Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
10
datasets available to search
ShareScore release 0.9.0
Dataset results
10 results for “iCub”
sim2real-iCub
<ul> <li>24000 camera images (with 12000 mask) from iCub simulation and real robot (at Imperial College London).</li> <li>a subset of real robot images (2000 image) in "_tiny" folders</li> </ul>
sim2real-iCub-iit
<p>Camera images (with mask) from iCub simulation and real robot (at Istituto Italiano di Tecnologia, Italy).</p> <ul> <li>4220 synthetic simulation images for training</li> <li>4220 synthetic simulation images for testing</li> <li>2000 real images for training</li> <li>2000 real images for testing</li> </ul>
sim2real-iCub-iit2
<p>Camera images (with mask) from iCub simulation and real robot (at Istituto Italiano di Tecnologia, Italy).</p> <ul> <li>4220 synthetic simulation images for training</li> <li>4220 synthetic simulation images for testing</li> <li>2239 real images for training</li> <li>2239 real images for testing</li> </ul>
iCub Joint Space Self-Collision Avoidance [Data & Code]
<p>These data files containg code sources for dataset creation & model learning (Joint-Space-SCA.zip) and collected synthetic dataset of free & collided postures for humanoid robot iCub (raw_binary_data.zip). Follow the Readme.MD files to launch the code if needed.</p><p>Corresponding Git repo: https://github.com/epfl-lasa/Joint-Space-SCA</p><p> </p>
iCube data visually impaired
<p>Here, I report the codebook of the dataset for the variable names that are harder to interpret:</p> <p><strong>group</strong>: 'early-blind', 'late-blind' or 'control'</p> <p><strong>main_group</strong>: 'blind' or 'sighted'</p> <p><strong>trial_type</strong>: 'memorize' or 'recall'</p> <p><strong>conf</strong>: the configuration of pins locations used in the specific trial</p> <p><strong>subject_orientation</strong>: oreintation of the subject in absolute coordinates while doing the test (e.g. 'north' if facing North)</p> <p><strong>pin_facet_1</strong>: number of pins in facet 1</p> <p>.</p> <p>.</p> <p><strong>pin_facet_6</strong>: number of pins in facet 6</p> <p><strong>cond_facet_1</strong>: kind of face based on pin number (even or odd)</p> <p>.</p> <p>.</p> <p><strong>cond_facet_6</strong>: kind of face based on pin number (even or odd)</p> <p><strong>correct</strong>: correct response (i.e. 'same' or 'different') for that trial</p> <p><strong>response</strong>: actual response of the subject</p> <p><strong>accuracy</strong>: 1 = correct; 0 = wrong</p> <p><strong>n_tocchi_trial </strong>= number (unfiltered) of active cells of the cube in the whole trial</p> <p><strong>n_tocchi_facet_1 </strong>= number (unfiltered) of active cells in face #1 of the cube in the whole trial</p> <p>.</p> <p>.</p> <p><strong>n_tocchi_facet_6 </strong>= number (unfiltered) of active cells in face #6 of the cube in the whole trial</p> <p><strong>filt_n_tocchi_trial</strong> = number (filtered, i.e., explorative touches only) of active cells of the cube in the whole trial</p> <p><strong>filt_n_tocchi_facet_1</strong> = number (filtered, i.e., explorative touches only) of active cells in face#1 of the cube in the whole trial</p> <p>.</p> <p>.</p> <p><strong>filt_n_tocchi_facet_6</strong> = number (filtered, i.e., explorative touches only) of active cells in face#6 of the cube in the whole trial</p> <p><strong>touch_density_trial</strong> = unfiltered touch frequency (active cells/second) in the whole trial</p> <p><strong>touch_density_facet_1</strong> = unfiltered touch frequency (active cells/second) in face#1 in the whole trial</p> <p>.</p> <p>.</p> <p><strong>touch_density_facet_6</strong> = unfiltered touch frequency (active cells/second) in face#6 in the whole trial</p> <p><strong>filt_touch_density_trial</strong> = filtered (i.e. explorative touches only) touch frequency (active cells/second) in the whole trial</p> <p><strong>filt_touch_density_facet_1</strong> = filtered touch frequency (active cells/second) in face#1 in the whole trial</p> <p>.</p> <p>.</p> <p><strong>filt_touch_density_facet_6</strong> = filtered touch frequency (active cells/second) in face#6 in the whole trial</p> <p><strong>duration_trial</strong> = duration of exploration in s</p> <p><strong>dur_facet_1</strong> = duration of exploration in face#1 in the whole trial</p> <p>.</p> <p>.</p> <p><strong>dur_facet_6</strong> = duration of exploration in face#6 in the whole trial</p> <p><strong>filt_dur_facet_1</strong> = filtered (explorative touches only) duration of exploration in face#1 in the whole trial</p> <p>.</p> <p>.</p> <p><strong>filt_dur_facet_6</strong> = filtered (explorative touches only) duration of exploration in face#6 in the whole trial</p> <p><strong>rot_abs_total</strong> = amount of rotation in deg in the whole trial</p> <p><strong>raw_mean_rot_velocity</strong> = unfiltered rotation velocity (deg/s)</p> <p><strong>filtered_mean_rot_velocity</strong> = filtered (removed rotations < 1deg/s) rotation velocity (deg/s)</p> <p><strong>facce_esplorate_0.8s</strong> = sequence of explored faces</p> <p><strong>orient_face_deg</strong> = faces orientation in spherical coordinates at the beginning of exploration of the faces reported in 'facce_esplorate_0.8s'. All cube faces are considered (i.e. list of 6 couples of coordinates for each initial timepoint of exploration of a face)</p> <p><strong>orient_face_world_coord</strong> = same as above but translated to world labels (e.g. 'north', 'up', 'west', etc.)</p> <p><strong>orient_face_local</strong> = same as above but translated to labels relative to the participants (e.g. 'left', 'down', 'rear'...)</p> <p><strong>timepoints_facce_esplorate_0.8s</strong> = timepoints in s of the beginning of exploration of a face (see 'facce_esplorate_0.8s')</p> <p><strong>mean_delta_timepoints</strong> = mean time to move from one explored face to the next (mean of 'timepoints_facce_esplorate_0.8s')</p> <p><strong>std_delta_timepoints</strong> = standard deviation of 'mean_delta_timepoints'</p> <p><strong>transition_local</strong> = position of explored face (see 'facce_esplorate_0.8s') relative to the participants</p> <p><strong>trans_matrices</strong> = matrices expressing the probability (prop) of moving from one location to another (e.g. from 'front' to 'left')</p> <p><strong>ritorni_0.8s</strong> = number of returns to already explored faces expressed as array (e.g. [0 0 0 2 0 0] = face#4 explored twice)</p> <p><strong>ritorni</strong> = total number of returns to already explored faces for that trial (sum of the array coded in ‘ritorni_0.8s’)</p>
Event-Driven Figure-Ground organisation model for the humanoid robot iCub
<p>Figure-ground organisation is a perceptual grouping mechanism for detecting objects and boundaries, essential for an agent interacting with the environment. Current figure-ground segmentation methods rely on classical computer vision or deep learning, requiring extensive computational resources, especially during training. Inspired by the primate visual system, we developed a bio-inspired perception system for the neuromorphic robot iCub. The model uses a hierarchical, biologically plausible architecture and event-driven vision to distinguish foreground objects from the background. Unlike classical approaches, event-driven cameras reduce data redundancy and computation. The system has been qualitatively and quantitatively assessed in simulations and with event-driven cameras on iCub in various scenarios. It successfully segments items in diverse real-world settings, showing comparable results to its frame-based version on simple stimuli and the Berkeley Segmentation dataset. This model enhances hybrid systems, complementing conventional deep learning models by processing only relevant data in Regions of Interest (ROI), enabling low-latency autonomous robotic applications.</p>
VIT_iCub_Dataset
<p>VIT_iCub_Dataset relative to Submitted Paper (RSOS-230937)</p>
IGBMC ICube LW4-1 : Image and annotations
<p>FIB-SEM cellular (HeLa cells) image with 6 classes segmentation :</p> <ul> <li>Mitochondrion (8 x 40 slices)</li> <li>Endoplasmic reticulum (2 x 40 slices)</li> <li>Nucleus (5 x 40 slices)</li> <li>Cell membrane / Cell filled (8 x 40 slices)</li> <li>Endosome (8 x 40 slices)</li> <li>Golgi apparatus (1 x 40 slices)</li> </ul> <p>Collection date : 05/04/2017<br> Instrument : Auriga 60-46-16<br> Fixation : High pressure frozen, freeze-substituted.<br> Embedding : Lowicryl<br> Coloration : Osmium / Uranyl Acetate<br> <br> Number of slices : 600<br> Pixel spacing x/y (nm) : 7.5</p> <p>Image acquisition : Fabien Alpy<br> Manual segmentation : Mallouh Véronique</p>
IGBMC ICube I3 : Image and annotations
<p>FIB-SEM cellular (HeLa cells) image with 4 classes segmentation :</p> <ul> <li>Mitochondrion (slice 0 to 500)</li> <li>Endoplasmic reticulum (slice 172 to 251)</li> <li>Nucleus (slice 1 to 250)</li> <li>Cell membrane (slice 1 to 250)</li> </ul> <p>Collection date : 18/01/2017<br> Instrument : Auriga 60-46-16<br> Fixation : Chemical fixation at room temperature.<br> Embedding : Lowicryl<br> Coloration : Osmium / Uranyl Acetate<br> <br> Number of slices : 500<br> Pixel spacing x/y (nm) : 5</p> <p>Image acquisition : Spehner Danièle<br> Manual segmentation : Mallouh Véronique</p>
iCub
<p>testing</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.