Artificial Palpation Primitives Dataset New
Technion – Israel Institute of Technology
Automatic robotic-palpation tactile dataset used in "More with LESS – Local Scene Representations for Tactile Imaging" (RSS 2026). We have included the "data-primitive" here, as described in the paper. See https://zoharri.github.io/LESS/ for more details.
touch cc-by-4.0
Artificial Palpation Poke-Orientation Dataset New
Technion – Israel Institute of Technology
Automatic robotic-palpation tactile dataset used in "More with LESS – Local Scene Representations for Tactile Imaging" (RSS 2026). We have included here the "data-poke", which is described in the paper (union of "data-v1" and "data-orientation"). See https://zoharri.github.io/LESS/ for more details.
touch cc-by-4.0
VisuoTactile-GS Visuo-tactile contact data with DenseTact optical tactile images paired to RGB views, packaged in the Open-X-Tactile / FTP-1 zarr format. The data format, key naming, pose convention and field semantics are defined by Open-X-Tactile. Please refer to the OXT website and the FTP-1 data processing documentation for how to read and interpret these files. Contents Sub-dataset Frames Scene block.zarr 166 textured block bunny_real.zarr 134… See the full description on the dataset page: https://huggingface.co/datasets/jsun/VisuoTactile-GS.
DenseTact Vision-based touch
awesome-touch New
sun254667
A curated, learning-friendly list of tactile sensing research resources for robotic manipulation: papers, datasets, benchmarks, simulation platforms, and frameworks, covering the integration of touch with Vision-Language-Action (VLA) models and World Models for contact-rich manipulation
touch vision
right_arm_manipulation_with_wrist_top_camera_tactile_merged_1_trim_ep5_17s_cleaned New
puheliang
No description provided upstream.
touch vision
tacwam-tactile-mot-v2-splits
haohw
tacWAM Tactile-MoT v2 — split manifests (train / validation / test) Partition + normalization manifests for the tacWAM Cosmos-3 video+tactile joint-prediction corpus (v2, combined ~30 h). This repo lets an evaluator know exactly which recordings are train / validation / test and how tactile is normalized — so eval is done on the held-out split with the same preprocessing as training. ⚠️ The raw data is NOT included here. The recordings are egocentric human-subject video +… See the full description on the dataset page: https://huggingface.co/datasets/haohw/tacwam-tactile-mot-v2-splits.
touch vision other
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so_tactile_follower", "total_episodes": 33, "total_frames": 42178, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:33" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/ydaichi/tactile_test2.
touch vision apache-2.0
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so_tactile_follower", "total_episodes": 0, "total_frames": 0, "total_tasks": 0, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": {}, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/ydaichi/tactile_test.
touch vision apache-2.0
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so_tactile_follower", "total_episodes": 0, "total_frames": 0, "total_tasks": 0, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": {}, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/ydaichi/tactile_pen_bag.
touch vision apache-2.0
tactile-deformation-response
Tachintech
Tactile Deformation Response Dataset Dataset Summary This dataset contains tactile array time-series samples collected from a 32 × 32 tactile sensor. Each sample is represented by a fixed-length sequence of base-corrected tactile response frames and paired with a JSON metadata file. The primary task is binary deformation response classification: rigid versus deformable. The dataset is intended for research on tactile perception, contact response modeling, material… See the full description on the dataset page: https://huggingface.co/datasets/Tachintech/tactile-deformation-response.
Taxel touch gpl-3.0
rough_tactile
Fxxkrobotics
robosuite (trimmed handoff build) A simulation setup based on robosuite (v1.5.2) for running robot manipulation tasks in MuJoCo and prototyping ideas. The original tactile data-collection / policy-training (ACT) scaffolding has been removed. This copy keeps only the runnable simulation core so you can get started quickly. What's in here Standard robosuite: built-in tasks (Lift, Stack, NutAssembly, PickPlace, Door, Wipe, two-arm, ...), controllers (OSC / JOINT /… See the full description on the dataset page: https://huggingface.co/datasets/Fxxkrobotics/rough_tactile.
touch
Tactile_Grasp_Dataset
OSU-RAD-Lab
Dataset of grasps with tactile and camera (wrist & overview) data.
