Extended Tactile Perception

TL;DR

We proposed a neuromorphic fast tactile sensor for robots, and a machine learning framework for interpreting micro-vibro tactile signals.

Humans display the remarkable ability to sense the world through tools and other held objects. For example, we are able to pinpoint impact locations on a held rod and tell apart different textures using a rigid probe.

In this work, we consider how we can enable robots to have a similar capacity, i.e., to embody tools and extend perception using standard grasped objects. We propose that vibro-tactile sensing using neuromorphic fast tactile sensors on the robot fingers, along with machine learning models, enables robots to decipher contact information that is transmitted as vibrations along rigid objects.

We demonstrate that robots are able to accurately localize taps on an acrylic rod using fast vibro-tactile sensing and machine learning. Next, we show that vibro-tactile perception can lead to reasonable grasp stability classification during object handover, and accurate food identification through a standard fork.

Resources

• Accessible version of the paper
• Code associated with the paper

Citation

If you build upon our results and ideas, please use this citation.

---
@article{taunyazov2021extended,
  title={Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects},
  author={Taunyazov, Tasbolat and Song, Luar Shui and Lim, Eugene and See, Hian Hian and Lee, David and Tee, Benjamin CK and Soh, Harold},
  journal={arXiv preprint arXiv:2106.00489},
  year={2021}
}
---