Tactile Gym 2.0: Sim-to-Real Deep Reinforcement Learning for Comparing Low-Cost High-Resolution Robot Touch

被引:26
作者
Lin, Yijiong [1 ,2 ]
Lloyd, John [1 ,2 ]
Church, Alex [1 ,2 ]
Lepora, Nathan F. [1 ,2 ]
机构
[1] Univ Bristol, Dept Engn Math, Bristol BS8 1UB, Avon, England
[2] Univ Bristol, Bristol Robot Lab, Bristol BS8 1UB, Avon, England
基金
英国工程与自然科学研究理事会;
关键词
Force and tactile sensing; Deep Learning; Dexterous Manipulation; SENSORS;
D O I
10.1109/LRA.2022.3195195
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
High-resolution optical tactile sensors are increasingly used in robotic learning environments due to their ability to capture large amounts of data directly relating to agent-environment interaction. However, there is a high barrier of entry to research in this area due to the high cost of tactile robot platforms, specialised simulation software, and sim-to-real methods that lack generality across different sensors. In this letter we extend the Tactile Gym simulator to include three new optical tactile sensors (TacTip, DIGIT and DigiTac) of the two most popular types, Gelsight-style (image-shading based) and TacTip-style (marker based). We demonstrate that a single sim-to-real approach can be used with these three different sensors to achieve strong real-world performance despite the significant differences between real tactile images. Additionally, we lower the barrier of entry to the proposed tasks by adapting them to an inexpensive 4-DoF robot arm, further enabling the dissemination of this benchmark. We validate the extended environment on three physically-interactive tasks requiring a sense of touch: object pushing, edge following and surface following. The results of our experimental validation highlight some differences between these sensors, which may help future researchers select and customize the physical characteristics of tactile sensors for different manipulations scenarios.
引用
收藏
页码:10754 / 10761
页数:8
相关论文
共 34 条
[31]   TACTO: A Fast, Flexible, and Open-Source Simulator for High-Resolution Vision-Based Tactile Sensors [J].
Wang, Shaoxiong ;
Lambeta, Mike ;
Chou, Po-Wei ;
Calandra, Roberto .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) :3930-3937
[32]   The TacTip Family: Soft Optical Tactile Sensors with 3D-Printed Biomimetic Morphologies [J].
Ward-Cherrier, Benjamin ;
Pestell, Nicholas ;
Cramphorn, Luke ;
Winstone, Benjamin ;
Giannaccini, Maria Elena ;
Rossiter, Jonathan ;
Lepora, Nathan F. .
SOFT ROBOTICS, 2018, 5 (02) :216-227
[33]  
Xu HZ, 2022, Arxiv, DOI arXiv:2106.02040
[34]   GelSight: High-Resolution Robot Tactile Sensors for Estimating Geometry and Force [J].
Yuan, Wenzhen ;
Dong, Siyuan ;
Adelson, Edward H. .
SENSORS, 2017, 17 (12)