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”
Figure 7 from: Hardy H, van Walsum M, Livermore L, Walton S (2020) Research and development in robotics with potential to automate handling of biological collections. Research Ideas and Outcomes 6: e61366. https://doi.org/10.3897/rio.6.e61366
Figure 7 The CultLab3D conveyor belt and automated imaging system (© CultLab3D).
Complete Data Set for the Master Thesis: Acceptance of Robotics in Tourism
<p>Data Set for the Master Thesis <i>Acceptance of Robotics</i> reseached and written by Elena Schiffmann. </p><p>Use only with permission. </p>
Robot-mediated asymmetric connection between humans can improve performance without increasing effort
Open the record for dataset details and reuse information.
Raw data for the article: Impact of Liver Cirrhosis, Severity of Cirrhosis, and Portal Hypertension on the Difficulty and Outcomes of Laparoscopic and Robotic Major Liver Resections for Primary Liver Malignancies
<p><strong>Background: </strong>Minimally invasive liver resections (MILR) offer potential benefits such as reduced blood loss and morbidity compared with open liver resections. Several studies have suggested that the impact of cirrhosis differs according to the extent and complexity of resection. Our aim was to investigate the impact of cirrhosis on the difficulty and outcomes of MILR, focusing on major hepatectomies.</p> <p><strong>Methods: </strong>A total of 2534 patients undergoing minimally invasive major hepatectomies (MIMH) for primary malignancies across 58 centers worldwide were retrospectively reviewed. Propensity score (PSM) and coarsened exact matching (CEM) were used to compare patients with and without cirrhosis.</p> <p><strong>Results: </strong>A total of 1353 patients (53%) had no cirrhosis, 1065 (42%) had Child-Pugh A and 116 (4%) had Child-Pugh B cirrhosis. Matched comparison between non-cirrhotics vs Child-Pugh A cirrhosis demonstrated comparable blood loss. However, after PSM, postoperative morbidity and length of hospitalization was significantly greater in Child-Pugh A cirrhosis, but these were not statistically significant with CEM. Comparison between Child-Pugh A and Child-Pugh B cirrhosis demonstrated the latter had significantly higher transfusion rates and longer hospitalization after PSM, but not after CEM. Comparison of patients with cirrhosis of all grades with and without portal hypertension demonstrated no significant difference in all major perioperative outcomes after PSM and CEM.</p> <p><strong>Conclusions: </strong>The presence and severity of cirrhosis affected the difficulty and impacted the outcomes of MIMH, resulting in higher blood transfusion rates, increased postoperative morbidity, and longer hospitalization in patients with more advanced cirrhosis. As such, future difficulty scoring systems for MIMH should incorporate liver cirrhosis and its severity as variables.</p>
Video Experiments - Agile Visual Programming of a Multi-Robot Cyber-Physical System with Operator Interaction
<p>Video of the experimental comparison between the classical VEROSIM programming approach, the newly introduced Agent Services Plugin, and the Scratch Visual Programming method described in the paper "Agile Visual Programming of a Multi-Robot Cyber-Physical System with Operator Interaction".</p>
Water strider robot
<p>S1 - A water-walking robot capable of moving forward and turning</p> <p>S2 - A real water strider's locomotion</p>
smallSSD: The Small Robot Company's detection dataset for agriculture
<p>The Small Robot Company's detection dataset for agriculture, consisting of images collected by the Tom robot labelled with bounding boxes to delineate wheat and weeds.</p> <p>This data is shared under a <a href="https://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial-4.0 International</a> license.</p> <p>More information about this data is available at <a href="https://github.com/SmallRobotCompany/smallssd">https://github.com/SmallRobotCompany/smallssd</a>.</p>
Supporting information for MSc thesis titled Reprogrammable Soft Robotics based on Compliant Microfluidic Fabrication Technique, Imerial College London
<p>The videos are proveided as supporting information as part of the thesis titled <em>Reprogrammable Soft Robotics based on Compliant Microfluidic Fabrication Technique </em>in MSc programme in Department of Materials, Imperial College London. </p>
A 3UPS/S Spherical Parallel Manipulator Designed for Robot Assisted Hand Rehabilitation after Stroke
