Slip detection and grasp stability estimation are essential for complex object manipulation. Numerous approaches addressing the challenge of slip detection and correction have been investigated, covering several sensing technologies and computational approaches. However, robust slip prevention algorithms are not yet widely available. This project aims at developing robust slip detection and grasps stability algorithms for multi-fingered robotic hands. The project can be addressed from several focus areas, such as:
1) developing algorithms for slip detection.
2) investigate the minimum amount and data required to detect slip or estimate grasping stability.
3) automate dataset creation and labelling of new datasets for slip detection (only on-site).
Goal:
developing robust slip detection algorithms
optional: (assistance in) generation of a new dataset for grasp stability estimation with a multi-fingered hand and deformable objects
optional: application on real hardware
Prior Knowledge:
Machine Learning
Python
Related Work:
Zenha, R., Denoun, B., Coppola, C., & Jamone, L. (2021). Tactile Slip Detection in the Wild Leveraging Distributed Sensing of Both Normal and Shear Forces. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2708-2713. https://doi.org/10.1109/IROS51168.2021.9636602
arcia-Garcia, A., Zapata-Impata, B. S., Orts-Escolano, S., Gil, P., & Garcia-Rodriguez, J. (2019). TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors. International Joint Conference on Neural Networks (IJCNN), 1-8. https://doi.org/10.1109/IJCNN.2019.8851984
Navarro-Guerrero, N., Toprak, S., Josifovski, J., & Jamone, L. (2022). Visuo-Haptic Object Perception for Robots: An Overview. Autonomous Robots. https://doi.org/10.48550/arXiv.2203.11544
We look forward to receiving your complete informative application documents. For further information and application, please contact Alexander Fabisch (alexander.fabisch@dfki.de)
