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.
6
datasets available to search
ShareScore release 0.9.0
Dataset results
6 results for “AEROARMS”
AEROARMS - Image Dataset for the Crawler Indirect Detection through its Cage
<p>Dataset containing images and ground-truth position of the crawler's cage used in the AEROARMS project experiments.</p>
AEROARMS - Crawler Direct Detection Image Dataset
<p>Dataset containing images and ground-truth position of the crawler used in the AEROARMS project experiments.</p>
AEROARMS Control-based local optimization methods for planning
<p>This package allows to perform a Dynamic (Re-)Planning within the Set-Based Task-Priority Inverse-Kinematics (SBTP-IK) framework. It is ROS-based and it is provided to work with the Kinova Jaco2 7DOFs but it is can be easily adapted to another robot system changing the files describing the robot kinematics such as Denvait Hartenberg parameters.</p> <p>The proposed approach is based on merging control-based local optimization methods inside the planning algorithms. For the experiments, a fixed-based 7 DOFs manipulator has been considered in two different scenarios. In the first case, a static environment has been considered. In the second one, the user places an obstacle on the manipulator’s path in real-time. Thus, a re-planning results necessary to manage this change in the environment.</p> <p> </p>
AEROARMS Visual servoing with actively movable camera
<p>This dataset includes a library of elementary behaviours, namely atomic tasks to be assigned to a dual arm aerial manipulator in a priority order. The devised approach, developed within the EU funded research project AEROARMS (AErial RObotic system integrating multiple ARMS and advanced manipulation capabilities for inspection and maintenance) funded by the European Commission under Horizon 2020 Program (grant agreement No. 644271), is based on a set-based inverse kinematics control [1]. For each elementary task the Jacobian matrix and the task function are provided.</p> <p>The code has been developed in C++ under ROS environment and it has been experimentally tested on the AEROARMS dual-arm prototype developed by the University of Seville constituted by an under-actuated multi-rotor with two arms, each of them characterized by 4 DOFs. The total number of DOFs of the system is 12, while the amount of implemented tasks required a total number of 23 DOFs. This is possible since the different tasks are never activated all together but only a subset of them, based on the state of the system. More in detail, the following equality tasks (i.e. tasks characterized by a specific desired value) have been implemented: </p> <p>• Position and orientation trajectory tracking of left arm end-effectors. Such a tasks requires 6 DOFs.</p> <p>• Center of mass, this task is aimed at ensuring that the center of mass of the dual-arm system is, as much as possible, aligned with that of the UAV, in such a way to avoid to destabilize the flight and reduce the power consumption. Such a task requires 1 DOFs.</p> <p>• Field of View of the end effector of the right arm, equipped with a micro camera.</p> <p>As concerns the set-based tasks (i.e. tasks whose desired value is represented by an interval) the following have been implemented:</p> <p>• Joint limits: for each joint, upper and lower limits are set in order to avoid its mechanical limits. Such a task requires 1 DOF for each joint of the arms, thus the total number of required DOFs is 8.</p> <p>• Virtual wall between the two arms: to avoid collisions between the two arms, a virtual wall is implemented in order to delimit their working spaces. Such a task requires 2 DOF.</p> <p>• Virtual wall between the arms and the vehicle: to avoid collisions between the arms and the vehicle, virtual walls are implemented in order to delimit their working spaces. Such a task requires 1 DOF for each arm, thus the total number of required DOFs is 2.</p> <p>• Manipulability, aimed at keeping the manipulators far enough from singular configurations, at which the structure loses mobility. Such a task requires 1 DOF.</p> <p>The equality tasks are always active, while the set-based tasks are active only when the task variable is close to the domain border. The experimental results are reported in the paper:</p> <p>E. Cataldi, F. Real, A. Suarez, P.A. Di Lillo, F. Pierri, G. Antonelli, F. Caccavale, G. Heredia, A. Ollero, Set-based Inverse Kinematics Control of an Anthropomorphic Dual Arm Aerial Manipulator, 2019 IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada.</p> <p>The following data and files are included:</p> <p>• The ROS code: ros_code_set_based.zip, that includes the nodes ros_aeroarms_set_based_seville and lib_multitasks that can be tested in simulation with the simulator V-Rep.</p> <p>• The model of a dual arm aerial manipulator, developed in V-Rep.</p> <p>• The experimental data both in the .mat format for reading with Matlab and in the .bag format for ROS.</p> <p>• The experimental results in ASCII files.</p> <p>[1] S. Moe, G. Antonelli, A. R. Teel, K. Y. Pettersen e J. Schrimpf, «Set-Based Tasks within the Singularity-Robust Multiple Task-Priority Inverse Kinematics Framework: General Formulation, Stability Analysis, and Experimental Results,» Frontiers in Robotics and AI , vol. 3, n. 16, 2016.</p>
