TY - GEN
T1 - Augmenting Tactile Simulators with Real-like and Zero-Shot Capabilities
AU - Azulay, Osher
AU - Mizrahi, Alon
AU - Curtis, Nimrod
AU - Sintov, Avishai
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/1
Y1 - 2024/1/1
N2 - Simulating tactile perception could potentially leverage the learning capabilities of robotic systems in manipulation tasks. However, the reality gap of simulators for high-resolution tactile sensors remains large. Models trained on simulated data often fail in zero-shot inference and require fine-tuning with real data. In addition, work on high-resolution sensors commonly focus on ones with flat surfaces while 3D round sensors are essential for dexterous manipulation. In this paper, we propose a bi-directional Generative Adversarial Network (GAN) termed SightGAN. SightGAN relies on the early CycleGAN while including two additional loss components aimed to accurately reconstruct background and contact patterns including small contact traces. The proposed SightGAN learns real-to-sim and sim-to-real processes over difference images. It is shown to generate real-like synthetic images while maintaining accurate contact positioning. The generated images can be used to train zero-shot models for newly fabricated sensors. Consequently, the resulted sim-to-real generator could be built on top of the tactile simulator to provide a real-world framework. Potentially, the framework can be used to train, for instance, reinforcement learning policies of manipulation tasks. The proposed model is verified in extensive experiments with test data collected from real sensors and also shown to maintain embedded force information within the tactile images.
AB - Simulating tactile perception could potentially leverage the learning capabilities of robotic systems in manipulation tasks. However, the reality gap of simulators for high-resolution tactile sensors remains large. Models trained on simulated data often fail in zero-shot inference and require fine-tuning with real data. In addition, work on high-resolution sensors commonly focus on ones with flat surfaces while 3D round sensors are essential for dexterous manipulation. In this paper, we propose a bi-directional Generative Adversarial Network (GAN) termed SightGAN. SightGAN relies on the early CycleGAN while including two additional loss components aimed to accurately reconstruct background and contact patterns including small contact traces. The proposed SightGAN learns real-to-sim and sim-to-real processes over difference images. It is shown to generate real-like synthetic images while maintaining accurate contact positioning. The generated images can be used to train zero-shot models for newly fabricated sensors. Consequently, the resulted sim-to-real generator could be built on top of the tactile simulator to provide a real-world framework. Potentially, the framework can be used to train, for instance, reinforcement learning policies of manipulation tasks. The proposed model is verified in extensive experiments with test data collected from real sensors and also shown to maintain embedded force information within the tactile images.
UR - http://www.scopus.com/inward/record.url?scp=85202430814&partnerID=8YFLogxK
U2 - 10.1109/ICRA57147.2024.10610442
DO - 10.1109/ICRA57147.2024.10610442
M3 - Conference contribution
AN - SCOPUS:85202430814
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5702
EP - 5708
BT - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
PB - Institute of Electrical and Electronics Engineers
T2 - 2024 IEEE International Conference on Robotics and Automation, ICRA 2024
Y2 - 13 May 2024 through 17 May 2024
ER -