Tactile sensing helps robots to localize and estimate the pose of a visually occluded object.
GelSight sensors are an example of such technology. They obtain high-resolution 3D contact information by watching the deformation of soft gels with cameras and applying photometric stereo when in touch. However, current GelSight sensors are either bulky or non-suitable for high-resolution reconstruction.
A recent paper on arXiv.org proposes the GelSight Wedge sensor, which can measure high-resolution 3D contact geometry in a compact shape.
It is possible to shrink the sensor to the size of a human finger for applications in fine manipulation tasks and multi-finger hands. The researchers show that the use of neural networks for estimating gradients improves 3D reconstruction. It enables the reconstruction when the lighting configuration is limited. The reconstructed 3D point cloud can also be used for pose tracking.
Vision-based tactile sensors have the potential to provide important contact geometry to localize the objective with visual occlusion. However, it is challenging to measure high-resolution 3D contact geometry for a compact robot finger, to simultaneously meet optical and mechanical constraints. In this work, we present the GelSight Wedge sensor, which is optimized to have a compact shape for robot fingers, while achieving high-resolution 3D reconstruction. We evaluate the 3D reconstruction under different lighting configurations, and extend the method from 3 lights to 1 or 2 lights. We demonstrate the flexibility of the design by shrinking the sensor to the size of a human finger for fine manipulation tasks. We also show the effectiveness and potential of the reconstructed 3D geometry for pose tracking in the 3D space.
Research paper: Wang, S., She, Y., Romero, B., and Adelson, E., “GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger”, 2021. Link: https://arxiv.org/abs/2106.08851