Qile Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Qile Su has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Baoyu Liang
Beihang University, Beijing, China
1 shared publication - Chao Tong
School of Computer Science and Engineering, Beihang University, Beijing, China
1 shared publication Daiyu Jia
School of Mechanical Engineering and Automation, Beihang University, Beijing, China
1 shared publication- Diansheng Chen
School of Mechanical Engineering and Automation, Beihang University, Beijing, China
1 shared publication - Junlin Ma
Institute of Robotics, Beihang University, Beijing 100191, People’s Republic of China
1 shared publication - Shoutai Zhu
School of Computer Science and Engineering and the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4698-4707
EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4698-4707
Open AccessEventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
- 16 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (13) , 14854-14863
A Self-Capacitance Proximity E-Skin With Long-Range Sensibility for Robotic Arm Environment Perception
Proximity sensing is a major requirement for intelligent robots and robotic arms to ensure safety and closed-loop control in human–robot interactions. E-skins have received increasing attention because of their ease of arraying and installation. However, problems, such as insufficient sensing distance and inaccurate distance prediction, still exist. To solve these problems, we propose a self-capacitance-based long-range proximity sensing e-skin. First, two electrode shape classifications, external edge and internal holes, were analyzed and optimized in COMSOL to explore the variation trends of charge distribution and capacitance proximity characteristics. Then, based on the self-capacitance proximity theory, the parameters of the fitting function for the actual capacitance–distance curves for the four electrodes were solved using the planning solution method. The results show that the sensor has a good dynamic response, a long proximity sensing range (10.9 cm), high distance estimation accuracy (σ = 0.45), and good repeatability (>2 h). Finally, we integrate the sensor array with the end joint of the robotic arm to complete a sorting task. A closed-loop control demonstration of safe obstacle avoidance and deceleration was achieved, thereby demonstrating the great potential of e-skin for future human–machine collaboration scenarios.
- 16 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (13) , 14854-14863
A Self-Capacitance Proximity E-Skin With Long-Range Sensibility for Robotic Arm Environment Perception
Proximity sensing is a major requirement for intelligent robots and robotic arms to ensure safety and closed-loop control in human–robot interactions. E-skins have received increasing attention because of their ease of arraying and installation. However, problems, such as insufficient sensing distance and inaccurate distance prediction, still exist. To solve these problems, we propose a self-capacitance-based long-range proximity sensing e-skin. First, two electrode shape classifications, external edge and internal holes, were analyzed and optimized in COMSOL to explore the variation trends of charge distribution and capacitance proximity characteristics. Then, based on the self-capacitance proximity theory, the parameters of the fitting function for the actual capacitance–distance curves for the four electrodes were solved using the planning solution method. The results show that the sensor has a good dynamic response, a long proximity sensing range (10.9 cm), high distance estimation accuracy (σ = 0.45), and good repeatability (>2 h). Finally, we integrate the sensor array with the end joint of the robotic arm to complete a sorting task. A closed-loop control demonstration of safe obstacle avoidance and deceleration was achieved, thereby demonstrating the great potential of e-skin for future human–machine collaboration scenarios.