Generation of GelSight Tactile Images for Sim2Real Learning
This addresses the problem of occlusion in robotic manipulation for researchers by enabling Sim2Real learning with tactile sensing, though it is incremental as it adapts an existing sensor type to simulation.
The paper tackles the lack of simulated tactile sensors for Sim2Real learning in robotics by introducing a method to simulate a GelSight tactile sensor in Gazebo, which generates realistic high-resolution images similar to real sensor outputs.
Most current works in Sim2Real learning for robotic manipulation tasks leverage camera vision that may be significantly occluded by robot hands during the manipulation. Tactile sensing offers complementary information to vision and can compensate for the information loss caused by the occlusion. However, the use of tactile sensing is restricted in the Sim2Real research due to no simulated tactile sensors being available. To mitigate the gap, we introduce a novel approach for simulating a GelSight tactile sensor in the commonly used Gazebo simulator. Similar to the real GelSight sensor, the simulated sensor can produce high-resolution images by an optical sensor from the interaction between the touched object and an opaque soft membrane. It can indirectly sense forces, geometry, texture and other properties of the object and enables Sim2Real learning with tactile sensing. Preliminary experimental results have shown that the simulated sensor could generate realistic outputs similar to the ones captured by a real GelSight sensor. All the materials used in this paper are available at https://danfergo.github.io/gelsight-simulation.