Visuotactile sensing offers rich contact information that can help mitigate performance bottlenecks in imitation learning, particularly under vision-limited conditions, such as ambiguous visual cues or occlusions. Effectively fusing visual and visuotactile modalities, however, presents ongoing challenges. We introduce GelFusion, a framework designed to enhance policies by integrating visuotactile feedback, specifically from high-resolution GelSight sensors. GelFusion using a vision-dominated cross-attention fusion mechanism incorporates visuotactile information into policy learning. To better provide rich contact information, the framework's core component is our dual-channel visuotactile feature representation, simultaneously leveraging both texture-geometric and dynamic interaction features. We evaluated GelFusion on three contact-rich tasks: surface wiping, peg insertion, and fragile object pick-and-place. Outperforming baselines, GelFusion shows the value of its structure in improving the success rate of policy learning.

Robotic tactile sensors, including vision-based and taxel-based sensors, enable agile manipulation and safe human-robot interaction through force sensation. However, variations in structural configurations, measured signals, and material properties create domain gaps that limit the transferability of learned force sensation across different tactile sensors. Here, we introduce GenForce, a general framework for achieving transferable force sensation across both homogeneous and heterogeneous tactile sensors in robotic systems. By unifying tactile signals into marker-based binary tactile images, GenForce enables the transfer of existing force labels to arbitrary target sensors using a marker-to-marker translation technique with a few paired data. This process equips uncalibrated tactile sensors with force prediction capabilities through spatiotemporal force prediction models trained on the transferred data. Extensive experimental results validate GenForce's generalizability, accuracy, and robustness across sensors with diverse marker patterns, structural designs, material properties, and sensing principles. The framework significantly reduces the need for costly and labor-intensive labeled data collection, enabling the rapid deployment of multiple tactile sensors on robotic hands requiring force sensing capabilities.

Safely handling objects and avoiding slippage are fundamental challenges in robotic manipulation, yet traditional techniques often oversimplify the issue by treating slippage as a binary occurrence. Our research presents a framework that both identifies slip incidents and measures their severity. We introduce a set of features based on detailed vector field analysis of tactile deformation data captured by the GelSight Mini sensor. Two distinct machine learning models use these features: one focuses on slip detection, and the other evaluates the slip's severity, which is the slipping velocity of the object against the sensor surface. Our slip detection model achieves an average accuracy of 92%, and the slip severity estimation model exhibits a mean absolute error (MAE) of 0.6 cm/s for unseen objects. To demonstrate the synergistic approach of this framework, we employ both the models in a tactile feedback-guided vertical sliding task. Leveraging the high accuracy of slip detection, we utilize it as the foundational and corrective model and integrate the slip severity estimation into the feedback control loop to address slips without overcompensating.

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4\% in full force range) for normal force, and 0.095N (6.3\%) and 0.062N (4.1\%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors.

Compliance is a useful parametrization of tactile information that humans often utilize in manipulation tasks. It can be used to inform low-level contact-rich actions or characterize objects at a high-level. In robotic manipulation, existing approaches to estimate compliance have struggled to generalize across object shape and material. Using camera-based tactile sensors, we present a novel approach to parametrize compliance through Young's modulus E. We evaluate our method over a novel dataset of 285 common objects, including a wide array of shapes and materials with Young's moduli ranging from 5.0 kPa to 250 GPa. Data is collected over automated parallel grasps of each object. Combining analytical and data-driven approaches, we develop a hybrid system using a multi-tower neural network to analyze a sequence of tactile images from grasping. This system is shown to estimate the Young's modulus of unseen objects within an order of magnitude at 74.2% accuracy across our dataset. This is a drastic improvement over a purely analytical baseline, which exhibits only 28.9% accuracy. Importantly, this estimation system performs irrespective of object geometry and demonstrates robustness across object materials. Thus, it could be applied in a general robotic manipulation setting to characterize unknown objects and inform decision-making, for instance to sort produce by ripeness.

