Touch and Go
University of Michigan / CMU
Human-collected egocentric video and GelSight readings from touching objects in natural environments.
CC BY 4.0; download from the official page.
Find original papers, datasets, code and technical documentation.
Choose data for your task, then check its origin, modalities and terms.
Vision, touch and contact measurements
DATASET INDEXHardware demonstrations, actions and simulation
DATASET INDEXBlade imagery, industrial surfaces and concrete cracks
Entries link to original access instructions. Collections can overlap with their constituent datasets; general anomaly benchmarks do not replace damage validation on actual equipment.
University of Michigan / CMU
Human-collected egocentric video and GelSight readings from touching objects in natural environments.
CC BY 4.0; download from the official page.
MIT CSAIL
Synchronised visual and tactile sequences of robot contact with everyday objects, for cross-modal prediction.
See the author page and repository for access; verify terms in the original files.
Stanford Vision and Learning Lab and collaborators
Meshes, videos, impact sounds and tactile measurements for 100 real objects.
Use the official ObjectFolder-Real download; follow the source terms.
Stanford Vision and Learning Lab and collaborators
Implicit representations of 1,000 objects queried by viewpoint, impact location and contact conditions.
Download and query the models following project instructions; distinguish them from measured touch.
Open X-Embodiment Collaboration
A collection of robot-manipulation datasets with a common format, dataset inventory and RT-X research.
Terms vary by constituent dataset. Separate BridgeData and RH20T entries provide details, not additional independent volume.
DROID Dataset Team
Multi-scene Franka manipulation trajectories, with language annotations, camera calibration and a data visualiser.
The official page supplies Colab and cloud-data paths; check terms for data, code and supplementary annotations.
UC Berkeley RAIL and collaborators
Teleoperated and scripted trajectories spanning pick-and-place, doors, cloth folding and sweeping.
Collection modes have separate downloads; portions also appear in Open X-Embodiment.
Shanghai Jiao Tong University
Contact-rich robot sequences paired with human demonstrations, multi-view vision, force, audio and actions.
RH20T-C and RH20T-NC have different licences; fingertip touch is limited to Cfg. 7. Google Drive and Baidu links are provided.
Lifelong Robot Learning collaborators
Teleoperated demonstrations in controlled simulated tasks for studying transfer of spatial, object and goal knowledge.
Download scripts are in the official repository; these are simulated data. See the repository licence.
Stanford / UT Austin and collaborators
An index of real and simulated manipulation demonstrations, with download, preprocessing and training interfaces.
This is a dataset index; download each subset and check its source, format and terms.
NVIDIA
NVIDIA’s cross-embodiment simulated manipulation data for GR00T-related training and research.
The data card specifies CC BY 4.0. Use the official files and check embodiment and format for the version.
Zilong Zhang and collaborators
Single-blade images (AeBAD-S) and blade videos (AeBAD-V) for anomaly detection under changes in illumination, view and scale.
Data: CC BY 4.0. The source repository links Google Drive and Tianyi downloads. Distinguish engineered specimen defects from in-service damage.
Mohammed Eltoum and collaborators
Synthetic turbine-blade renders covering normal, dent, nick, scratch and corrosion classes, with defect segmentation masks.
The original record is on Figshare; generation files and scripts are in the author repository. Check the dataset-record licence.
MVTec Software
Normal and anomalous industrial object and texture images, with pixel-level defect annotations.
CC BY-NC-SA 4.0; access through the official form. Non-commercial use.
MVTec Software
More demanding backgrounds and illumination conditions, with public and hidden-annotation test splits.
CC BY-NC-SA 4.0; the hidden-annotation split is evaluated by the official server.
MVTec Software
Object-surface scans acquired with an industrial 3D sensor for anomaly detection and localisation.
CC BY-NC-SA 4.0; data and evaluation code are linked from the official page.
Amazon Science
Visual anomaly data for PCBs and everyday objects, including scratches, dents and missing components.
Data: CC BY 4.0; code: Apache 2.0. Download and splits are in the official repository.
Utah State University
Cracked and non-cracked concrete deck, wall and pavement images, including shadows and surface clutter.
CC BY 4.0; image-level classification labels, not pixel-level crack segmentation.