touch vision mit
SmolVLA-DexHand-Tactile-Data
KrisYoung
SmolVLA DexHand Tactile Data 本仓库存放 SmolVLA DexHand Tactile 项目的 MuJoCo 模仿学习数据。任务为 RM65 + Gaia 五指灵巧手抓取苹果并放入盘中。 内容 当前普通数据：300 episodes，由 regular_300_local、regular_300_s1、regular_300_s2 三个独立数据源各 100 episodes 组成。 每帧包含 20D 指尖触觉、双 RGB 相机和 22D state/action。 数据为 20 Hz LeRobot 格式。每个数据源保留为独立目录，不在 Hub 端重新拼接；准确的目录、 episode/frame 数量、seed 范围、场景资产 SHA256 和适用限制以代码仓库的 configs/artifacts.json 为准。 为与当前最佳 S2V 权重严格对应，本仓库不上传旧版 302、额外普通 500 或纠错 90 条数据。 下载… See the full description on the dataset page: https://huggingface.co/datasets/KrisYoung/SmolVLA-DexHand-Tactile-Data.
touch vision
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so_tactile_follower", "total_episodes": 3, "total_frames": 4480, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:3" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/hazel1016/tactile_test.
touch vision apache-2.0
board_insertion_ablation_dagger_round2_tactile
chomeed
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "fps": 30, "features": { "observation.state": { "dtype": "float32", "shape": [ 27 ], "names": [ "arm_left.joint1", "arm_left.joint2", "arm_left.joint3", "arm_left.joint4", "arm_left.joint5"… See the full description on the dataset page: https://huggingface.co/datasets/chomeed/board_insertion_ablation_dagger_round2_tactile.
touch apache-2.0
tactile-genesis-heavy-mg-v2
jalal06
Tactile Genesis heavy-cube pick-and-place (heavy_mg_v2) 272 success-filtered scripted-expert episodes (158 frames each, 60 Hz sim / 1 control step per frame) of a Franka Panda picking up a randomized-mass grey cube (0.24–1.19 kg, uniform-by-density; visually identical across masses) among 3 distractor cubes and placing it in a basket, in the Genesis simulator. The scripted expert is tactile-reactive: grip force ramps on sensed slip. Collected with MimicGen-style stratified… See the full description on the dataset page: https://huggingface.co/datasets/jalal06/tactile-genesis-heavy-mg-v2.
touch vision force mit
board_insertion_ablation_dagger_tactile
chomeed
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "fps": 30, "features": { "observation.state": { "dtype": "float32", "shape": [ 27 ], "names": [ "arm_left.joint1", "arm_left.joint2", "arm_left.joint3", "arm_left.joint4", "arm_left.joint5"… See the full description on the dataset page: https://huggingface.co/datasets/chomeed/board_insertion_ablation_dagger_tactile.
touch vision apache-2.0
multi_cam_tactile_wallmount
Ishrath-98
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so_follower", "total_episodes": 15, "total_frames": 8437, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:15" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Ishrath-98/multi_cam_tactile_wallmount.
touch vision apache-2.0
awesome-taptic-papers
mistephan
A curated reading list of vision-tactile robot learning papers, covering tactile VLA/VTLA, world models, datasets, sensing hardware, and contact-rich manipulation.
touch vision
vtwm-tactile-latent-delta-viz
yxma
VideoVAE+ vs Cosmos — Latent tokenizer diagnostic for visuo-tactile world model Timeline: 2026-07-02 to 2026-07-03. Diagnosing whether our current VideoVAE+ latent tokenizer has architectural issues that hurt downstream world model training, and whether NVIDIA's Cosmos Tokenizer CV4x8x8 is a viable replacement. TL;DR Two architectural issues found in VideoVAE+, both absent in Cosmos: Right-bottom spatial hotspot — Downsample2plus1D uses asymmetric zero-pad on… See the full description on the dataset page: https://huggingface.co/datasets/yxma/vtwm-tactile-latent-delta-viz.
touch vision
clothumi-0619-0623-uniforce-tactile-clean-alltrain-zarr
LancetRobotics
No description provided upstream.
