Naibang Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Naibang Wang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoxi Hu
Tsinghua University
3 shared publications - Deyong Shang
School of Mechanical and Electrical Engineering, China University of Mining and Technology (Beijing), Beijing, China
2 shared publications Chengyong Liu
Affiliation China Coal Energy Research Institute Co., Ltd., Xi’an, Shaanxi Province, China
1 shared publication- Chengzhi Jiang
School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics, China
1 shared publication - Dandan Peng
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China
1 shared publication Haixing Cheng
Affiliation China Coal Energy Research Institute Co., Ltd., Xi’an, Shaanxi Province, China
1 shared publication
Latest Publications
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Roadside Multi-Modal Sensor Fusion for 3D Object Detection: A Review
Roadside perception systems deployed on fixed infrastructure such as intersections and gantries offer an infrastructurecentric vantage point for Intelligent Transportation Systems, enabling persistent and large-area monitoring of complex traffic environments. Within this paradigm, roadside 3D object detection plays a pivotal role in capturing diverse traffic participants beyond the inherent constraints of vehicle-mounted sensing. However, achieving reliable roadside perception remains challenging, as single-modality solutions are susceptible to long-range sensing degradation, severe occlusions, expansive fields of view, and adverse illumination or weather conditions. Multi-modal sensor fusion, integrating complementary modalities including cameras, LiDAR, and radar, has therefore emerged as a critical foundation for robust infrastructure-based perception. This paper provides a comprehensive, system-level review of roadside multi-modal sensor fusion for 3D object detection. We synthesize the characteristics of roadside sensing modalities, examine spatial–temporal calibration and synchronization strategies, analyze representative fusion architectures with an emphasis on Bird’s-Eye-View (BEV) representations, and overview publicly available datasets alongside evaluation practices. Furthermore, we distill key technical challenges and highlight emerging research directions, positioning roadside multi-modal fusion as a cornerstone for next-generation intelligent transportation infrastructure.
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
Roadside Multi-Modal Sensor Fusion for 3D Object Detection: A Review
Roadside perception systems deployed on fixed infrastructure such as intersections and gantries offer an infrastructurecentric vantage point for Intelligent Transportation Systems, enabling persistent and large-area monitoring of complex traffic environments. Within this paradigm, roadside 3D object detection plays a pivotal role in capturing diverse traffic participants beyond the inherent constraints of vehicle-mounted sensing. However, achieving reliable roadside perception remains challenging, as single-modality solutions are susceptible to long-range sensing degradation, severe occlusions, expansive fields of view, and adverse illumination or weather conditions. Multi-modal sensor fusion, integrating complementary modalities including cameras, LiDAR, and radar, has therefore emerged as a critical foundation for robust infrastructure-based perception. This paper provides a comprehensive, system-level review of roadside multi-modal sensor fusion for 3D object detection. We synthesize the characteristics of roadside sensing modalities, examine spatial–temporal calibration and synchronization strategies, analyze representative fusion architectures with an emphasis on Bird’s-Eye-View (BEV) representations, and overview publicly available datasets alongside evaluation practices. Furthermore, we distill key technical challenges and highlight emerging research directions, positioning roadside multi-modal fusion as a cornerstone for next-generation intelligent transportation infrastructure.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (8) , 12398-12407
JFDNet: A Robust Industrial Robot Multijoint Fault Detection Network Under Sensor Fault and Environmental Noise Scenarios
Despite recent progress in deep learning for robot joint fault detection, most existing methods are trained on clean laboratory data and degrade significantly under real-world disturbances. These disturbances corrupt vibration signals and obscure fault-related cues, thereby reducing precision and recall. To address this problem, we propose the Joint Fault Detection Network (JFDNet), an end-to-end model for robust per-joint fault detection in multi-joint industrial robots under sensor fault and environmental noise scenarios. JFDNet features a Single-Joint Tri-Axis Wavelet (SJTAW) backbone that uses Trainable Discrete Wavelet Convolution (TDWC) and an Axis-Interaction Module (AIM) to suppress disturbances and preserve joint-specific fault patterns. A Dynamic Inter-Joint Relation (DIJR) neck further models cross-joint dependencies via a Bi-Directional Mamba Mixer (BDMM) flanked by attention modules. Extensive experiments demonstrate that JFDNet outperforms existing methods, delivering strong results across standard evaluation metrics while maintaining robustness. This work paves the way for deploying robot fault detection systems under sensor fault and environmental noise scenarios.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (8) , 12398-12407
JFDNet: A Robust Industrial Robot Multijoint Fault Detection Network Under Sensor Fault and Environmental Noise Scenarios
Despite recent progress in deep learning for robot joint fault detection, most existing methods are trained on clean laboratory data and degrade significantly under real-world disturbances. These disturbances corrupt vibration signals and obscure fault-related cues, thereby reducing precision and recall. To address this problem, we propose the Joint Fault Detection Network (JFDNet), an end-to-end model for robust per-joint fault detection in multi-joint industrial robots under sensor fault and environmental noise scenarios. JFDNet features a Single-Joint Tri-Axis Wavelet (SJTAW) backbone that uses Trainable Discrete Wavelet Convolution (TDWC) and an Axis-Interaction Module (AIM) to suppress disturbances and preserve joint-specific fault patterns. A Dynamic Inter-Joint Relation (DIJR) neck further models cross-joint dependencies via a Bi-Directional Mamba Mixer (BDMM) flanked by attention modules. Extensive experiments demonstrate that JFDNet outperforms existing methods, delivering strong results across standard evaluation metrics while maintaining robustness. This work paves the way for deploying robot fault detection systems under sensor fault and environmental noise scenarios.
