Elastic Tactile Sensor Glove for Dexterous Teaching by Demonstration
Author:
Ruppel Philipp1ORCID, Zhang Jianwei1ORCID
Affiliation:
1. Department of Informatics, Universität Hamburg, 22527 Hamburg, Germany
Abstract
We present a thin and elastic tactile sensor glove for teaching dexterous manipulation tasks to robots through human demonstration. The entire glove, including the sensor cells, base layer, and electrical connections, is made from soft and stretchable silicone rubber, adapting to deformations under bending and contact while preserving human dexterity. We develop a glove design with five fingers and a palm sensor, revise material formulations for reduced thickness, faster processing and lower cost, adapt manufacturing processes for reduced layer thickness, and design readout electronics for improved sensitivity and battery operation. We further address integration with a multi-camera system and motion reconstruction, wireless communication, and data processing to obtain multimodal reconstructions of human manipulation skills.
Funder
Deutsche Forschungsgemeinschaft
Reference53 articles.
1. Ruppel, P., and Zhang, J. (2020–24, January 24). Learning Object Manipulation with Dexterous Hand-Arm Systems from Human Demonstration. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA. 2. Ijspeert, A.J., Nakanishi, J., and Schaal, S. (2002, January 9–14). Learning Attractor Landscapes for Learning Motor Primitives. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada. 3. Paraschos, A., Daniel, C., Peters, J., and Neumann, G. (2013, January 5–8). Probabilistic Movement Primitives. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA. 4. Chi, C., Feng, S., Du, Y., Xu, Z., Cousineau, E., Burchfiel, B., and Song, S. (2023, January 10–14). Diffusion Policy: Visuomotor Policy Learning via Action Diffusion. Proceedings of the Robotics: Science and Systems (RSS), Daegu, Republic of Korea. 5. Elastic Tactile Sensor Skin on Double-Curved Surfaces for Robots and Wearables;Ruppel;IEEE Access,2022
|
|