touch
ego-tactile-manipulation
OpenGraphLabs-Research
Ego-Tactile Manipulation Egocentric video + dense two-hand tactile + touch-grounded action labels - by OpenGraph Labs. Four episodes visualized in our dashboard - egocentric video with live tactile & sensor signals. Synchronized ego + touch human-manipulation data is rare. This is a clean 1.28-hour sample from OpenGraph Labs' Physical-AI data pipeline: a head camera plus our OGLO tactile gloves on both hands, with action labels derived from the physical contact signal.… See the full description on the dataset page: https://huggingface.co/datasets/OpenGraphLabs-Research/ego-tactile-manipulatio…
touch vision cc-by-4.0
Fixed_Viewpoint_Tactile_Dataset
Tachintech
Fixed Viewpoint Tactile Dataset 基于固定机位动捕设备的动捕-触觉数据集。 格式：LeRobot v3.0 fps: 20 episodes: 160，frames: 59158 观测：动捕位置/四元数、20 路触觉、RGB + Depth 视频 机器人类型：tactile_hand_motion_321_340 安装依赖 pip install -r requirements.txt # 需要 Python >= 3.10 快速开始 from lerobot.datasets.lerobot_dataset import LeRobotDataset ds = LeRobotDataset("Tachintech/Fixed_Viewpoint_Tactile_Dataset") # 自动下载 s = ds[100] # 一帧 = dict s["action"]… See the full description on the dataset page: https://huggingface.co/datasets/Tachintech/Fixed_Viewpoint_Tactile_Dataset.
touch vision depth apache-2.0
Awesome-Dexterous-Hands
CyanHaze
A curated list of papers, datasets, simulators, hardware platforms, and open-source resources for dexterous robot hands and hand-object manipulation.
touch cc-by-4.0
The first cross-sensor unified tactile annotation benchmark — TLabel-Bench
touch other
dual-gelsight-marker-20260617
LancetRobotics
Dual GelSight Marker-Mask Dataset 20260617 This dataset contains synchronized marker-mask tactile captures from two GelSight-style sensors: gelsight_mini: GelSight Mini camera stream gelsight: custom UVC GelSight-style camera stream Only marker-mask images are included. Raw RGB camera frames were intentionally omitted from this Hub upload. Directory Layout marker/<sensor>/<indenter>/<frame_id>.jpg Sensors marker/gelsight_mini: 3280x2464… See the full description on the dataset page: https://huggingface.co/datasets/LancetRobotics/dual-gelsight-marker-20260617.
GelSight touch vision other
Awesome-Visuo-Tactile-Datasets
lif314
Dataset Is All You Need!
touch
gelsight-mini-gelsight-20260617
LancetRobotics
Dual GelSight Tactile Dataset 20260617 This dataset contains synchronized marker-mask tactile captures from two GelSight-style sensors: gelsight_mini: GelSight Mini camera stream gelsight: custom UVC GelSight-style camera stream The data was collected on 2026-06-17 for real-world finetuning/adaptation of UniForce-style tactile models. Directory Layout marker/<sensor>/<indenter>/<frame_id>.jpg collection_log.txt The marker folders contain marker mask images… See the full description on the dataset page: https://huggingface.co/datasets/LancetRobotics/gelsight-mini-gelsight-20260617.
GelSight touch vision other
The dataset for TacSpike，generated by v2e from Gelsight
GelSight touch
Gelsight-Welds Paired tactile (GelSight Mini) and top-down RGB (Intel RealSense D555) captures of weld beads on a flat sample plate. Each sample (session) is scanned with a 10×10 grid of GelSight touches; the D555 takes one overhead shot per session, which we crop into per-tile RGB images aligned with each touch. Loading from datasets import load_dataset ds = load_dataset("Gelsight-Welds", split="all") # uses config "v2" by default; no train/val/test split is… See the full description on the dataset page: https://huggingface.co/datasets/ppak10/Gelsight-Welds.
GelSight touch vision mit
Pie et al. 2026 Figure Data
Vrije Universiteit Amsterdam
This is the source data for the figures in the article " Touch responses in barrel cortex layer 5 pyramidal cell types are differentially shaped by visuotactile experience " by Pie, van den Heuvel, et al. (2026)
touch cc-by-4.0
tactile-video-pretrain-nc
yxma
Tactile Video Pretrain — non-commercial sibling (yxma/tactile-video-pretrain-nc) Companion to yxma/tactile-video-pretrain — aggregates GelSight-style tactile-video sources whose licenses do not allow commercial use and so cannot mix into the MIT main repo. Currently included: Baihu-VTouch (sample subset of 4 tasks across 2 robot platforms). Format Each episode lives at: videos/baihu_vtouch/<task>/<robot>/<episode_id>/ ├── bimanual.mp4 ← compact preview… See the full description on the dataset page: https://huggingface.co/datasets/yxma/tactile-video-pretrain-nc.
GelSight touch vision cc-by-nc-sa-4.0
tactile-video-pretrain
yxma
Tactile Video Pretrain (yxma/tactile-video-pretrain) ~48 hours of GelSight-style tactile video, aggregated across 4 public sources. Each row is one demonstration / episode / scan / touch session. Two configs share one shared video folder: tactile_only — one tactile stream per row. Use for tactile-only self-supervised pretraining (video MAE / V-JEPA / contrastive / masked). tactile_rgb — paired (tactile, scene-RGB) videos per row. Use for cross-modal alignment (CLIP-style… See the full description on the dataset page: https://huggingface.co/datasets/yxma/tactile-video-pretrain.
