Surface Following using Deep Reinforcement Learning and a GelSightTactile Sensor
arXiv:1912.00745
Abstract
Tactile sensors can provide detailed contact in-formation that can facilitate robots to perform dexterous, in-hand manipulation tasks. One of the primitive but important tasks is surface following that is a key feature for robots while exploring unknown environments or workspace of inaccurate modeling. In this paper, we propose a novel end-to-end learning strategy, by directly mapping the raw tactile data acquired from a GelSight tactile sensor to the motion of the robot end-effector.Experiments on a KUKA youBot platform equipped with theGelSight sensor show that 80% of the actions generated by a fully trained SFDQN model are proper surface following actions; the autonomous surface following test also indicates that the proposed solution works well on a test surface.
7 pages, 7 figures
References in corpus (1)
Cited by in corpus (5)
- When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective
- Tacchi: A Pluggable and Low Computational Cost Elastomer Deformation Simulator for Optical Tactile Sensors
- Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learning
- Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear
- Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard