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.
2,639
datasets available to search
ShareScore release 0.9.0
Dataset results
2,639 results for “Robotic”
REFLEX Dataset: A Multimodal Dataset of Human Reactions to Robotic Failures and Subsequent Robotic Explanations.
<p>REFLEX Dataset is a comprehensive collection of multimodal Human Behavioral reactions to Robot Failures and Explanations. <br><br>The version 1.0 is a representative sample of this dataset with the reactions from 5 users out of a total 55 users.</p> <p>This version 1.1.0 is the full dataset with the reactions from a total 55 users.<br><br>Please refer to the Readme in the zipped file for further information.</p> <p><br>This data was recorded from a user study and has been processed for anonymization.</p> <h2>About Data</h2> <p>This description gives a detailed process on how the data was collected. It should describe the conditions under which the data was recorded and also the devices used to record the data.</p> <h3>Data Organisation</h3> <p>The data is structured by strategy and participant, as shown below:</p> <pre><code>Strategy Dir/ -Participant Dir/ - analysis - questonnaire - facetorch - openface - gaze - hume - body - voice - time - video_cam1 - video_cam2 </code></pre> <p>We employed five different strategies (C1, C2, C3, D1, D2), collecting data from 11 participants for each strategy. The data for each participant is organized within a corresponding folder.</p> <p>Participants are labeled based on their assigned strategy. For example, data from the first participant under the “Fixed Low” (C1) strategy can be found in the C1-1 subfolder within the C1 directory.</p> <h3>Collected Data</h3> <p>Each participant folder contains various datasets related to different modalities. All visual data are collected using the camera 1 video. The collected data are outlined below:</p> <ul> <li> <p><strong>Anonymized Videos</strong> (<code>video_cam1.mp4</code>, <code>video_cam2.mp4</code>) - Visual Representation:</p> <ul> <li>Video from camera 1 (robot side of view)</li> <li>Video from camera 2 (experiment side of view)</li> </ul> </li> <li> <p><strong>Analysis</strong> (<code>analysis.csv</code>) - Failure Instance Description:</p> <ul> <li>Failure type</li> <li>Explanation strategy</li> <li>Explanation level</li> <li>Phase (Pre, Failure, Explanation, Resolution)</li> <li>Start/End frame and time of failure</li> <li>Task Resolved</li> </ul> </li> <li> <p><strong>Questionnaire</strong> (<code>questionnaire.csv</code>) - Failure Instance Description:</p> <ul> <li>Participant Data (Age, Gender, etc)</li> <li>Answers of explanation-satisfaction rate question for rounds and overall experiment</li> </ul> </li> <li> <p><strong>Facetorch</strong> (<code>facetorch.csv</code>) - <a href="https://github.com/tomas-gajarsky/facetorch" target="_blank" rel="nofollow noopener">Facetorch</a> - Face:</p> <ul> <li>Arousal/Valence levels</li> <li>Presence of Facial Action Units (AUs)</li> <li>Dominant Emotion (Out of six basic emotions and neutral)</li> </ul> </li> <li> <p><strong>OpenFace</strong> (<code>openface.csv</code>) - <a href="https://github.com/TadasBaltrusaitis/OpenFace" target="_blank" rel="nofollow noopener">OpenFace</a> - Face, Gaze, Head:</p> <ul> <li>Eye Gaze (2D and 3D Landmarks)</li> <li>Eye Direction (vector and in radians)</li> <li>Head Pose Estimation (Pose Estimation, Rotation)</li> <li>Face Landmarks (2D and 3D Landmarks)</li> <li>Facial Action Units (0.0-1.0 intensity scores, occurrences)</li> </ul> </li> <li> <p><strong>Gaze</strong> (<code>gaze.csv</code>) - Gaze:</p> <ul> <li>Eye Gaze Classification (e.g., Robot, Task, Miscellaneous)</li> </ul> </li> <li> <p><strong>Hume</strong> (<code>hume.csv</code>) - <a href="https://www.hume.ai/" target="_blank" rel="nofollow noopener">Hume Expression Measurement API</a> - Face:</p> <ul> <li>48 Emotion likelihoods</li> <li>Facial Action Units (0.0-1.0 score)</li> <li>Facial Descriptions (0.0-1.0 score)</li> </ul> </li> <li> <p><strong>Voice</strong> (<code>speech.csv</code>) - <a href="https://www.hume.ai/" target="_blank" rel="nofollow noopener">Hume Expression Measurement API</a> - Speech:</p> <ul> <li>Speech conversation data</li> <li>Emotional likelihoods inferred from prosody</li> </ul> </li> <li> <p><strong>Body</strong> (<code>body.csv</code>) - <a href="https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker" target="_blank" rel="nofollow noopener">MediaPipe Pose Landmark Detection</a> - Body:</p> <ul> <li>Pose classifications (e.g., crossed arms, arms behind back)</li> <li>2D and 3D Pose Landmarks</li> </ul> </li> <li> <p><strong>Time</strong> (<code>time.csv</code>) - <a href="https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker" target="_blank" rel="nofollow noopener">MediaPipe Pose Landmark Detection</a>:</p> <ul> <li>Associated timestamp and time for each frame of camera 1 video.