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”
Attitudes toward artificial intelligence and robots in healthcare in the general population: a qualitative study
<p>It is an extract of the transcripts of in-depth interviews used for the preparation of the paper titled "The perception of facilitators and barriers to the use of e-health solutions in Poland: a qualitative study"</p> <p>This research was funded in whole by the National Centre of Science, Poland within the project titled "Determinanty akceptacji i gotowości wykorzystania aplikacji e-zdrowia i technologii Zdrowia 4.0 w polskim społeczeństwie" (Grant No 2021/43/B/NZ7/02140). </p> <p>For the purpose of Open Access, the author has applied a CC-BY public copyright license to any Author Accepted Manuscript (AAM) version arising from this submission.</p>
Supplementary data for "Crawling, Climbing, Perching, and Flying by FiBa Soft Robots"
<p>Supplementary Information for paper "Crawling, climbing, perching, and flying by FiBa soft robots". <a href="https://doi-org.ezp-prod1.hul.harvard.edu/10.1126/scirobotics.adk4533">DOI: 10.1126/scirobotics.adk4533</a> </p>
Bimanual Robot Arm Cloth Manipulation Dataset
<p>This dataset contains 945 trials of a bimanual robot arm setup, where one arm holds a piece of cloth (e.g., a towel) by one corner while the other arm, equipped with a wrist-mounted camera, captures images from approximately 180 different angles by making a half-circle motion around the cloth. Each trial includes images and the corresponding TCP (Tool Center Point) poses of the second arm. Additionally, the dataset provides annotated positions of the two corners adjacent to the held corner, which are critical for unfolding the cloth by grasping these points. This dataset is valuable for research in robotic manipulation, computer vision, and cloth handling tasks.</p>
Tuta Absoluta Robotic Traps Dataset
<p>This dataset focuses on enabling Tuta absoluta detection, necessitated annotated images. It was created as part of the H2020 PestNu project (No. 101037128) using the SpyFly AI-robotic trap from Agrorobotica. The SpyFly trap features a color camera (Svpro 13MP, sensor: Sony 1/3” IMX214) with a resolution of 3840 × 2880 for high-quality image capture. The camera was positioned 15 cm from the glue-paper to capture the entire adhesive board. In Total 217 images were captured.</p> <p>Expert agronomists annotated the images using Roboflow, labeling a total of 6787 T. absoluta insects, averaging 62.26 annotations per image. Images without insects were excluded, resulting in 109 annotated images, one per day.</p> <p>The dataset was split into training and validation subsets with an 80–20% ratio, leading to 87 images for training and 22 for validation. The dataset is organized into two main folders: “<em>0_captured_dataset</em>" contains the original 217 .jpg images. "<em>1_annotated_dataset</em>" includes the images and the annotated data, split into separate subfolders for training and validation. The Tuta absoluta count in each subset can be seen in the following table:</p> <table> <tbody> <tr> <td><strong>Set</strong></td> <td><strong>Images</strong></td> <td><strong>Tuta Absoluta Instances</strong></td> </tr> <tr> <td>Training</td> <td>87</td> <td>5344</td> </tr> <tr> <td>Validation</td> <td>22</td> <td>1443</td> </tr> <tr> <td>Total</td> <td>109</td> <td>6787</td> </tr> </tbody> </table>
Adaptive Online Fault Diagnosis in Robot Swarms
<p>Contained are the data sets generated and analysed for the paper 'Adaptive Online Fault Diagnosis in Robot Swarms' by James O'Keeffe, Danesh Tarapore, Alan G. Millard and Jon Timmis</p>
Self-Organised Braiding on Mobile Thymio Robots Experiment Videos
<p>Self-organised braiding without any global control was implemented on mobile Thymio robots. The videos of the final experiments are provided here. Each experiment type was recorded three times: braiding with four, six, and eight robots and removing two from six robots.</p>
ERL Service Robot Competition Dataset FBM1 and FBM2 (Lisbon 2017 Tournament)
<p>Dataset for ERL Service Robot Competition (Major competition in Lisbon 2017)</p> <p>FBM1:Object Perception and FBM2:Navigation Functionality benchmarks.</p> <p>Log files are in Rosbag format and include two files per trial of the benchmark:</p> <p>1) Internal Robot data (information logged by the robot such as onboard sensors and control commands)</p> <p>2) RSBB data (Information From the Referee box that contains benchmark related information as well as the ground truth data measured by motion capture system)</p> <p> </p>
European Robotics League Consumer - Lisbon 2019 contest - FBM 2 - Navigation functionality
<p>Benchmark logs for the FBM2 benchmark: navigation functionality.</p> <p>ERL Consumer competition in Lisbon.</p>
European Robotics League Consumer - Lisbon 2019 contest - SocRob team's files for task benchmarks
<p>Internal log files of the robot used by SocRob's team (from Instituto Superior Técnico) for the 4 Task Benchmarks performed at the ERL Consumer Lisbon 2019 contest.</p>
The behaviour of commercial broilers in response to a mobile robot - Behavioural dataset
<p>The data files associated with the paper titled 'The behaviour of commercial broilers in response to a mobile robot'.</p> <p> </p>
Plasticity in Collective Decision-Making for Robots: Creating Global Reference Frames, Detecting Dynamic Environments, and Preventing Lock-ins
<p>Swarm robots operate as autonomous agents and a swarm as a whole gets autonomous by its capability of collective decision-making.<br> Despite intensive research on models of<br> collective decision-making, the implementation in multi-robot systems is still challenging.<br> Here, we advance the state of the art by introducing more plasticity to the decision-making process and by increasing the task difficulty.<br> Most studies on large-scale multi-robot decision-making are limited to one instance of an iterated exploration-dissemination phase followed by successful and permanent convergence.<br> We investigate a dynamic environment that requires constant collective monitoring of option qualities.<br> Once a significant change in qualities is detected by the swarm, it has to collectively reconsider its previous decision accordingly.<br> This is only possible by preventing lock-ins, a global consensus state of no return.<br> In addition, we introduce a task of increased difficulty as the robots must locate themselves to assess the quality of an option.<br> Using local communication, swarm robots propagate hop-count information throughout the swarm to form a global reference frame.<br> We successfully validate our implementation in many swarm robot experiments concerning robustness to disruptions of the reference frame, scalability, and adaptivity to a dynamic environment.</p>
Towards ice core sampling by subsea robotic vehicles: Electronic supplement - Video from Coring Trials
<p>This video provides recordings of trials where a subsea manipulator arm was used for ice core sampling. </p> <p>It is a electronic supplement to "Towards ice core sampling by subsea robotic vehicles" by C. Katlein.</p> <p>The first coring system is a open source in-house built corer Thomsen et al. 2020:</p> <p>Steffen Thomsen, Mads Holm Hansen, Jeppe Pinholt Lillethorup, Frederik Sebastian Tirsgaard, Adam Flytkjær, Claus Melvad, Søren Rysgaard, Daniel F. Carlson,<br>An affordable and miniature ice coring drill for rapid acquisition of small iceberg samples, HardwareX, Volume 7, 2020, e00101, ISSN 2468-0672, https://doi.org/10.1016/j.ohx.2020.e00101.</p> <p>design files are available at <a href="https://www.sciencedirect.com/science/article/pii/S2468067220300109" target="_blank" rel="noopener">https://www.sciencedirect.com/science/article/pii/S2468067220300109</a> </p> <p>The second coring system is a Kovacs Mark II <a href="https://kovacsicedrillingequipment.com/coring-systems/coring-systems/">https://kovacsicedrillingequipment.com/coring-systems/coring-systems/</a> </p>
When monkeys meet an ANYmal robot in the wild
<p>Data and script used to analyse data for the study: "When monkeys meet an ANYmal robot in the wild"</p>
Adaptive planning for assistive-care robotic missions - use case 1
<p>Videos of scenarios A and B from Use Case 1 (UC1), recreated in a digital environment using the <a href="https://gazebosim.org/home">Gazebo</a> simulator and our adaptive path-finding framework.</p>
Validation of the pelvic attachment mechanism of NIMBLE, an ambulatory user support gait rehabilitation robot.