- Open Access
- 4 September 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (9) , e0331195
LGMMFusion: A LiDAR-guided multi-modal fusion framework for enhanced 3D object detection
Multi-modal data fusion plays a critical role in enhancing the accuracy and robustness of perception systems for autonomous driving, especially for the detection of small objects. However, small object detection remains particularly challenging due to sparse LiDAR points and low-resolution image features, which often lead to missed or imprecise detections. Currently, many methods process LiDAR point clouds and visible-light camera images separately, and then fuse them in the detection head. However, these approaches often fail to fully exploit the advantages of multi-modal sensors and overlook the potential for enhancing the correlation between modalities before feature fusion. To address this, we propose a novel LiDAR-guided multi-modal fusion framework for object detection, called LGMMfusion. This framework leverages the depth information from LiDAR to guide the generation of image Bird’s Eye View (BEV) features. Specifically, LGMMfusion promotes spatial interaction between point clouds and pixels before the fusion of LiDAR BEV and image BEV features, enabling the generation of higher-quality image BEV features. To better align image and LiDAR features, we incorporate a multi-head multi-scale self-attention mechanism and a multi-head adaptive cross-attention mechanism, using the prior depth information from point clouds to generate image BEV features that better match the spatial positions of LiDAR BEV features. Finally, the LiDAR BEV features and image BEV features are fused to provide enhanced features for the detection head. Experimental results show that LGMMfusion achieves 71.1% NDS and 67.3% mAP on the nuScenes validation set, while also improving the detection of small objects and enhancing the detection accuracy of most objects.
- 4 September 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (9) , e0331195
Open AccessLGMMFusion: A LiDAR-guided multi-modal fusion framework for enhanced 3D object detection
Multi-modal data fusion plays a critical role in enhancing the accuracy and robustness of perception systems for autonomous driving, especially for the detection of small objects. However, small object detection remains particularly challenging due to sparse LiDAR points and low-resolution image features, which often lead to missed or imprecise detections. Currently, many methods process LiDAR point clouds and visible-light camera images separately, and then fuse them in the detection head. However, these approaches often fail to fully exploit the advantages of multi-modal sensors and overlook the potential for enhancing the correlation between modalities before feature fusion. To address this, we propose a novel LiDAR-guided multi-modal fusion framework for object detection, called LGMMfusion. This framework leverages the depth information from LiDAR to guide the generation of image Bird’s Eye View (BEV) features. Specifically, LGMMfusion promotes spatial interaction between point clouds and pixels before the fusion of LiDAR BEV and image BEV features, enabling the generation of higher-quality image BEV features. To better align image and LiDAR features, we incorporate a multi-head multi-scale self-attention mechanism and a multi-head adaptive cross-attention mechanism, using the prior depth information from point clouds to generate image BEV features that better match the spatial positions of LiDAR BEV features. Finally, the LiDAR BEV features and image BEV features are fused to provide enhanced features for the detection head. Experimental results show that LGMMfusion achieves 71.1% NDS and 67.3% mAP on the nuScenes validation set, while also improving the detection of small objects and enhancing the detection accuracy of most objects.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (16) , 30255-30274
Collaborative Perception Datasets for Autonomous Driving: A Review
Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (16) , 30255-30274
Collaborative Perception Datasets for Autonomous Driving: A Review
Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://github.com/frankwnb/Collaborative-Perception-Datasets-for-Autonomous-Driving.