</li> </ul> </li> </ul> <p>Notes</p> <ul> <li>Data was synchronized based on the `video_cam1.mp4`</li> <li>The `hume.csv` and `gaze.csv` files contain data only for frames within failure periods.</li> <li>Failure events were divided into four phases:<br> 1. Pre-failure phase: Period before the failure occurs<br> 2. Failure phase: When the actual failure action takes place<br> 3. Explanation phase: When the robot provides an explanation for the failure<br> 4. Resolution phase: When the robot guides the participant to resolve the issue</li> </ul> <h2>How to Visualize Participant Data</h2> <p>Please visit the github repository: https://github.com/andreasnaoum/reflex-viz</p>
AI4EU Robotics Pilot: Vibration sensor measurements in a robotic pump
<p>The robotic pump demonstrator represents a hydraulic pump that can be mounted on an industrial robot, for example, to pump liquid paint for spray painting. On this pump, one accelerometer is mounted for vibration monitoring and recording.</p> <p>The pump can be controlled in terms of speed (rotations per minute, rpm), affecting the throughput of paint and the pressure in and out of the pump.</p> <p>The dataset consists of 380 million measurements of several sensor data of the pump system in 1-second intervals over two months in 2020. The data is split by the recording date over 33 files.</p>
AI4EU Robotics Pilot: Vibration sensor measurements in a robotic wrist
<p>The robotic wrist demonstrator represents a mechanical wrist with three axes that can hold tools, e.g. for spray painting in combination with a pump. On this robotic wrist, two accelerometers are mounted for vibration monitoring and recording: one in the movable front part of the wrist and one in the shaft. The wrist can be controlled through the torque or the designated position of each axis’ motor.</p> <p>The dataset consists of 1.8 billion measurements of several sensor data of the robotic wrist in 1-second intervals over six months in 2020. The data is split by the recording date over 98 files.</p>
Dataset for: An experimental comparison of anomaly detection methods for collaborative robot manipulators
<p>The dataset contains data recordings from a UR5e robot during normal and anomalous operation and is recorded to support the authors Master thesis project and the associated Paper: <em>"An Experimental Comparison of Anomaly Detection Methods for Collaborative Robot Manipulators" </em>(inProceeding).</p> <p>An in-depth description of the dataset can be found in the pdf uploaded with the dataset and an example of a data loader is also provided.</p>
Replication Package for ROSDiscover: Statically Detecting Run-Time Architecture Misconfigurations in Robotics Systems
<p><strong>Replication Package for ROSDiscover: Statically Detecting Run-Time Architecture Misconfigurations in Robotics Systems</strong></p> <p>This is the replication package for the paper, ROSDiscover: Statically Detecting Run-Time Architecture Misconfigurations in Robotics Systems, which has been accepted at the International Conference on Software Architecture (ICSA), 2021. A preprint of the paper is included in this replication package (paper.pdf).</p> <p>This artifact is archived on Zenodo with the following DOI: <a href="https://doi.org/10.5281/zenodo.5834633">https://doi.org/10.5281/zenodo.5834633</a></p> <p>The study associated with this artifact was carried out by the following investigators:</p> <ul> <li><a href="http://christimperley.co.uk">Christopher S. Timperley</a> (Carnegie Mellon University)</li> <li><a href="https://tobiasduerschmid.github.io">Tobias Dürschmid</a> (Carnegie Mellon University)</li> <li><a href="https://www.cs.cmu.edu/~schmerl">Bradley Schmerl</a> (Carnegie Mellon University)</li> <li><a href="http://www.cs.cmu.edu/~garlan">David Garlan</a> (Carnegie Mellon University)</li> <li><a href="https://clairelegoues.com">Claire Le Goues</a> (Carnegie Mellon University)</li> </ul> <p>If you have any questions regarding the research or the replication package, you should contact Christopher, Tobias, or Bradley.</p> <p><strong>Abstract</strong></p> <p>Robot systems are growing in importance and complexity. Ecosystems for robot software, such as the Robot Operating System (ROS), provide libraries of reusable software components that can be configured and composed into larger systems. To support compositionality, ROS uses late binding and architecture configuration via “launch files” that describe how to initialize the components in a system. However, late binding often leads to systems failing silently due to misconfiguration, for example by misrouting or dropping messages entirely.