For robots manipulating open-world objects, tactile representations must generalize to unseen materials. We introduce RCT (Robotic Contact Tactile), a robot-collected touch-vision-language dataset with 29,279 tactile frames from full robot presses on 122 industrial reference materials in 7 categories, recorded with three DIGIT sensors at multiple contact positions. RCT preserves each press as a contact sequence, enabling held-out evaluation across materials, categories, sensors, contact positions, and contact sequences. Frames from one press are strongly correlated: frame-random splits can place near-duplicate observations of the same physical interaction in both training and test. With the encoder held fixed, removing contact-sequence overlap reduces tactile-to-text Recall@1 by 17.7 percentage points. When materials are additionally held out at training time, performance drops sharply, leaving held-out-material Recall@1 at 25.1 +/- 6.1

As robots become increasingly integrated into everyday tasks, their ability to perceive both the shape and properties of objects during in-hand manipulation becomes critical for adaptive and intelligent behavior. We present SemanticFeels, an extension of the NeuralFeels framework that integrates semantic labeling with neural implicit shape representation, from vision and touch. To illustrate its application, we focus on material classification: high-resolution Digit tactile readings are processed by a fine-tuned EfficientNet-B0 convolutional neural network (CNN) to generate local material predictions, which are then embedded into an augmented signed distance field (SDF) network that jointly predicts geometry and continuous material regions. Experimental results show that the system achieves a high correspondence between predicted and actual materials on both single- and multi-material objects, with an average matching accuracy of 79.87

Abstract We present a compact, low-cost solution for palpation and imaging in minimally invasive surgery and other applications requiring a small diameter. The design, called CERVA, employs a soft 8 mm silicone lens profile at the tip of a flexible endoscope. The surface is semi-relective: when illuminated from inside, light reflects to create a high-resolution tactile display. When illuminated externally, the camera can perform direct imaging of tissue. A compelling application is cervical colposcopy, where the combination of imaging and tactile display may help to identify high-risk cervical regions. We demonstrate the tactile capabilities of the sensor by comparing contact areas to classical models and through an in vivo tissue classification task. Using a phantom created to simulate stage 1A cervical cancer, we also demonstrate the imaging capabilities through visual inspection in comparison to images taken using an endoscope without the tactile dome. Our results suggest that CERVA is a promising solution to improve the accuracy of minimally-invasive palpation for data sharing between populations.

Active perception is a fundamental skill that enables us humans to deal with uncertainty in our inherently partially observable environment. For senses such as touch, where the information is sparse and local, active perception becomes crucial. In recent years, active perception has emerged as an important research domain in robotics. However, current methods are often bound to specific tasks or make strong assumptions, which limit their generality. To address this gap, this work introduces APPLE (Active Perception Policy Learning) - a novel framework that leverages reinforcement learning (RL) to address a range of different active perception problems. APPLE jointly trains a transformer-based perception module and decision-making policy with a unified optimization objective, learning how to actively gather information. By design, APPLE is not limited to a specific task and can, in principle, be applied to a wide range of active perception problems. We evaluate two variants of APPLE across different tasks, including tactile exploration problems from the Tactile MNIST benchmark. Experiments demonstrate the efficacy of APPLE, achieving high accuracies on both regression and classification tasks. These findings underscore the potential of APPLE as a versatile and general framework for advancing active perception in robotics.

Minimally invasive and robot-assisted surgery offer many advantages over traditional open surgery, but deprive surgeons of tactile feedback and the ability to palpate tissue with their fingers. To address this lack of tactile feedback, we introduce the MISTac, a high resolution vision-based tactile sensor specifically designed for palpation in MIS. The sensor has a replaceable sensor tip with a diameter of 8 mm which allows it to fit through the trocars used in minimally invasive surgery. Its modular 3D-printed case design allows the use of bulky off-the-shelf illumination and imaging hardware that can easily be exchanged and upgraded. The sensor has an optical resolution of 176.68 μm, a tactile resolution of 250 μm, and can resolve forces as little as 24.3 mN. An in vivo study with the sensor shows its usability in minimally invasive surgery. We trained a machine learning model with the tactile data collected in the trial on a tissue classification task achieving an aggregate accuracy of 84

