Safe trajectories from local information for coverage control in non-convex environments
DOI10.5281/zenodo.13763588Zenodo13763588MaRDI QIDQ6704470FDOQ6704470
Dataset published at Zenodo repository.
Federico Pratissoli, Lorenzo Sabattini, Mattia Mantovani, Mattia Catellani
Publication date: 14 September 2024
Copyright license: Creative Commons Attribution 4.0 International
Description This dataset contains 3-channels grid-based representations of local information individually retrieved by robots in a team, tasked with a coverage control operation. Data collection was performed running 50 episodes of a coverage control mission with a team of 16 robots controlled by a theoretically proven safe expert controller. Features Features encode local information in a 3-channels64 x 64 image, corresponding to the discretized sensing region of the robot. The first channel encodes the local likelihood density, the second one the position of team-mates, and the third channel contains the position of obstacles and boundaries. imgs{i}.npy files contain data collected over each episode in the form of a [S, N, C, W, W] numpy array, where S is the number of steps of that episode, N is the number of robots, C = 3 is the number of channels, and W = 64 is the size of the image. Labels Labels contain the 2D velocity calculated by the expert controller, which is theoretically proven to guarantee collision avoidance. vels{i}.npyfiles contain data collected over each episode in the form of a [S, N, 2]numpy array, associated to the corresponding feature. Training and Testing Code for training and testing a CNN-based model mapping local information to 2D velocity is available at https://github.com/ARSControl/cnn_coverage.git. Contact Information If you are interested in any further information, please contactmattia.catellani@unimore.it.
This page was built for dataset: Safe trajectories from local information for coverage control in non-convex environments
