TY - CPAPER AB - Deep learning and reinforcement learning meth-ods have been shown to enable learning of flexible and complexrobot controllers. However, the reliance on large amounts oftraining data often requires data collection to be carried outin simulation, with a number of sim-to-real transfer methodsbeing developed in recent years. In this paper, we study thesetechniques for tactile sensing using the TacTip optical tactilesensor, which consists of a deformable tip with a cameraobserving the positions of pins inside this tip. We designeda model for soft body simulation which was implemented usingthe Unity physics engine, and trained a neural network topredict the locations and angles of edges when in contact withthe sensor. Using domain randomisation techniques for sim-to-real transfer, we show how this framework can be used toaccurately predict edges with less than 1 mm prediction errorin real-world testing, without any real-world data at all. AU - Ding,Z AU - Lepora,N AU - Johns,E DO - 10.1109/ICRA40945.2020.9197512 EP - 1645 PB - IEEE PY - 2020/// SN - 2152-4092 SP - 1639 TI - Sim-to-real transfer for optical tactile sensing UR - http://dx.doi.org/10.1109/ICRA40945.2020.9197512 UR - https://ieeexplore.ieee.org/abstract/document/9197512 UR - http://hdl.handle.net/10044/1/78459 ER -