Vision-Language-Action models (VLAs) mark a major shift in robot learning. They replace specialized architectures and task-tailored components of expert policies with large-scale data collection and setup-specific fine-tuning. In this machine learning-focused workflow that is centered around models and scalable training, traditional robotics software frameworks become a bottleneck, while robot simulations offer only limited support for transitioning from and to real-world experiments. In this work, we close this gap by introducing Robot Control Stack (RCS), a lean ecosystem designed from the ground up to support research in robot learning with large-scale generalist policies. At its core, RCS features a modular and easily extensible layered architecture with a unified interface for simulated and physical robots, facilitating sim-to-real transfer. Despite its minimal footprint and dependencies, it offers a complete feature set, enabling both real-world experiments and large-scale training in simulation. Our contribution is twofold: First, we introduce the architecture of RCS and explain its design principles. Second, we evaluate its usability and performance along the development cycle of VLA and RL policies. Our experiments also provide an extensive evaluation of Octo, OpenVLA, and Pi-Zero on multiple robots and shed light on how simulation data can improve real-world policy performance. Our code, datasets and videos are available at https://robotcontrolstack.github.io/

The field of robotic manipulation has advanced significantly in recent years. At the sensing level, several novel tactile sensors have been developed, capable of providing accurate contact information. On a methodological level, learning from demonstrations has proven an efficient paradigm to obtain performant robotic manipulation policies. The combination of both holds the promise to extract crucial contact-related information from the demonstration data and actively exploit it during policy rollouts. However, this integration has so far been underexplored, most notably in dynamic, contact-rich manipulation tasks where precision and reactivity are essential. This work therefore proposes a multimodal, visuotactile imitation learning framework that integrates a modular transformer architecture with a flow-based generative model, enabling efficient learning of fast and dexterous manipulation policies. We evaluate our framework on the dynamic, contact-rich task of robotic match lighting - a task in which tactile feedback influences human manipulation performance. The experimental results highlight the effectiveness of our approach and show that adding tactile information improves policy performance, thereby underlining their combined potential for learning dynamic manipulation from few demonstrations.

Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select which low-level skill to execute based on feedback from both the environment and the low-level skill policies themselves. Compared to learning from scratch, the hierarchical policy is more robust to out-of-distribution changes and transfers easily from simulation to real-world environments. Additionally, we propose a generalizable object pose estimator that uses proprioceptive information, low-level skill predictions, and control errors as inputs to estimate the object's pose over time. We demonstrate that our system can reorient objects, including symmetrical and textureless ones, to a desired pose.

Towards the grand challenge of achieving human-level manipulation in robots, playing piano is a compelling testbed that requires strategic, precise, and flowing movements. Over the years, several works demonstrated hand-designed controllers on real world piano playing, while other works evaluated robot learning approaches on simulated piano playing. In this work, we develop the first piano playing robotic system that makes use of learning approaches while also being deployed on a real world dexterous robot. Specifically, we use a Sim2Real2Sim approach where we iteratively alternate between training policies in simulation, deploying the policies in the real world, and use the collected real world data to update the parameters of the simulator. Using this approach we demonstrate that the robot can learn to play several piano pieces (including Are You Sleeping, Happy Birthday, Ode To Joy, and Twinkle Twinkle Little Star) in the real world accurately, reaching an average F1-score of 0.881. By providing this proof-of-concept, we want to encourage the community to adopt piano playing as a compelling benchmark towards human-level manipulation in the real world. We open-source our code and show additional videos at www.lasr.org/research/learning-to-play-piano .

Tactile perception has the potential to significantly enhance dexterous robotic manipulation by providing rich local information that can complement or substitute for other sensory modalities such as vision. However, because tactile sensing is inherently local, it is not well-suited for tasks that require broad spatial awareness or global scene understanding on its own. A human-inspired strategy to address this issue is to consider active perception techniques instead. That is, to actively guide sensors toward regions with more informative or significant features and integrate such information over time in order to understand a scene or complete a task. Both active perception and different methods for tactile sensing have received significant attention recently. Yet, despite advancements, both fields lack standardized benchmarks. To bridge this gap, we introduce the Tactile MNIST Benchmark Suite, an open-source, Gymnasium-compatible benchmark specifically designed for active tactile perception tasks, including localization, classification, and volume estimation. Our benchmark suite offers diverse simulation scenarios, from simple toy environments all the way to complex tactile perception tasks using vision-based tactile sensors. Furthermore, we also offer a comprehensive dataset comprising 13,500 synthetic 3D MNIST digit models and 153,600 real-world tactile samples collected from 600 3D printed digits. Using this dataset, we train a CycleGAN for realistic tactile simulation rendering. By providing standardized protocols and reproducible evaluation frameworks, our benchmark suite facilitates systematic progress in the fields of tactile sensing and active perception.