</p> <p>In this paper we present ROSDiscover, which statically recovers the run-time architecture of ROS systems to find such architecture misconfiguration bugs. First, ROSDiscover constructs component level architectural models (ports, parameters) from source code. Second, architecture configuration files are analyzed to compose the system from these component models and derive the connections in the system. Finally, the reconstructed architecture is checked against architectural rules described in first-order logic to identify potential misconfigurations.</p> <p>We present an evaluation of ROSDiscover on real world, off-the-shelf robotic systems, measuring the accuracy, effectiveness, and practicality of our approach. To that end, we collected the first data set of architecture configuration bugs in ROS from popular open-source systems and measure how effective our approach is for detecting configuration bugs in that set.</p>
Human-robot co-manipulation of soft materials: enable a robot manual guidance using a depth map feedback [Dataset]
<p>Dataset used for the paper submitted to RO-MAN 2022</p> <p>Human-robot co-manipulation of soft materials: enable a robot manual guidance using a depth map feedback<br> Giorgio Nicola, Enrico Villagrossi, Nicola Pedrocchi</p>
The effects of robotic assistance on upper limb spatial muscle synergies in healthy people during planar upper-limb training
<p>This is the minimal dataset underlying the paper:</p> <p>"The effects of robotic assistance on upper limb spatial muscle synergies in healthy people during planar upper-limb training"</p>
Magnetic Soft Robotic Bladder for Assisted Urination
<p>The poor contractility of the detrusor muscle in underactive bladders (UABs) fails to increase the pressure inside the UAB, leading to strenuous and incomplete urination. However, existing therapeutic strategies by modulating/repairing detrusor muscles, e.g., neurostimulation and regenerative medicine, still have low efficacy and/or adverse effects. Here, we present an implantable magnetic soft robotic bladder (MRB) that can directly apply mechanical compression to the UAB to assist urination. Composed of a biocompatible elastomer composite with optimized magnetic domains, the MRB enables on-demand contraction of the UAB when actuated by magnetic fields. A representative MRB for an UAB in a porcine model is demonstrated and MRB-assisted urination is validated by in situ computed tomography imaging after 14-day implantation. The urodynamic tests show a series of successful urination with a high pressure increase and fast urine flow. Our work paves the way for developing MRB to assist urination for humans with UABs.</p>
Dataset on Force Myography for Human Robot Interactions
<p>Force myography (FMG) is a contemporary, non-invasive, wearable technology that can read the underlying muscle volumetric changes during muscle contractions and expansions. The FMG technique can be used in recognizing human applied hand forces during physical human robot interactions (pHRI) via data-driven models. Several FMG-based pHRI studies were conducted in 1D, 2D and 3D during dynamic interactions between a human participant and a robot to realize human applied forces in intended directions during certain tasks. Raw FMG signals were collected via 16-channel (forearm) and 32-channel (forearm and upper arm) FMG bands while interacting with a biaxial stage (linear robot) and a serial manipulator (Kuka robot). In this paper, we present the datasets and their structures, the pHRI environments, and the collaborative tasks performed during the studies. We believe these datasets can be useful in future studies on FMG biosignal-based pHRI control design.</p> <p>The full description of this dataset, it’s components and structure are available in the data descriptor article submitted in MDPI Data. Please cite the following data descriptor article if you are using this open-access dataset for legitimate scientific research:</p> <p> U. Zakia, and C. Menon. Dataset on Force Myography for Human Robot Interactions. Data 2022, vol., no., pp, <a href="https://doi.org/10.3390/data7040050">doi:</a> (submitted on June 2022).</p> <p> </p>
A fluidic relaxation oscillator for reprogrammable sequential actuation in soft robots