GelSight touch vision mit
fiber-tactile-calibration-sim
Yang251552
Simulated high-throughput robotic calibration & characterization platform for a custom optical-fiber tactile sensor: HAL → contact physics → forward sensor model → dataset → inverse ML → characterization.
touch mit
tactile_align_encoder_pretrain_xela
youngw
No description provided upstream.
uSkin touch proprioception
Daimon-Infinity
dmrobot-admin
Daimon-Infinity: The world's largest omni-modal robotics dataset for physical AI, including high-resolution tactile sensing.
touch other
insert_hdmi_tactile_lerobot_hw_270_480
adk111
No description provided upstream.
touch vision
LESS OOD Dataset
Technion – Israel Institute of Technology
Automatic robotic-palpation tactile dataset used in "More with LESS – Local Scene Representations for Tactile Imaging" (RSS 2026). We have included here the "multiple" set measurements (phantoms with multiple inclusions), which is described in the paper. See https://zoharri.github.io/LESS/ for more details.
touch cc-by-4.0
piper-stack-act-tactile-depth-v0
axiboai
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": null, "total_episodes": 400, "total_frames": 223205, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100,"video_files_size_in_mb": 200, "fps": 50, "splits": { "train": "0:400" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/axiboai/piper-stack-act-tactile-depth-v0.
touch vision depth apache-2.0
univtac_insert_hdmi_tactile_lerobot_50
adk111
No description provided upstream.
touch vision
gelsight-mini-pretrain-video
yxma
GelSight Mini Pretrain · Video / Sequence Subset 🎬 Companion to yxma/gelsight-mini-pretrain. Where the main repo treats every kept frame as an independent image, this repo preserves temporal sequences — one row per frame, ordered, with explicit sequence-id + position metadata, for video tactile pretraining. Why this repo The main repo's pipeline applies perceptual-hash dedupe within each capture to drop near-identical adjacent frames. That's great for image-level… See the full description on the dataset page: https://huggingface.co/datasets/yxma/gelsight-mini-pretrain-video.
GelSight touch vision cc-by-4.0
gelsight-mini-pretrain-nc
yxma
GelSight Mini Pretrain · Non-Commercial Extension ⚠️ Non-commercial use only. This repository is licensed CC-BY-NC-4.0 because it includes upstream sources whose licenses restrict commercial use. For commercial-friendly Mini tactile data, see the main yxma/gelsight-mini-pretrain repo (CC-BY-4.0). This dataset is the CC-BY-NC extension of yxma/gelsight-mini-pretrain. It contains only the GelSight Mini sources whose upstream licenses are not compatible with CC-BY-4.0 aggregation.… See the full description on the dataset page: https://huggingface.co/datasets/yxma/gelsight-mini-pretrain-nc.
GelSight touch vision cc-by-nc-4.0
gelsight-mini-pretrain
yxma
GelSight Mini Pretrain ~853K GelSight Mini tactile RGB frames, 12 public sources, one parquet schema. Built for self-supervised representation learning (VAE / MAE / SimCLR / DINO) — every frame contact-filtered, channel-normalized, and re-encoded as JPEG q92. Frames Sources Real 536K FoTA (labeled+unlabeled), 3DCal, FEATS, GelSLAM, TactileTracking, RTM, FeelAnyForce, UniT, TacQuad Sim 317K sim_tactile_mnist, sim_starstruck (Taxim-rendered, Mini-calibrated) NC… See the full description on the dataset page: https://huggingface.co/datasets/yxma/gelsight-mini-pretrain.
GelSight touch vision cc-by-4.0
piper-stack-act-tactile-v0
axiboai
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": null, "total_episodes": 400, "total_frames": 223894, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 50, "splits": { "train": "0:400" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/axiboai/piper-stack-act-tactile-v0.
touch vision apache-2.0
so101-tactile-pick-place-v1_20260514_211037
Jingyi-Z
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "fps": 30, "features": { "action": { "dtype": "float32", "names": [ "shoulder_pan.pos", "shoulder_lift.pos", "elbow_flex.pos", "wrist_flex.pos", "wrist_roll.pos", "gripper.pos" ], "shape": [ 6… See the full description on the dataset page: https://huggingface.co/datasets/Jingyi-Z/so101-tactile-pick-place-v1_20260514_211037.
touch vision apache-2.0
tactile-mnist-touch-syn-single-t32-320x240
anonymous-submission-hf
Documentation is available at https://github.com/[REDACTED]/tactile-mnist/blob/main/doc/datasets.md#touch-datasets.