When robots perform complex and context-dependent tasks in our daily lives, deviations from expectations can confuse users. Explanations of the robot's reasoning process can help users to understand the robot intentions. However, when to provide explanations and what they contain are important to avoid user annoyance. We have investigated user preferences for explanation demand and content for a robot that helps with daily cleaning tasks in a kitchen. Our results show that users want explanations in surprising situations and prefer concise explanations that clearly state the intention behind the confusing action and the contextual factors that were relevant to this decision. Based on these findings, we propose two algorithms to identify surprising actions and to construct effective explanations for Belief-Desire-Intention (BDI) robots. Our algorithms can be easily integrated in the BDI reasoning process and pave the way for better human-robot interaction with context- and user-specific explanations.

Object handover is an important skill that we use daily when interacting with other humans. To deploy robots in collaborative setting, like houses, being able to receive and handing over objects safely and efficiently becomes a crucial skill. In this work, we demonstrate the use of Reinforcement Learning (RL) for dexterous object handover between two multi-finger hands. Key to this task is the use of a novel reward function based on dual quaternions to minimize the rotation distance, which outperforms other rotation representations such as Euler and rotation matrices. The robustness of the trained policy is experimentally evaluated by testing w.r.t. objects that are not included in the training distribution, and perturbations during the handover process. The results demonstrate that the trained policy successfully perform this task, achieving a total success rate of 94% in the best-case scenario after 100 experiments, thereby showing the robustness of our policy with novel objects. In addition, the best-case performance of the trained policy decreases by only 13.8% when the other robot moves during the handover, proving that our policy is also robust to this type of perturbation, which is common in real-world object handovers. Code and videos can be found here.

Optical tactile sensors have recently become popular. They provide high spatial resolution, but struggle to offer fine temporal resolutions. To overcome this shortcoming, we study the idea of replacing the RGB camera with an event-based camera and introduce a new event-based optical tactile sensor called Evetac. Along with hardware design, we develop touch processing algorithms to process its measurements online at 1000 Hz. We devise an efficient algorithm to track the elastomer's deformation through the imprinted markers despite the sensor's sparse output. Benchmarking experiments demonstrate Evetac's capabilities of sensing vibrations up to 498 Hz, reconstructing shear forces, and significantly reducing data rates compared to RGB optical tactile sensors. Moreover, Evetac's output and the marker tracking provide meaningful features for learning data-driven slip detection and prediction models. The learned models form the basis for a robust and adaptive closed-loop grasp controller capable of handling a wide range of objects. We believe that fast and efficient event-based tactile sensors like Evetac will be essential for bringing human-like manipulation capabilities to robotics. The sensor design is open-sourced at https://sites.google.com/view/evetac .

In our daily life, we often encounter objects that are fragile and can be damaged by excessive grasping force, such as fruits. For these objects, it is paramount to grasp gently—not using the maximum amount of force possible, but rather the minimum amount of force necessary. This paper proposes using visual, tactile, and auditory signals to learn to grasp and regrasp objects stably and gently. Specifically, we use audio signals as an indicator of gentleness during the grasping, and then train an end-to-end action-conditional model from raw visuo-tactile inputs that predicts both the stability and the gentleness of future grasping candidates, thus allowing the selection and execution of the most promising action. Experimental results on a multi-fingered hand over 1,500 grasping trials demonstrated that our model is useful for gentle grasping by validating the predictive performance (3.27% higher accuracy than the vision-only variant) and providing interpretations of their behavior. Finally, real-world experiments confirmed that the grasping performance with the trained multi-modal model outperformed other baselines (17% higher rate for stable and gentle grasps than vision-only). Our approach requires neither tactile sensor calibration nor analytical force modeling, drastically reducing the engineering effort to grasp fragile objects. Dataset and videos are available at https://lasr.org/research/gentle-grasping.