<p>This dataset contains data and code to replicate main and supplemental figures for the related article published in Matter:</p> <p>Title: A fluidic relaxation oscillator for reprogrammable sequential actuation in soft robots</p> <p>DOI: 10.1016/j.matt.2022.06.002</p> <p>In the article we introduce a simple and compact soft valve with intentional hysteresis, analogous to an electronic relaxation oscillator. By integrating the valve with a soft actuator, we transform a continuous inflow to cyclic activation. Importantly, we show that our circuits can activate up to five actuators in various sequences, and that we can physically reprogram the activation order by varying the (initial) conditions in the fluidic circuit. Moreover, we show the feasibility of our approach under more realistic conditions by building a four-legged robot.</p> <p>This dataset contains measurement data and simulation files.</p> <p>The data are recorded (in human-readable format) from experiments on our fluidic circuits (e.g., pressure, flow data), and are accompanied by MATLAB scripts for data processing as well as generating figures.</p> <p>The simulation files are MATLAB and LTspice files for simulating our fluidic circuits making use of the analogy with electronic circuits. For more involved parameter sweeps we generate, run, and post-process LTspice input and result files using MATLAB. More details and instruction for use are provided in the included readme.txt files.</p>
Parents' Evaluation of Interaction between Robots and Children with Neurodevelopmental Disorders
<p>This presentation concerns the paper:</p> <p>Andreeva, A., Lekova, A., Simonska, M., Tanev, T. (2022). Parents’ Evaluation of Interaction Between Robots and Children with Neurodevelopmental Disorders. In: Uskov, V.L., Howlett, R.J., Jain, L.C. (eds) Smart Education and e-Learning - Smart Pedagogy. SEEL-22 2022. Smart Innovation, Systems and Technologies, vol 305. Springer.</p> <p>It presents the evaluation of child-robot interaction in play-like structured speech and language therapy for children with neurodevelopmental disorders. It is organized like a group session. Participants are a speech and language therapist, a child and two robots that assist the therapeutic session: the humanoid robot NAO and its “friend” the emotion-expressive robot EMOSAN. Two engineers who developed and deployed the technical scenarios observe the process and control the robots. Researchers developed an online questionnaire for evaluation of interaction between the child and the robots. Parents of involved children with neurodevelopmental disorders stay in the room and they observe the robot-assisted session. Results show that children are interested in playing and learning with robots. There is a correlation between the type of children’s neurodevelopmental disorder and the use of verbal communication in interaction. According to parents’ answers of the questionnaire, most of the children liked to interact with robots during the play-like structured activities in the speech and language therapy session.</p>
Robots for Microfarms (ROMI) - Farmers Dashboard Video - D3.4
<p><strong>The following video shows the functionalities and usage of the Farmer’s Dashboard developed within the Robots for Microfarms (ROMI) project funded by EU Grant 773875</strong></p> <p><em>You can also watch it on <a href="https://www.youtube.com/channel/UCT55o32SE30a8pTu-chatTA/videos">Youtube</a></em></p> <p><strong>Video content:</strong></p> <ul> <li><em>Farmers Dashboard Summary.mp4</em></li> <li><em>Tell me more - a deeper dive into the Cablebot.mp4</em></li> <li><em>Tell me more - a deeper dive into the Farmers Dashboard.mp4</em></li> </ul> <p> </p> <p><strong>Videos summary:</strong></p> <p><br> The Farmer’s Dashboard is a farming tool that provides daily automated insights about your crops. It helps with mapping of crop bed, the location and identification of individual plants, and the extraction of their growth curves from the collected data. </p> <p>The dashboard benefits polycrop farmers and researchers. It opens-up technology and practices common to industrial-scale agriculture, making them accessible and useful to ecological and sustainable farmers.</p> <p>It relies on an automated system for data acquisition, a set of tools for image analytics, and finally, an online platform for spatial management and data visualization. The data can be provided by different types of devices: a cablebot, a drone or a rover according to the configuration of each farm. </p> <p>The Cable Bot can be fixed above a crop bed using a tensioned cable, which is especially easy using a polytunnel. We can use the manual remote to correctly position the camera, to capture all of the crops. Once set up, the Cable Bot will move multiple times a day across the crop bed, taking high definition images and sending them to a ROMI server. The images are assembled into a unique portrait of your crop bed. After plants are detected, a catalogue of individual plants is created. By comparing them with historical data, we can obtain plant growth curves. All of the information is then combined into a weed map which is made available on the Farmers Dashboard website.