<p>Description of the project<br><span><span>NIMBLE project aims to design and validate a novel gait rehabilitation robot. The objective of the robot is to provide ambulatory, body-weight supported walking training assisting user's limbs and its center of mass. The NIMBLE robot is comprised by a robotic frame, a lower limb exoskeleton, and a exoskeleton-frame coupling mechatronics that allows to assist the user's center of mass.</span></span></p> <p>Description of the dataset<br><span><span>This dataset contains the results of an experiment conducted to assess the alteration on walking kinematics due to the mechatronic device coupling the frame and the exoskeleton.</span></span></p> <p>--------------------------<br>METHODOLOGY<br>--------------------------<br>1. Methodology<br>The walking kinematics were recorded and analyzed at slow (0.5 m/s) and normal (1 m/s) speeds under three different conditions: unrestricted walking, walking while wearing the Exo-H3 corset, and walking while wearing the Exo-H3 corset coupled to the robotic frame. Only the corset is worn, to isolate and evaluate the direct impact of the designed mechanism without the kinematic restrictions imposed by the exoskeleton. This approach ensures that the effects observed are solely attributable to the mechanism itself, avoiding any confounding influences from the exoskeleton. This approach allows the evaluation of the influence of the exoskeleton corset, as it is a required component to secure the user to the robotic frame, and a comparison of its impact with that of the robotic frame. For this purpose, joint angles and their maximum and minimum values and ranges of motion (ROM) are analyzed in both the sagittal and frontal planes, along with the step width and the displacement of the CoM in the vertical and horizontal directions.</p> <p>2. Software<br>Data were collected using Kinovea and then processed and analyzed using Matlab.</p> <p>--------------------------<br>FILES<br>--------------------------<br>1. Files <br>One ".m" file is included. For each subject (idX), three subfolders are found:<br>- Calib folder: it contains the initial position and angular value of the markers and angles analyzed.<br>- frontal folder: for both speeds and the three analyzed conditions (Unrestricted walking CL, wearing the corset CC, and attached to the robotic frame CML), it contains the raw data, filtered data, segmented data normalized by gait cycles, mean and standard deviation data of those segmented cycles, and normalized data using the initial value from Calib file, for every marker position in the frontal plane (ankle, knee, hip and center of mass). Also, segmented, mean and deviations are presented from angular values in the frontal plane (right and left hip abduction and pelvic list).<br>- sagittal folder: for both speeds and the three analyzed conditions (Unrestricted walking CL, wearing the corset CC, and attached to the robotic frame CML), it contains the raw data, filtered data, segmented data normalized by gait cycles, mean and standard deviation data of those segmented cycles, and normalized data using the initial value from Calib file, for every marker position in the sagittal plane (hip, knee, ankle and toe tip). Also, segmented, mean and deviations are presented from angular values in the frontal plane (hip, knee and ankle flexo-extension).</p> <p>In addition, one average folder (media) includes average data for the statistical analysis. Signals subfolder includes all segmented data from the previous variables for every speed and conditions, joining the data from every subject in one table, a total of 50 samples (10 segmented cycles x 5 subjects). Value subfolder includes maximum, minimum and ranges of motion of angular variables. Every variable has 50 rows (10 segmented cycles x 5 subjects) and 3 columns (CL, CC, and CML conditions). Also mean step width is presented, as the distance between ankle markers in the frontal plane.</p> <p>--------------------------<br>OTHERS<br>--------------------------<br>1. Data dictionary<br>speed05: data collected at 0.5 m/s<br>speed1: data collected at 1 m/s<br>CL: Unrestricted walking condition<br>CC: Wearing the corset condition<br>CML: Attached to the robotic frame condition<br>R: right leg<br>L: left leg<br>x: horizontal direction<br>y: vertical direction<br>ANKLE, KNEE, HIP, COM: ankle, knee, hip, and virtual center of mass markers in the frontal plane.<br>HIP_lat, KNEE_lat, ANKLE_lat and TOE_lat: hip, knee, ankle, and toe tip markers in the sagittal plane.<br>Abd: hip abduction angle.<br>Hip_Angle, Knee_Angle, Ankle_Angle: hip, knee, and ankle flexo-extension angles.</p> <p>--------------------------<br>SPONSORSHIP INFORMATION AND GRANT IDs<br>--------------------------<br>1. Grant Information<br>This work is part of the R&D project PID2021-123657OB-C32, funded by MCIN/ AEI/10.13039/501100011033/ and by “ERDF A way of making Europe”.</p>
