#Visual-tactile (6)

Waterfall Pagination

0:32

Prima 1 robotic hand: 22 DOF with vision and touch

@spaceandtech_ · 165 views · 2026-09-02

XynovaPrima 1Robotic Hand

3:08

ADEPT: Sim Pre-training for Zero-Shot Visuo-Tactile Dexterity

@jayjunleee · 130 views · 2026-08-20

ADEPTDexterous HandDexterous Manipulation

Lumibot Lumi-Dex-23 High-DoF Dexterous Hand

The Lumi-Dex-23 is the industrial-flagship dexterous hand from Zhejiang Shiyue Technology (Lumibot): 23 active DoF with a hybrid direct-drive + linkage actuation and integrated driver-controller, weighing only 850 g at 225 mm total length (98 mm four-finger palm width). The thumb yaws 90° to touch the little-fingertip; fingers bend MCP/PIP/DIP 90°/90°/70° with ±15° splay, thumb yaw speed up to 360°/s and bend 270°/s, four-finger bend 0.3 s/cycle. It delivers 20 N fingertip press, 40 N pinch and 80 N grip active force with a 25 kg passive load, stably grasping 10-50 mm cylindrical/spherical objects. Optional Lumi-Tac visuotactile fingertips (10 μm spatial resolution, 0.02 N force precision), DC12V power, RS485/CAN communication and replaceable four fingers target research, biopharma, 3C electronics, rail transit and automotive manipulation.

COMPONENT

Dexterous HandLumi-Dex-23ShiYue TechnologyVisual-tactileHigh Degrees of Freedom

Daimon DM-Tac X Vision-Based Tactile Sensor

Compact vision-based tactile sensor, 41x24x18 mm at 19.2 g; 20x15 mm² sensing area, 640x480 camera, 384x288 tactile resolution with 110,592 sensing points, 120 Hz, IP67, USB 2.0, sensitivity <1% F.S., for dexterous manipulation.

COMPONENT

Visual-tactileTactile sensorsDaimengDM-Tac

ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation

Contact-rich robot manipulation requires physical interaction cues that are often invisible to cameras, making tactile sensing essential for robust control. However, scaling visuo-tactile robot learning remains difficult because real tactile interaction data are expensive to collect, hardware-dependent, and limited in task and scene diversity. We present ViTacWorld, an action-conditioned visuo-tactile world model for scalable contact-rich robot manipulation. ViTacWorld leverages public real tactile datasets and a constructed simulation environment to scale visuo-tactile-action data, exploiting the fact that tactile signals are directly grounded in physical contact and can exhibit a smaller simulation-to-real gap than purely visual observations. The model is first pretrained with large-scale real and simulated visuo-tactile trajectories, and then finetuned with real-world policy rollouts to better match downstream manipulation behaviors. Given robot actions, ViTacWorld predicts temporally aligned visual observations and tactile feedback, enabling visuo-tactile-action rollout generation. To the best of our knowledge, ViTacWorld is the first framework that uses a world model for robot visuo-tactile-action trajectory generation and policy evaluation. It serves two roles: synthesizing rollouts to improve downstream tactile policies, and evaluating policies by predicting action-conditioned visuo-tactile outcomes under controlled action sequences. Experiments on contact-rich manipulation tasks show that ViTacWorld generates physically meaningful rollouts, improves policy performance through scalable data augmentation, and enables action-conditioned policy evaluation. Project page: https://vitacworld.github.io/

Yunao Huang, Shiyu Sang, Haotao LuJul 24, 2026

World ModelsVisuo-TactileRobot ManipulationJul 24, 2026

FELT: Generating Tactile Signals from Vision for Visuo-Tactile Manipulation

The sense of touch is central to manipulation, especially when vision is occluded or ambiguous. Although combining vision and touch improves manipulation, learning robust visuo-tactile policies requires substantial tactile data. Such data remains scarcer than visual data, because tactile sensors are fragile, specialized, and hard to standardize. To address this, we present Feature-Extracted Latent Tactile (FELT), a learning-based framework that synthesizes per-finger pressure tactile images from RGB observations, reducing the need for tactile-equipped data collection. FELT uses a large frozen visual encoder and a lightweight query decoder to predict tactile signals in a single feed-forward pass. To respect the physical topology of dual-finger tactile sensors, FELT decodes the left and right tactile sensor panels through separate branches, capturing the asymmetric contact patterns during interactions such as wiping, insertion, and in-hand rotation. At inference time, FELT only requires RGB data, allowing us to augment existing vision-only data with tactile observations, either as generated tactile images or as latent tactile features. Experiments on four contact-rich manipulation tasks demonstrate that both generated tactile images and latent tactile features improve policy success over vision-only baselines, with latent feature requiring no real tactile sensor during policy training or deployment. Supplementary material is available on our anonymous website: https://felt-tactile.github.io/.

Zinan Li, Yiyang Ling, Yuming GuJul 22, 2026

Tactile GenerationVisual-tactileCross-ModalityJul 22, 2026