</p> <p>Because of the legal restrictions on the use of drones and because of the rapid evolution of the drone market, the ROMI project has decided to direct its effort to a hardware solution that complements the existing tools: the Cablebot. Multiple iterations were needed to achieve a powerful yet robust and low-cost solution. The current system is a fully automated imaging device able to collect data on a high variety of crops. </p> <p>The first iteration of the software focuses on the mapping of crop rows, the location and identification of individual plants, and the extraction of their growth curves from the collected data. </p> <p>The rover is available as an Open Source project. All of the source code and plans are freely available. That allows us to improve the design over time using input from farmers and engineers. That is also why we made the design modular using components that can be found “off-the-shelf” or that can be produced using 3D printers and laser cutters. People with development skills can also contribute. Our software is available online on Github. That makes the Romi Farmers Dashboard an excellent platform to experiment with innovative tools for farming.</p>
Data set: Quantifying the Accuracy of Collaborative IoT and Robot Sensing in Indoor Settings of Rigid Objects
<p>This is the data set accompanying the paper "Quantifying the Accuracy of Collaborative IoT and Robot Sensing in Indoor Settings of Rigid Objects" by Sune L. Sørensen and Mikkel Baun Kjærgaard. Please refer to the paper for a description of the hardware used to record the data and how it is recorded.</p> <p>It consists of the following files:</p> <p><em>IoT camera images</em>: RBG images, named img_aa_bbb_0.jpg, where aa is the setup ID, bb is the camera ID (101, 102, 103 or 104).</p> <p><em>Robot RGB images</em>: RBG images, named aa0.png where aa is the setup ID.</p> <p><em>Robot point clouds</em>: pcd-files, named aa0.pcd where aa is the setup ID.</p> <p>The transformation from the IoT coordinate system to the robot coordinate system is:</p> <p>robotTiot = np.array([[0.914428, 0.134934, -0.378832, 3.76475],</p> <p>[0.393661, -0.49845, 0.772371, 0.791051],</p> <p>[-0.0846896, -0.855336, -0.509056, 2.37154],</p> <p>[0.0, 0.0, 0.0, 1.0]])</p> <p>Example, tranforming a pose in IoT coordinates to robot coordinates: p_rob = robotTiot * p_iot</p>
Biomimetic robotic skin implemented with hydrogel-elastomer hybrids and tomographic imaging methods
<p>Human skin perceives physical stimuli applied to the body and mitigates the risk of physical interaction through its soft and resilient mechanical properties. Social robots would benefit from whole-body robotic skin (or tactile sensors) resembling human skin in realizing a safe, intuitive, and contact-rich interaction with humans. However, existing soft tactile sensors show several drawbacks (complex structure, poor scalability, and fragility), which limit their application in whole-body robotic skin. Here, we introduce biomimetic robotic skin based on hydrogel-elastomer hybrids and tomographic imaging. The developed skin consists of tough hydrogel and silicone elastomer forming a skin-inspired multilayer structure, achieving sufficient softness and resilience for protection. The sensor structure can also be easily repaired with adhesives even after severe damage (incision). For multimodal tactile sensation, electrodes and microphones are deployed in the sensor structure to measure local resistance changes and vibration due to touch. The ionic hydrogel layer is deformed due to an external force, and the resulting local conductivity changes are measured via electrodes. The microphones also detect the vibration generated from touch to determine the location and type of dynamic tactile stimuli. The measurement data are then converted into multimodal tactile information through tomographic imaging and deep neural networks. We further implement a sensorized cosmetic prosthesis, demonstrating that our design could be used to implement deformable or complex-shaped robotic skin.</p>
CT Dataset associated with the paper: (PLOSONE) Modular robotic platform for precision neurosurgery with a bio-inspired needle: system overview and first in-vivo deployment