STEM CO-EDUCATIONAL ENVIRONMENTS COMBINING EDUCATIONAL ROBOTICS AND COMPUTATIONAL THINKING
<h1><span>AMBIENTES COEDUCATIVOS STEM QUE COMBINAN ROBÓTICA EDUCATIVA Y PENSAMIENTO COMPUTACIONAL </span></h1> <p><span> </span></p> <p><strong><span>STEM CO-EDUCATIONAL ENVIRONMENTS COMBINING EDUCATIONAL ROBOTICS AND COMPUTATIONAL THINKING</span></strong></p> <p> </p> <p> </p> <p> </p> <p><span>Resumen en español </span></p> <p><span>El presente artículo de investigación se enfoca en abordar las desigualdades de género en el ámbito educativo, especialmente en las disciplinas STEM, mediante el uso de la robótica educativa y el pensamiento computacional. Para ello se realiza una revisión sistemática de literatura, con el objetivo de analizar tendencias, desafíos y oportunidades en la implementación de estas estrategias en Colombia y su impacto en el cierre de brechas de género. Aunque no se encontró una revisión que sintetice la evidencia de estos temas de manera conjunta, el estudio actual busca llenar ese vacío y contribuir a intervenciones educativas futuras más equitativas.</span></p> <p><span>Palabras clave (en español): </span><span>Educación STEM, Robótica educativa, Pensamiento computacional, Brechas de género, Vocaciones científicas</span><span>.</span><span> </span></p> <p>Resumen en inglés</p> <p><span>This research article focuses on addressing gender inequalities in education, especially in STEM disciplines, through the use of educational robotics and computational thinking. To this end, a systematic literature review is conducted, with the aim of analyzing trends, challenges and opportunities in the implementation of these strategies in Colombia and their impact on closing gender gaps. Although no review was found that synthesizes the evidence on these topics together, the current study seeks to fill this gap and contribute to more equitable future educational interventions.</span></p> <p><span>Palabras clave (en inglés): STEM education, educational robotics, Computational thinking, Gender gaps, Scientific vocations. </span></p>
Robust CBF-based STL motion planning for socially responsible robot navigation in the presence of measurement noise
<p>Video of submitted paper entitled "Robust CBF-based STL motion planning for socially responsible robot navigation in the presence of measurement noise"</p>
Replication Package for: "How do Workers Adjust to Robots? Evidence from China"
<p>Replication Package for:</p> <p> "How do Workers Adjust to Robots? Evidence from China"</p> <p>Osea Giuntella, Yi Lu, Tianyi Wang</p> <p>10.5281/zenodo.13760908</p>
Synthetic Multimodal Dataset using MuJoCo: UR5 Robot Motion
<p>Using the Mujoco environment, we simulated robot trajectory and transitions from one formation<br> to another. Mujoco is a 3D simulator, while Gym serves as an interface to the UR5 robot.<br> The robot has measurement units that allow the acquisition of the angles, positions,<br> and quaternions of the joints and the position of the end-effector. The robot is located on<br> a table with 4 cameras all from the same radius to the center of the robot just<br> rotated by 90° for each of them. Using the described environment, we collected 1999 samples <br> at a rate of 10 samples per second.<br> <br> ################################################################<br> ################################################################<br> <br> camera views:</p> <p> id: 0<br> name: 'camera_0'<br> xmat: array([ 0.70710678, 0.42537261, -0.56485232, -0.70710678, 0.42537261,<br> -0.56485232, 0. , 0.79882181, 0.60156772])<br> xpos: array([-2., -2., 3.])</p> <p> id: 1<br> name: 'camera_1'<br> xmat: array([-0.70710678, 0.42537261, -0.56485232, -0.70710678, -0.42537261,<br> 0.56485232, 0. , 0.79882181, 0.60156772])<br> xpos: array([-2., 2., 3.])</p> <p> id: 2<br> name: 'camera_2'<br> xmat: array([ 0.70710678, -0.42537261, 0.56485232, 0.70710678, 0.42537261,<br> -0.56485232, -0. , 0.79882181, 0.60156772])<br> xpos: array([ 2., -2., 3.])</p> <p> id: 3<br> name: 'camera_3'<br> xmat: array([-0.70710678, -0.42537261, 0.56485232, 0.70710678, -0.42537261,<br> 0.56485232, 0. , 0.79882181, 0.60156772])<br> xpos: array([2., 2., 3.])