Tao Fang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tao Fang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Ao Li
The School of Information Science and Technology, University of Science and Technology of China, Hefei, China
1 shared publication - Minghui Wang
The School of Information Science and Technology, University of Science and Technology of China, Hefei, China
1 shared publication - Wei Liu
Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
1 shared publication - Yin Luo
School of Information Science and Technology, University of Science and Technology of China, China
1 shared publication
Latest Publications
- Open Access
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 372-376
Grasp stability assessment through the fusion of visual and tactile signals using deep bilinear network
Evaluating the grasp stability of the robot is critical to robotic manipulation. It is very effective to combine visual and tactile information to evaluate the stability of a grip. However, most of the methods directly concatenate features of heterogeneous data that may ignore the comprehensive interaction between different modalities. Furthermore, existing methods ignore the influence of intra-modality that may degrade the performance of grasp stability assessment. To address this issue, we proposed a framework named visual and tactile deep bilinear network (VTDBN) to evaluate the grasp stability of robots by integrating visual data and tactile data. Moreover, we conduct comprehensive experiments to build a dataset that can be used for training and testing. The experiment results show that VTDBN model significantly improves the performance of robotic grasp stability assessment and outperforms traditional methods.
- 23 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 372-376
Open AccessGrasp stability assessment through the fusion of visual and tactile signals using deep bilinear network
Evaluating the grasp stability of the robot is critical to robotic manipulation. It is very effective to combine visual and tactile information to evaluate the stability of a grip. However, most of the methods directly concatenate features of heterogeneous data that may ignore the comprehensive interaction between different modalities. Furthermore, existing methods ignore the influence of intra-modality that may degrade the performance of grasp stability assessment. To address this issue, we proposed a framework named visual and tactile deep bilinear network (VTDBN) to evaluate the grasp stability of robots by integrating visual data and tactile data. Moreover, we conduct comprehensive experiments to build a dataset that can be used for training and testing. The experiment results show that VTDBN model significantly improves the performance of robotic grasp stability assessment and outperforms traditional methods.