<p>Imaging dataset associated with the work entitled "Modular robotic platform for precision neurosurgery with a bio-inspired needle: system overview and first in-vivo deployment.", published in the journal PLOS ONE</p>
Imperial Robotics Lab- Lake Vrana Freshwater Dataset
<p>Raw bird diversity data and soundscape index data extracted from acoustic data and used for the analysis of acoustic diversity and bird diversity. R scripts are included for PCA , bird composition and soundscape analysis.</p>
Micro-wear data from robotic use-wear experiments on force
<p>This data is the result of highly controlled experiments investigating the influence of force and duration on lithic micro-wear using a robot arm. Its targeted application is in archaeology and anthropology on the study of human tool use in the prehistory. The data consists of three zip files of html reports containing experimental data together with the microscopic images, and MATLAB scripts of the analysis methods. The images were collected at different stages of the experiment using a focus variation microscope, which produces true-color as well as topographic images. </p>
Figure 5. Forward walking image sequence-Design and Implementation of an Autonomous Humanoid Robot Based on Fuzzy Rule-Based Motion Controller
<p>The behavior module determines the target position and orientation according to the results<br> of localization and the sensor measurements, and then constructs an action series which consists of<br> the elementary gaits to realize omni directional walking. The implementation of forward walking is<br> applying Virtual Slope Walking in the sagittal plane with the Lateral Swing Movement for lateral<br> stability. The sideward walking and turning is realized by carefully designing the key frames. All of<br> above gait is generated by connecting the key frames with smooth sinusoids. The forward walking<br> speed of PERSIA Humanoid Robot is 25cm/s. The image sequences of forward walking are shown<br> in Figure 5.</p>
Figure 2. Mechanical construction of the PERSIA humanoid robots-Design and Implementation of an Autonomous Humanoid Robot Based on Fuzzy Rule-Based Motion Controller
<p>Figure 2 shows one of the constructions used for our robots. Knee joints are considered to<br> bend in both directions which help faster response of the robot in backward walking. Efforts have<br> been made to hold the proportions as much as possible human like. The PERSIA robot is 38cm tall<br> and weighs about 1.6 kg. It has 18 degrees of freedom: 5 in each leg, 3 in each hand and 2 in head.<br> To facilitate exchange of the players, all robots use mechanically the same structure.</p>
Figure 4. (a)Our Humanoid soccer robot, (b) Overview of the Control System-Design and Implementation of an Autonomous Humanoid Robot Based on Fuzzy Rule-Based Motion Controller
<p>Figure 4 shows the block diagram of the software which runs in the robot’s main processor.<br> The program consists of 4 main blocks:<br> • Hardware Interface: Contains all low level routines to access hardware of the robot including<br> sensors and actuators.<br> • Vision: Contains image processing algorithms such as recognition of landmarks and other<br> object. Self localization is done using particle filtering. Particles are scored by comparing a<br> simulated image from each particle with the current frame captured by camera. Using<br> “Sampling-Importance Resampling” method, a new distribution of the particles is created after<br> each step.<br> Particles are also updated using a motion model. Final distribution of the particles converges to<br> the real pose of the robot.<br> • Planning: Planning system of the robot is based on a multi layer, and multi thread structure.<br> The layers are named Strategy, Role, Behavior and Motion. Each layer contains a Scenario<br> which runs in parallel with the scenarios in the other layers. A scenario in a higher level can<br> terminate and change the scenario running in the lower level; however it is usually done in<br> synchronization with the lower level scenario to avoid conflicts and instabilities. (Such as<br> stopping the walking motion while one of the feet is still in the air).<br> • Network: Mainly responsible for the wireless communication of the robot with the other robots<br> or the referee box. This is done via WLAN.<br> • Motion Control: manages all the actuators of the robot, and controls locomotion or any other<br> action of the robot according to the requests from Cognition.<br> • Sensor Control: manages other sensors, and interacts with the Sub-Controller.</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.