Vision-based tactile sensors use structured light to measure deformation in their elastomeric interface. Until now, vision-based tactile sensors such as DIGIT and GelSight have been using a single, static pattern of structured light tuned to the specific form factor of the sensor. In this work, we investigate the effectiveness of dynamic illumination patterns, in conjunction with image fusion techniques, to improve the quality of sensing of vision-based tactile sensors. Specifically, we propose to capture multiple measurements, each with a different illumination pattern, and then fuse them together to obtain a single, higher-quality measurement. Experimental results demonstrate that this type of dynamic illumination yields significant improvements in image contrast, sharpness, and background difference. This discovery opens the possibility of retroactively improving the sensing quality of existing vision-based tactile sensors with a simple software update, and for new hardware designs capable of fully exploiting dynamic illumination.

Vision-based tactile sensors have recently become popular due to their combination of low cost, very high spatial resolution, and ease of integration using widely available miniature cameras. The associated field of view and focal length, however, are difficult to package in a human-sized finger. In this paper we employ optical fiber bundles to achieve a form factor that, at 15 mm diameter, is smaller than an average human fingertip. The electronics and camera are also located remotely, further reducing package size. The sensor achieves a spatial resolution of 0.22 mm and a minimum force resolution 5 mN for normal and shear contact forces. With these attributes, the DIGIT Pinki sensor is suitable for applications such as robotic and teleoperated digital palpation. We demonstrate its utility for palpation of the prostate gland and show that it can achieve clinically relevant discrimination of prostate stiffness for phantom and ex vivo tissue.

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent years, how to best learn the model is still an unresolved question. The majority of MBRL algorithms aim at training the model to make accurate predictions about the environment and subsequently using the model to determine the most rewarding actions. However, recent research has shown that model predictive accuracy is often not correlated with action quality, tracing the root cause to the objective mismatch between accurate dynamics model learning and policy optimization of rewards. A number of interrelated solution categories to the objective mismatch problem have emerged as MBRL continues to mature as a research area. In this work, we provide an in-depth survey of these solution categories and propose a taxonomy to foster future research.

Touch is an important sensing modality for humans, but it has not yet been incorporated into a multimodal generative language model. This is partially due to the difficulty of obtaining natural language labels for tactile data and the complexity of aligning tactile readings with both visual observations and language descriptions. As a step towards bridging that gap, this work introduces a new dataset of 44K in-the-wild visiontouch pairs, with English language labels annotated by humans (10%) and textual pseudo-labels from GPT-4V (90%). We use this dataset to train a vision-language-aligned tactile encoder for open-vocabulary classification and a touch-visionlanguage (TVL) model for text generation using the trained encoder. Results suggest that by incorporating touch, the TVL model improves (+29% classification accuracy) tactile-vision-language alignment over existing models trained on any pair of those modalities. Although only a small fraction of the dataset is human labeled, the TVL model demonstrates improved visual-tactile understanding over GPT-4V (+12%) and open-source vision-language models (+32%) on a new touch-vision understanding benchmark. Code, checkpoints and data are available on https: //tactile-vlm.github.io.

To achieve human-level dexterity, robots must infer spatial awareness from multimodal sensing to reason over contact interactions. During in-hand manipulation of novel objects, such spatial awareness involves estimating the object's pose and shape. The status quo for in-hand perception primarily uses vision and is restricted to tracking a priori known objects. Moreover, visual occlusion of objects in hand is imminent during manipulation, preventing current systems from pushing beyond tasks without occlusion. We combined vision and touch sensing on a multifingered hand to estimate an object's pose and shape during in-hand manipulation. Our method, NeuralFeels, encodes object geometry by learning a neural field online and jointly tracks it by optimizing a pose graph problem. We studied multimodal in-hand perception in simulation and the real world, interacting with different objects via a proprioception-driven policy. Our experiments showed final reconstruction F scores of 81% and average pose drifts of 4.7 millimeters, which was further reduced to 2.3 millimeters with known object models. In addition, we observed that, under heavy visual occlusion, we could achieve improvements in tracking up to 94% compared with vision-only methods. Our results demonstrate that touch, at the very least, refines and, at the very best, disambiguates visual estimates during in-hand manipulation. We release our evaluation dataset of 70 experiments, FeelSight, as a step toward benchmarking in this domain. Our neural representation driven by multimodal sensing can serve as a perception backbone toward advancing robot dexterity.