GelSight touch vision cc-by-4.0
tactile-mnist-touch-real-single-t256-320x240
anonymous-submission-hf
Documentation is available at https://github.com/[REDACTED]/tactile-mnist/blob/main/doc/datasets.md#touch-datasets.
GelSight touch vision cc-by-4.0
bimanual-yam-tactile-vision-demo
hcisbmm
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "bi_yam_follower", "total_episodes": 2, "total_frames": 1406, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:2" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/hcisbmm/bimanual-yam-tactile-vision-demo.
touch vision apache-2.0
bimanual-yam-tactile-demo
hcisbmm
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "bi_yam_follower", "total_episodes": 2, "total_frames": 1348, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:2" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/hcisbmm/bimanual-yam-tactile-demo.
touch vision apache-2.0
empty_can_depth_tactile
eunjuri
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v2.1", "robot_type": "Unitree_G1_Inspire", "total_episodes": 82, "total_frames": 30756, "total_tasks": 1, "total_videos": 164, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:82" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/eunjuri/empty_can_depth_tactile.
touch vision depth apache-2.0
baseball_depth_tactile
eunjuri
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v2.1", "robot_type": "Unitree_G1_Inspire", "total_episodes": 85, "total_frames": 20075, "total_tasks": 1, "total_videos": 170, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:85" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/eunjuri/baseball_depth_tactile.
touch vision depth apache-2.0
tactile_test_tube_pyflexitac
Tna001
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so100_tactile_follower", "total_episodes": 64, "total_frames": 75041, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:64" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet"… See the full description on the dataset page: https://huggingface.co/datasets/Tna001/tactile_test_tube_pyflexitac.
touch vision apache-2.0
Awesome-Dexterous-Manipulation
chang-xinhai
A curated awesome list for dexterous robot manipulation, tactile sensing, dexterous hands, robot learning, datasets, benchmarks, and simulators.
touch mit
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so100_tactile_follower", "total_episodes": 86, "total_frames": 103541, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:86" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet"… See the full description on the dataset page: https://huggingface.co/datasets/WT-MM/lerobot_tactile.
touch vision apache-2.0
PromptFusionNet_dataset
Xie, Yuzhen
Self-made Tri-Modal Dataset. This dataset provides visual, tactile, and textual recordings collected from a robotic grasping platform to support research on multi-modal perception, robot grasping, and task-guided manipulation. It integrates RGB-D visual data, high-resolution tactile force data, and natural language instructions, enabling studies in perception-driven manipulation, cross-modal learning, and robust object recognition under manufacturing uncertainties. The dataset was collected to validate the proposed tri-modal fusion method described in our paper. It is publicly available to pr…
touch vision force cc-by-4.0
tactile_peg_hole_new
Tna001
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so100_tactile_follower", "total_episodes": 100, "total_frames": 14910, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 10, "splits": { "train": "0:100" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet"… See the full description on the dataset page: https://huggingface.co/datasets/Tna001/tactile_peg_hole_new.
touch vision apache-2.0
demo-interactive-tactile-manipulation-dataset
DelbyIntelligence
No description provided upstream.
touch
pick_place_tactile
dishantpatel1207
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "Unitree_G1_Inspire_2cam", "total_episodes": 217, "total_frames": 115245, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:217" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/dishantpatel1207/pick_place_tactile.
touch vision apache-2.0
3588_camera_full_tactile
Xense
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "mock_robot", "total_episodes": 1, "total_frames": 301, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 30, "splits": { "train": "0:1" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet", "video_path":… See the full description on the dataset page: https://huggingface.co/datasets/Xense/3588_camera_full_tactile.
touch vision apache-2.0
This dataset was created using LeRobot. Dataset Structure meta/info.json: { "codebase_version": "v3.0", "robot_type": "so100_tactile_follower", "total_episodes": 200, "total_frames": 45044, "total_tasks": 1, "chunks_size": 1000, "data_files_size_in_mb": 100, "video_files_size_in_mb": 200, "fps": 10, "splits": { "train": "0:200" }, "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet"… See the full description on the dataset page: https://huggingface.co/datasets/Tna001/tactile_tube_200.
touch vision apache-2.0