</p> <p> <br> <br> The camera data is stored as .png files with a size of 256x256 </p> <p><br> <br> ################################################################<br> ################################################################<br> <br> The files angles.pt, angular_velocity.pt, angular_acceleration.pt contains information about<br> the motor data of the joints. The angles, velocity, acceleration is the information about the <br> Motor in each joint in following order:<br> ['base_to_lik', 'base_to_rik', 'elbow_joint', 'shoulder_lift_joint', 'shoulder_pan_joint', 'wrist_1_joint', 'wrist_2_joint', 'wrist_3_joint']<br> <br> <br> ################################################################<br> ################################################################<br> <br> The files pose.pt and quaternion.pt contains information about<br> the body data of the robot. The pose of each element is in following order:<br> ['base', 'base_link', 'box_2_link', 'box_link', 'drop_box', 'ee_link', 'forearm_link', 'left_inner_finger', 'left_inner_knuckle', 'right_inner_finger', 'right_inner_knuckle', 'robotiq_85_base_link', 'shoulder_link', 'upper_arm_link', 'world', 'wrist_1_link', 'wrist_2_link', 'wrist_3_link']<br> <br> <br> ################################################################<br> ################################################################<br> <br> The file action.pt contains information about the used action in the corresponding time-step. <br> The action of each element is in following order:<br> ['forearm_T', 'gripper_motor', 'shoulder_lift_T', 'shoulder_pan_T', 'wrist_1_T', 'wrist_2_T', 'wrist_3_T']<br> <br> </p>
Synthetic Multimodal Dataset using ABB Studio: Single Robot Welding Station
<p>## README</p> <p>### Overview</p> <p>This repository provides the setup and data collected from simulations conducted in RobotStudio for various ABB robot configurations. The simulation, based on Löppenberg et al. (2024), was designed to capture precise sensory data in a controlled environment that mirrors real-world welding conditions.</p> <p>### Simulation Setup</p> <p>The simulation tracks essential parameters of the ABB robot and its end-effector, including:<br>- **Joint Angles**: Real-time angles for each joint.<br>- **TCP Position**: 3D positional coordinates of the Tool Center Point.<br>- **TCP Orientation**: Orientation captured as quaternions to represent rotational states.<br>- **Additional Attributes**: Various other robot-specific details relevant to performance in a welding setup.</p> <p>### Data Collection</p> <p>To generate a high-resolution dataset, data were sampled at intervals between 12 ms and 96 ms. This detailed sampling provides accurate insights into the robot's operation in a simulated welding environment.</p> <p>### Key Parameters</p> <p>The dataset includes the following parameters:</p> <p>- **Camera View**: One camera view with a resolution of 3 x 256 x 256, normalized to the range [0, 1].<br>- **Motor Power (P)**: The power consumed by the robot’s motors, constrained within \([0, P_{\text{max}}]\).<br>- **TCP Speed (v_TCP)**: The velocity of the end-effector, with a maximum cap of 5 m/s.<br>- **TCP Acceleration (a_TCP)**: The acceleration of the TCP, bounded within \([a_{\text{min}}, a_{\text{max}}]\).<br>- **TCP Orientation (q_TCP)**: Quaternion representing orientation, with a normalization condition \(||\mathbf{q}_{\text{TCP}}(t)|| = 1\).<br>- **TCP Position (p_TCP)**: A 3D vector for positional coordinates, with each coordinate constrained within \([p_{\text{min}}, p_{\text{max}}]\).<br>- **Braking Distance (d_brake)**: The distance each joint travels during braking, within bounds \([d_{\text{min}}, d_{\text{max}}]\).<br>- **Holding Position (θ_hold)**: The maintained angles for each joint, constrained to the interval \([-π, π]\).<br>- **Joint Angles (θ)**: The current angles of each joint, also within the interval \([-π, π]\).</p> <p>Frame '02655_frame' is corrupted. That means the corresponding values of the other modality needs to be removed as well.</p> <p><br>### Citation</p> <p>For more details on the simulation methodology, please refer to:<br>- Löppenberg, M., Yuwono, S., Diprasetya, M. R., & Schwung, A. (2024). Dynamic robot routing optimization: State-space decomposition for operations research-informed reinforcement learning. Robotics and Computer-Integrated Manufacturing, 90, 102812.</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.