4 datasets found

A dataset of 100 workspaces for training and 10 workspaces for testing, with 200 unseen start and goal configurations in each workspace.

A dataset of 110 different workspaces for motion planning, including simple 2D (s2D), complex 2D (c2D), complex 3D (c3D), and rigid-body (rigid) environments.

The dataset is used to train the ClearanceNet model. It contains 106 training and 104 evaluation samples for each environment.

ClearanceNet is a neural network that estimates minimum separation distance, conditioned on joint robot-workspace pose. ClearanceNet is trained using large-scale hyperparameter...