<p><span>Hand dysfunction is a common symptom in stroke patients. This paper presents a r<span>obot</span>ic device which assists rehabilitation process in order to reduce the need of physical therapy, i.e., a <span>3UPS/S parallel robot</span>ic device is employed for repetitive robot-assisted rehabilitation. Euler angle representation was used to solve the robot's inverse kinematics. The robot's joint space and rotational workspace are determined for two scenarios. In the first scenario, the workspace is obtained considering the actuator’s stroke limitations, while in the second scenario, the workspace is determined by adding a second condition, i.e. the range of motion of the spherical joints. Singularity analysis is performed using geometric algebra approach. The robot was manufactured using additive manufacturing technology. The solution of the inverse kinematic problem is employed to control the robot. The robot can perform full range of motion during wrist ulnar deviation and radial deviation motions, with the exception of limited wrist flexion and extension motions. The robot has singular configurations within its workspace. Although the spherical joints have roles in reducing the workspace, the primary causes are actuator selection, radiuses of base and moving platforms and the length of the central leg. These factors can be considered to improve the workspace. Singularity can be avoided by carefully selecting the rotation of the moving platform about Z-axis and avoiding same leg lengths.</span></p>
EchoPT: A Pretrained Transformer Architecture for Predicting 2D In-Air Sonar Images in Mobile Robotics
<h1>EchoGPT</h1> <p>This folder contains the supplementary data and code for the submission "EchoPT: A Pretrained Transformer Architecture for Predicting 2D In-Air Sonar Images in Mobile Robotics" to the NeurIPS 2024 conference.</p> <h2>Dependencies</h2> <p>Matlab 2024a or higher is needed with the following toolboxes:</p> <ul> <li>Image Processing Toolbox</li> <li>Parallel Computing Toolbox</li> <li>Deep Learning Toolbox</li> <li>Signal Processing Toolbox</li> <li>System Identification Toolbox</li> </ul> <h2>Data</h2> <h3>Simulation</h3> <p>This folder contains the saved sonar images (energyscapes) as well as the motion data for each frame from a particular simulation run (LongRun1). These are saved into batches and saved as compressed .mat files within the <em>\DataCalculated\SimulationData\LongRun1\Raw</em> folder.</p> <h3>Trained model</h3> <p>The model used in the experiments of this submission is saved in <em>\DataCalculated\Networks</em> as a Matlab dlnetwork object. There is a trained (with weights) and an untrained version available.</p> <h2>Code</h2> <h3>Data pre-processing</h3> <p>To extract the data from the batch .mat files into seperate frames a script <strong>preprocessEchoPT.m</strong> is available in the main folder. This will save these individual frames once again to individual .mat files into a folder <em>\DataCalculated\ESSequences</em> by default.</p> <h3>Training</h3> <p>To train the model a Matlab script <strong>trainEchoPT.m</strong> is provided.</p> <h3>Evaluation</h3> <p>To generate the figures of the submission as well as additional outputs such as GIFs three different evaluation scripts are available:</p> <ul> <li><strong>evaluateEchoPT.m</strong>: Evaluate the trained model on the dataset.</li> <li><strong>evaluateEchoPT_ComparisonAccFlow_ARLoop.m</strong>: Evaluate the trained model on the dataset and compare it to acoustic flow with autoregressive prediction.</li> <li><strong>evaluateEchoPT_ComparisonAccFlow_NoAR.m</strong>: Evaluate the trained model on the dataset and compare it to acoustic flow without autoregressive prediction.</li> </ul> <h3>Source</h3> <p>Within the folder <em>\Source</em> all additional Matlab functions and classes can be found.</p> <h2>Open-Source libraries included in this project</h2> <ul> <li>Progress bar by HyunGwang Cho <a href="https://www.mathworks.com/matlabcentral/fileexchange/121363-progress-bar-cli-gui-parfor?s_tid=srchtitle">(link)</a></li> </ul>
Implementation of Inverse Model Policy based on KineNN in Physical Robot for Pick and Place Scenario
<p>Inverse Model Policy based on KineNN was trained in a simulation. After that, the policy is evaluated with the physical robot. The policy is used to drive the robot to specific target such as: Pick Position, Safe Pick Position, Place Position, Safe Place Position. </p>
Sensor data from multi-robot formation
<p>ROSbag data from a multi-robot formation experiment at the UF REEF, Shalimar, FL, USA.</p>
Speaking with Robots in Noisy Environments
<p>The dataset contains training, validation and test data used for training the StoRM and DFNet 3 models for speech enhancement along with a README file on how to use this dataset to reproduce the enhancement and word error rate results presented in the paper "Speaking with Robots in Noisy Environments" at HRI, 2025. </p>
Robot Motion Dataset
