomous Exploration for Mobile Robot in Three Dimensional Multi-layer Space
- 13 October 2023
- Published by Springer Nature
- p. 254-266
Autonomous Exploration for Mobile Robot in Three Dimensional Multi-layer Space