Qi Sun

Ms. Qi Sun

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
24 September 2023 in Sensors
Verified
Journal Article
Open access
PDF file
HXHao Xu
Hao Xu
QSQi Sun
Qi Sun
WLWeiwei Liu
Weiwei Liu
MYMinghao Yang
Minghao Yang
Secure grasping of objects in complex scenes is the foundation of many tasks. It is important for robots to autonomously determine the optimal grasp based on visual information, which requires reasoning about the stacking relationship of objects and detecting the grasp position. This paper proposes a multi-task secure grasping detection model, which consists of the grasping relationship network (GrRN) and the oriented rectangles detection network CSL-YOLO, which uses circular smooth label (CSL). GrRN uses DETR to solve set prediction problems in object detection, enabling end-to-end detection of grasping relationships. CSL-YOLO uses classification to predict the angle of oriented rectangles, and solves the angle distance problem caused by classification. Experiments on the Visual Manipulate Relationship Dataset (VMRD) and the grasping detection dataset Cornell demonstrate that our method outperforms existing methods and exhibits good applicability on robot platforms.

27 December 2022
Verified
Conference Paper
Open access
HXHao Xu
Hao Xu
YSYangchang Sun
Yangchang Sun
QSQi Sun
Qi Sun
MYMinghao Yang
Minghao Yang
JCJinlong Chen
Jinlong Chen
JWJinghong Wang
Jinghong Wang
This work proposes a three-dimensional (3D) robot grasp pose generation method for robot manipulators from the predicted two-dimensional (2D) anchors and the depth information of the local surface. Compared to the traditional image-based grasp area detection methods in which the grasp pose is only presented by two contact points, the proposed method can generate a more accurate 3D grasp pose. Furthermore, different from the 6-DoF object pose regression methods in which the point cloud of the whole objects is considered, the proposed method is very lightweight, since the 3D computation is only processed on the depth information of the local grasp surface. The method consists of three steps: (1) detecting the 2D grasp anchor and extracting the local grasp surface from the image; (2) obtaining the average vector of the objects’ local grasp surface from the objects’ local point cloud; (3) generating the 3D grasp pose from 2D grasp anchor based on the average vector of local grasp surface. The experiments are carried out on the Cornell and Jacquard grasp datasets. It is found that the proposed method yields improvement in the grasp accuracy compared to state-of-the-art 2D anchor methods. And the proposed method is also validated on the practical grasp tasks deployed on a UR5 arm with Robotiq Grippers F85. It outperforms state-of-the-art 2D anchor methods on the grasp success rate for dozens of practical grasp tasks.

24 June 2025
Verified
Book Chapter
Closed access
PDF file
JHJunyu Hao
Junyu Hao
JLJianheng Liu
Jianheng Liu
YZYongjia Zhao
Yongjia Zhao
ZCZuofan Chen
Zuofan Chen
QSQi Sun
Qi Sun
MYMinghao Yang
Minghao Yang

4 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
JHJunyu Hao
Junyu Hao
JLJianheng Liu
Jianheng Liu
YZYongjia Zhao
Yongjia Zhao
ZCZuofan Chen
Zuofan Chen
QSQi Sun
Qi Sun
MYMinghao Yang
Minghao Yang
When presented with one or a few photos of a previously unseen object, humans can instantly recognize it in different scenes. Although the human brain mechanism behind this phenomenon is still not fully understood, this work introduces a novel technical realization of this task. It consists of two phases: (1) generating a Similarity Density Map (SDM) by convolving the scene image with the given object image patch(es) so that the highlight areas in the SDM indicate the possible locations; (2) obtaining the object occupied areas in the scene through a Region Alignment Network (RAN). The RAN is constructed on a backbone of Deep Siamese Network (DSN), and different from the traditional DSNs, it aims to obtain the object accurate regions by regressing the location and area differences between the ground truths and the predicted ones indicated by the highlight areas in SDM. By pre-learning from labels annotated in traditional datasets, the SDM-RAN can detect previously unknown objects without fine-tuning. Experiments were conducted on the MS COCO, PASCAL VOC datasets. The results indicate that the proposed method outperforms state-of-the-art methods on the same task.

22 October 2026 in Machines
Verified
Journal Article
Open access
PDF file
QSQi Sun
Qi Sun
ZCZuofan Chen
Zuofan Chen
LHLili He
Lili He
Despite the development of various dexterous grasping techniques, it remains challenging for robots to successfully pick unknown objects through an image or speech input provided by a human. The challenge lies in the absence of an effective mechanism to integrate visual information and instruction derived from human interaction, and to subsequently associate this integration with unknown objects captured by sensors in a real-world scenario. To address this challenge, this work proposes an interactive vision and instruction grasping method for unknown objects (VIG-Un). The proposed VIG-Un offers users three communication modes: visual interaction, instruction interaction, and vision–instruction combined interaction. In the vision-based mode, ARUCO marker boards serve as input samples for object detection, providing a reliable visual reference for accurate object localization. In the instruction mode, we introduce a Semantic-Aware Image Generation Branch (SAIGB), which generates relevant images based on textual instructions, enabling semantic understanding in grasping tasks. Then, VIG-Un leverages a Deep Siamese Network (DSN)-based few-shot object detection approach, reducing the reliance on visual fine-tuning and substantially enhancing the flexibility and adaptability of robotic manipulators during grasp operations. In experimental evaluations benchmarked against state-of-the-art methods, including YOLO-World and RT-1, the VIG-Un framework achieves higher object detection accuracy and grasping success rates than these competitors on object-grasping tasks in typical indoor environments, while maintaining acceptable execution efficiency, demonstrating its effectiveness and robustness.

3 January 2025 in Machine Vision and Applications
Verified
Journal Article
Closed access
PDF file
WLWeiwei Liu
Weiwei Liu
QSQi Sun
Qi Sun
MYMinghao Yang
Minghao Yang