<p>The Robot Motion Dataset contains experimental data from a study investigating human-robot interaction with a leader who used a teleoperated follower robot. So, thirty participants controlled the TFR wearing a virtual reality (VR) headset and using a rudder platform. Thus, the dataset includes sensor data such as accelerometer, gyroscope, trajectory, objects' distance, data questionnaires, and so forth. </p> <p>The dataset is used in the work presented in the following articles:</p> <ul> <li>Di Tecco, A., Genua, A., Serra, F., Camardella, C., Loconsole, C., Ragusa, E., ... & Frisoli, A. (2025, February). Evaluation of a Haptic-Actuated Glove for Remote Human-Robot Interaction (HRI): A Proof of Concept. In European Robotics Forum (pp. 213-219). Cham: Springer Nature Switzerland.</li> <li>Di Tecco, A., Frisoli, A., Loconsole, C. (2025, August). Machine Learning for Predicting User Satisfaction in Human-Robot Interaction (HRI) Teleoperation Tasks. In IEEE ACCESS. </li> </ul>
Video - Agile Visual Programming of a Multi-Robot Cyber-Physical System with Operator Interaction
<p>Video of the assembly sequence described in the paper "Agile Visual Programming of a Multi-Robot Cyber-Physical System with Operator Interaction".</p>
Training Skills in Minimally Invasive, Robotic and Open Surgery: Brain Activation as an Opportunity for Learning
<p>The advantages of the robotic approach in surgery are undisputed. However, during surgical training, how this technique influences the learning curve has not been described. We provide a tentative model for analyzing the learning curves associated with observation and active participation in learning different surgical techniques, using functional imaging. Forty medical students were enrolled and assigned to 4 groups who underwent training in robotic (ROB), laparoscopic (LAP), or open (OPEN) surgery, and a control group that performed motor training without surgical instruments. Surgical/motor training included six 1-h sessions completed over 6 days of the same week. All subjects underwent functional magnetic resonance imaging (fMRI) scanning sessions, before and after surgical training during. Twenty-three participants completed the study. The 3 surgical groups exhibited different learning curves during training. The main effects of the day of training (<em>p</em> < 0.01) and the group (<em>p</em> < 0.01) as well as a significant interaction of day of training group (<em>p</em> < 0.01) were observed. The performance increased in the first 4 days, reaching a peak at day 4, when all groups were considered together. The OPEN group showed the best performance compared to all other groups (<em>p</em> < 0.04). The OPEN group showed a rapid improvement in performance, which peaked at day 4 and decreased on the last day. Similarly, the LAP group showed a steady increase in the number of exercises they completed, which continued for the entire training period and reached a peak on the last day. However, the participants training in ROB surgery, after a performance initially indistinguishable from that of the LAP group, had a dip in their performance, quickly followed by an improvement and reaching a plateau on day 4. fMRI analysis documented the different involvement of the cortical and subcortical areas based on the type of training. Surgical training modified the activation of some brain regions during both observation and the execution of tasks. Differences in the learning curves of the 3 surgical groups were noted. Functional brain activity represents an interesting starting point to guide training programs.</p>
Obstacle avoidance function of the rolling and jumping robot
<p>Obstacle avoidance function of the rolling and jumping robot</p>
Figure 3 from: Seibt J, Vestergaard C (2018) Fair Proxy Communication: Using Social Robots to Modify the Mechanisms of Implicit Social Cognition. Research Ideas and Outcomes 4: e31827. https://doi.org/10.3897/rio.4.e31827
Figure 3 The Telenoid robot created by Hiroshi Ishiguro, ATR Hiroshi Ishiguro Lab, Japan.
Full Data Set for the Paper: An Evaluation of Open Source Trajectory Planners for Robotic Manipulators with Focus on Human-Robot Collaboration
<p>This data sets contain the full evaluation data for the paper "An Evaluation of Open Source Trajectory Planners for Robotic Manipulators with Focus on Human-Robot Collaboration".</p>
Robot Solid dispensing_200mg
<p><strong>YuMi_one_disp_real_time_front: </strong>Full dispensing cycle for a solid (carbon black, 200 mg target weight) recorded in 4 K, shown in normal speed (front view) </p> <p><strong>YuMi_one_disp_real_time_side: </strong>Full dispensing cycle for a solid (carbon black, 200 mg target weight) recorded in 4 K, shown in normal speed (side view) </p> <p><strong>YuMi_intercut_real_time_4K: </strong>Full dispensing cycle for a solid (carbon black, 200 mg target weight) recorded in 4 K, shown in normal speed (3 separate dispenses, intercut). This video is an intercut montage and shows close ups and different camera angles; because it was recorded with a single camera, the video is a combination of three separate dispensing operations. For single, uncut video of a dispensing cycle, see YuMi_one_disp_real_time_front<strong> </strong>and YuMi_one_disp_real_time_side.</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.