Simulation is a widely used tool in robotics to reduce hardware consumption and gather large-scale data. Despite previous efforts to simulate optical tactile sensors, there remain challenges in efficiently synthesizing images and replicating marker motion under different contact loads. In this work, we propose a fast optical tactile simulator, named FOTS, for simulating optical tactile sensors. We utilize multi-layer perceptron mapping and planar shadow generation to simulate the optical response, while employing marker distribution approximation to simulate the motion of surface markers caused by the elastomer deformation. Experimental results demonstrate that FOTS outperforms other methods in terms of image generation quality and rendering speed, achieving 28.6 fps for optical simulation and 326.1 fps for marker motion simulation on a single CPU without GPU acceleration. In addition, we integrate the FOTS simulation model with physical engines like MuJoCo, and the peg-in-hole task demonstrates the effectiveness of our method in achieving zero-shot Sim2Real learning of tactile-motor robot manipulation skills. Our code is available at https://github.com/Rancho-zhao/FOTS.

Recently, several morphologies, each with its advantages, have been proposed for the \textit{GelSight} high-resolution tactile sensors. However, existing simulation methods are limited to flat-surface sensors, which prevents their usage with the newer sensors of non-flat morphologies in Sim2Real experiments. In this paper, we extend a previously proposed GelSight simulation method developed for flat-surface sensors and propose a novel method for curved sensors. In particular, we address the simulation of light rays travelling through a curved tactile membrane in the form of geodesic paths. The method is validated by simulating the finger-shaped GelTip sensor and comparing the generated synthetic tactile images against the corresponding real images. Our extensive experiments show that combining the illumination generated from the geodesic paths, with a background image from the real sensor, produces the best results when compared to the lighting generated by direct linear paths in the same conditions. As the method is parameterised by the sensor mesh, it can be applied in principle to simulate a tactile sensor of any morphology. The proposed method not only unlocks simulating existing optical tactile sensors of complex morphologies but also enables experimenting with sensors of novel morphologies, before the fabrication of the real sensor. Project website: https://danfergo.github.io/geltip-sim

MIT researchers developed a soft-rigid robotic finger that incorporates powerful sensors along its entire length, enabling them to produce a robotic hand that could accurately identify objects after only one grasp. Inspired by the human finger, MIT researchers have developed a robotic hand that uses high-resolution touch sensing to accurately identify an object after grasping it just one time. Many robotic hands pack all their powerful sensors into the fingertips, so an object must be in full contact with those fingertips to be identified, which can take multiple grasps. Other designs use lower-resolution sensors spread along the entire finger, but these don't capture as much detail, so multiple regrasps are often required. Instead, the MIT team built a robotic finger with a rigid skeleton encased in a soft outer layer that has multiple high-resolution sensors incorporated under its transparent "skin."

Inspired by the human finger, MIT researchers have developed a robotic hand that uses high-resolution touch sensing to accurately identify an object after grasping it just one time. Many robotic hands pack all their powerful sensors into the fingertips, so an object must be in full contact with those fingertips to be identified, which can take multiple grasps. Other designs use lower-resolution sensors spread along the entire finger, but these don't capture as much detail, so multiple regrasps are often required. Instead, the MIT team built a robotic finger with a rigid skeleton encased in a soft outer layer that has multiple high-resolution sensors incorporated under its transparent "skin." The sensors, which use a camera and LEDs to gather visual information about an object's shape, provide continuous sensing along the finger's entire length.

Moreover, to obtain (VTSs) have recently been developed to improve tactile a high-resolution image using a less sensitive GelSight sensor perception via high-resolution visual information [1]. VTSs (i.e., having a high thickness and stiffness gel layer), often can provide high-resolution 3D visual image reconstruction a higher interaction force is required to deform the gel layer and localization of the interacting objects by capturing tiny and obtain high-resolution images. Of note, this might not deformations of an elastic gel layer that directly interacts be feasible for several applications (e.g., high-fidelity manipulation with the objects' surface [2]. GelSight is the most wellknown of fragile objects [12] and surgical applications [13]- VTS, developed by Johnson and Adelson [3], and has [15] and may damage the sensor and reduce its durability.