Dataset AEROARMS - Perception for robot operation
<p><strong>Dataset description: </strong>This dataset contains the images used for validating the perception algorithms to support aerial and ground robot operations.</p> <p><strong>Data description:</strong> The images where obtained using an Intel Realsense d435 camera. Additionally, the calibration of the camera is given in XML format.</p> <p><strong>Dataset size: </strong>72.8Mb</p>
AEROARMS Behavioural coordinated control
<p>This dataset includes a library of elementary behaviours, namely atomic tasks to be assigned to a dual arm aerial manipulator in a priority order. The devised approach, developed within the EU funded research project AEROARMS (AErial RObotic system integrating multiple ARMS and advanced manipulation capabilities for inspection and maintenance) funded by the European Commission under Horizon 2020 Program (grant agreement No. 644271), is based on a set-based inverse kinematics control [1]. For each elementary task the Jacobian matrix and the task function are provided. </p> <p>The code has been developed in C++ under ROS environment and it has been experimentally tested on a dual-arm prototype developed by the University of Seville constituted by an under-actuated multi-rotor with two arms, each of them characterized by 4 DOFs. The total number of DOFs of the system is 12, while the amount of implemented tasks required a total number of 23 DOFs. This is possible since the different tasks are never activated all together but only a subset of them, based on the state of the system. More in detail, the following equality tasks (i.e. tasks characterized by a specific desired value) have been implemented: </p> <p>• Position and orientation trajectory tracking of both the end-effectors. Such a tasks requires 6 DOFs for each arm.</p> <p>• Center of mass, this task is aimed at ensuring that the center of mass of the dual-arm system is, as much as possible, aligned with that of the UAV, in such a way to avoid to destabilize the flight and reduce the power consumption. Such a task requires 1 DOFs.</p> <p>As concerns the set-based tasks (i.e. tasks whose desired value is represented by an interval) the following have been implemented:</p> <p>• Joint limits: for each joint, upper and lower limits are set in order to avoid its mechanical limits. Such a task requires 1 DOF for each joint of the arms, thus the total number of required DOFs is 8.</p> <p>• Virtual wall between the two arms: to avoid collisions between the two arms, a virtual wall is implemented in order to delimit their working spaces. Such a task requires 2 DOF.</p> <p>• Virtual wall between the arms and the vehicle: to avoid collisions between the arms and the vehicle, virtual walls are implemented in order to delimit their working spaces. Such a task requires 1 DOF for each arm, thus the total number of required DOFs is 2.</p> <p>• Manipulability, aimed at keeping the manipulators far enough from singular configurations, at which the structure loses mobility. Such a task requires 1 DOF.</p> <p>The equality tasks are always active, while the set-based tasks are active only when the task variable is close to the domain border. The experimental results are reported in the paper:</p> <p>E. Cataldi, F. Real, A. Suarez, P.A. Di Lillo, F. Pierri, G. Antonelli, F. Caccavale, G. Heredia, A. Ollero, Set-based Inverse Kinematics Control of an Anthropomorphic Dual Arm Aerial Manipulator, 2019 IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada.</p> <p>The following data and files are included:</p> <p>• The ROS code: ros_code_set_based.zip, that includes the nodes ros_aeroarms_set_based_seville and lib_multitasks that can be tested in simulation with the simulator V-Rep.</p> <p>• The model of a dual arm aerial manipulator, developed in V-Rep.</p> <p>• The experimental data both in the .mat format for reading with Matlab and in the .bag format for ROS.</p> <p>• The experimental results in ASCII files.</p> <p>[1] S. Moe, G. Antonelli, A. R. Teel, K. Y. Pettersen e J. Schrimpf, «Set-Based Tasks within the Singularity-Robust Multiple Task-Priority Inverse Kinematics Framework: General Formulation, Stability Analysis, and Experimental Results,» Frontiers in Robotics and AI , vol. 3, n. 16, 2016.</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.