Wyss Institute at Harvard University
Wyss Institute, 2018 · Science Robotics
NASA Jet Propulsion Laboratory
NASA/JPL · robotics project and field-test records
Yu Sun, Heng Ren, Jiajia Ning, Qingkai Guo, Xuefeng Chen, Shaojiang Dong, Laihao Yang
IEEE Robotics and Automation Letters
Qingkai Guo, Yu Sun, Yunbo Wang, Zipan Zhao, Changfeng Nan, Shaojiang Dong, Laihao Yang, Xuefeng Chen
International Journal of Mechanical Sciences
Stanford University research team
Stanford Engineering · 2017 research report
MIT News · research by Yoonho Kim and collaborators
MIT · 2019 research report
Rolls-Royce / University of Nottingham
Innovate UK Business Connect, 2020, pp. 142–143
Tony G. Chen, Julia Di, Stephanie Newdick, Mathieu Lapotre, Marco Pavone, Mark R. Cutkosky
IEEE ICRA Workshop on Field Robotics, 2024 · arXiv:2405.15005
Giovanni Pittiglio, James H. Chandler, Tomas da Veiga et al.
Communications Engineering 2, 50
Wyss Institute at Harvard University · research report
Wyss Institute · 2020
Julian Whitman, Nico Zevallos, Matt Travers, Howie Choset
Carnegie Mellon University · 2018 publication
MIT News · research by Shuhei Miyashita and collaborators
MIT / CSAIL · 2016 research report
Renee Zhao and collaborators · Stanford University
Stanford Engineering · 2022 research report
Zheshuai Yang, Laihao Yang, Yu Sun, Xuefeng Chen
IEEE Transactions on Robotics
Ling Wang, Yu Sun, Laihao Yang, Yuxuan Sun, Qingkai Guo, Yixue Liu, Xuefeng Chen, Yajing Shen
Science Advances
Qingkai Guo, Yu Sun, Tianxiang Zhang, Shiyu Xie, Xuefeng Chen, Zhuang Zhang, Hanqing Jiang, Laihao Yang
Advanced Science
Boston Dynamics / National Grid
Boston Dynamics · customer case
ANYbotics / BASF
ANYbotics · 2023 field tests
Yufeng Chi et al. · UC Berkeley
RSS 2025
Tairan He et al. · NVIDIA / CMU and collaborators
ICRA 2025
NVIDIA GR00T research team
NVIDIA · 2025 research release
Google DeepMind
Vision-language-action and on-device models; access follows the official partner or testing programmes.
Physical Intelligence
arXiv · 2024 / openpi
Zipeng Fu, Tony Z. Zhao, Chelsea Finn · Stanford
CoRL 2024
OpenLoong / Gewu Playground
Reinforcement learning, imitation learning and simulation examples; see repository licence
Linqi Ye et al.
arXiv preprint · 2503.05146
NVIDIA
Robot foundation models, training and inference code; check weight licences separately.
NVIDIA / Isaac Sim
A robotics-learning and simulation framework; dependencies and assets have separate licences.
Physical Intelligence
Robot policy models, checkpoints and fine-tuning examples; check code and model terms.
Hugging Face
Tools for robot data collection, training and deployment; hardware support is documented separately.
Hybrid Robotics · UC Berkeley
Humanoid hardware files, control software and assembly documentation; licences vary by file type.
Tesla
Official technical overview and demonstrations; a reusable full open-source system was not verified.
Boston Dynamics
Public SDK, APIs and examples; not the complete hardware design or low-level control stack.
Google DeepMind
Spatial understanding and multi-step planning, available through the Gemini API or AI Studio; motor execution is handed to a lower-level model or control system.
arXiv · Haitham El-Hussieny
Preprint · simulation · v1 · 2026-11-06
NEURA Robotics · 官方公告 / official announcement
Partnership · planned pilot · 2026-11-05
arXiv · Duo Tang 等 / et al.
Preprint · simulation and hardware · v1 · 2026-11-04
arXiv · Sourav Selvaraj 等 / et al.
Preprint · hardware experiments · v1 · 2026-11-04
arXiv · Ella Walsh、Eric Diller、Jessica Burgner-Kahrs
Preprint · proof of concept · v1 · 2026-10-29
arXiv · Jiahe Wang 等 / et al.
Preprint · hardware closed-loop control · v1 · 2026-10-28
TEPCO · 东京电力
Official update · field work · Vol.60 · 2026-10-25
深圳环水集团 · 招标采购数字管理平台
Procurement result · R&D · 采购结果公告 · 2026-10-14
arXiv · Yunti Xu 等 / et al.
Preprint · platform experiments · v1 · 2026-10-14
No matching sources. Adjust the filters.