Guangbin Sun

Guangbin Sun

Auto-generated profile, based on publicly available information

Guangbin Sun

Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 October 2018 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
HDHuixu Dong
Huixu Dong
Ehsan AsadiEhsan Asadi
Ehsan Asadi
GSGuangbin Sun
Guangbin Sun
Dilip K. PrasadDilip K. Prasad
Dilip K. Prasad
ICI-Ming Chen
I-Ming Chen
Robotic manipulation employs the object detection in images to create a scene awareness and locate an object's pose. In dynamic scenarios, fast multiobject detection and tracking are crucial. Many objects commonly found in household and industrial environments are represented by cylindrical shapes. Thus, it is available for robots to manipulate them through the real-time detection of elliptic shape primitives formed by the circular tops of these objects. We devise an efficient algorithm of the detection of elliptic shape primitives, which in turn enables robust and real-time robotic manipulations of such objects. The proposed algorithm incorporates the information of elliptic edge curvature, splits complex curves into arcs, classifies the arcs into different quadrants of a candidate elliptic shape, determines the quality of arc selection for ellipse fitting, and then retrieves the corresponding elliptic shape primitive. Our algorithm provides either faster or more accurate ellipse detection results than the current state-of-the-art methods, irrespective of challenging scenarios such as occluded or overlapping ellipses. This is verified by performance comparison with six state-of-the-art elliptic shape detection algorithms on four public image datasets. The algorithm has been integrated on robots to demonstrate the ability to carry out accurate robotic manipulations (tracking, grasping, and stacking) of cylindrical objects in real time. We show that the robotic manipulator, empowered by the elliptic shape primitive algorithm, performs well in complex manipulation experiments as well as dynamic scenarios.

23 August 2018 in RSC Advances
Verified
Journal Article
Open access
PDF file
FWFuwang Wang
Fuwang Wang
XZXiaolei Zhang
Xiaolei Zhang
FWFu-wang Wang
Fu-wang Wang
GSGuangbin Sun
Guangbin Sun
This study describes the detection of driving fatigue using the characteristics of brain networks in a real driving environment. First, the θ, β and 36–44 Hz rhythm from the EEG signals of drivers were extracted using wavelet packet decomposition (WPD). The correlation between EEG channels was calculated using a Pearson correlation coefficient and subsequently, the brain networks were built. Furthermore, the clustering coefficient (C) and global efficiency (G) of the complex brain networks were calculated to analyze the functional differences in the brains of drivers over time. Combined with the relative power spectrum ratio (β/θ) of EEG signals and the mean value from questionnaires, the correlation of data characteristics between brain networks and subjective and objective data was analyzed. The results show that changes in the fatigue state of drivers can be effectively detected by calculating the data characteristics of brain networks in a real driving environment.

15 May 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
HDHuixu Dong
Huixu Dong
GSGuangbin Sun
Guangbin Sun
WPWee-Ching Pang
Wee-Ching Pang
Ehsan AsadiEhsan Asadi
Ehsan Asadi
Dilip K. PrasadDilip K. Prasad
Dilip K. Prasad
ICI-Ming Chen
I-Ming Chen
Robotic manipulation of objects requires a fast recognition from image stream. For many cylindrical object (e.g. cans, cups, pipes, bottles, etc.) this is possible through detection of ellipse depicting the circular top of the cylinder. Growing industrial and warehouse applications of robots drive the demand for fast and reliable detection of ellipses, while state-of-the-art methods are lacking in either speed or accuracy strength. We present a novel algorithm to perform fast and robust ellipse detection. First, the method utilizes the information of edge curvature to split curves into arcs. Next, the arc convexity-concavity is used to classify arcs into different quadrants of ellipses. Then based on multiple geometric constraints the arcs can be grouped at low computational cost. Our method is compared with six state-of-the-art methods using three public image datasets. The comparison results show that the proposed algorithm outperforms other methods with high detection accuracy and fast detection speed. Lastly, the algorithm is applied to identifying cylindrical objects in real-time for arranging and tracking purposes.

1 June 2018 in Sensors
Verified
Journal Article
Open access
PDF file
FWFuwang Wang
Fuwang Wang
XZXiaolei Zhang
Xiaolei Zhang
FWFu-wang Wang
Fu-wang Wang
GSGuangbin Sun
Guangbin Sun
A home-auxiliary robot platform is developed in the current study which could assist patients with physical disabilities and older persons with mobility impairments. The robot, mainly controlled by brain computer interface (BCI) technology, can not only perform actions in a person’s field of vision, but also work outside the field of vision. The wavelet decomposition (WD) is used in this study to extract the δ (0~4 Hz) and θ (4~8 Hz) sub-bands of subjects’ electroencephalogram (EEG) signals. The correlation between pairs of 14 EEG channels is determined with synchronization likelihood (SL), and the brain network structure is generated. Then, the motion characteristics are analyzed using the brain network parameters clustering coefficient (C) and global efficiency (G). Meanwhile, the eye movement characteristics in the F3 and F4 channels are identified. Finally, the motion characteristics identified by brain networks and eye movement characteristics can be used to control the home-auxiliary robot platform. The experimental result shows that the accuracy rate of left and right motion recognition using this method is more than 93%. Additionally, the similarity between that autonomous return path and the real path of the home-auxiliary robot reaches up to 0.89.

18 December 2018 in RSC Advances
Verified
Journal Article
Open access
PDF file
FWFuwang Wang
Fuwang Wang
QXQing Xu
Qing Xu
FWFu-wang Wang
Fu-wang Wang
GSGuangbin Sun
Guangbin Sun
The study of driving skill level discrimination based on EEG, EOG and ECG characteristics, which uses the driver's license examination “subject two”, is carried out in our current research work.

22 August 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
RFRongrong Fu
Rongrong Fu
KWKunpeng Wang
Kunpeng Wang
QLQisen Li
Qisen Li
GSGuangbin Sun
Guangbin Sun
GWGuilin Wen
Guilin Wen
The control of manipulator by hand surface electromyography (sEMG) signal is a key area of human-computer interaction research. One of the challenges in gesture recognition is to ensure high accuracy while maintaining a fast recognition speed. This paper uses Recursive Feature Elimination with Cross-Validation (RFECV) to select relevant features, enhancing model performance. Therefore, we propose an optimized random forest (RF) model inspired by dung beetle algorithm that mimics four key behaviors of dung beetles: rolling, breeding, foraging, and stealing. This approach introduces four optimization methods to determine the optimal number of trees and tree depth, thereby improving both the global and local search capabilities. Experimental results demonstrate that the Random Forest model based on dung beetle optimization (DBO-RF) significantly enhances the recognition accuracy of sEMG signals. Results from experiments on both our self-collected dataset and the public NinaproDB1 dataset indicate that the model exhibits superior performance and robustness compared to state-of-the-art deep learning models and traditional classification models. Additionally, experimental validation of the model’s rapid recognition capability through robotic arm control provides new insights for research in the field of human-computer interaction.