-
Object Rearrangement Using Learned Implicit Collision Functions
A learned collision checking model that dramatically increases collision checking speeds between point clouds for motion planning in real-world rearrangement tasks. -
End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning
The proposed method uses raw depth images obtained from a front-facing camera and directly generates local motion plans in the form of smooth motion primitives that move a... -
Pholus Robot Configurations
The dataset used for the experiments in the paper is a collection of robot configurations for the Pholus robot. -
Constraint Satisfying Robot Configurations
The dataset used for the experiments in the paper is a collection of constraint-satisfying robot configurations. -
Autoencoder Trajectory Primitive (ATP)
The dataset used in the paper is a collection of demonstrated trajectories for a robotic system. -
ClearanceNet Training Dataset
The dataset is used to train the ClearanceNet model. It contains 106 training and 104 evaluation samples for each environment. -
Neural Collision Clearance Estimator for Batched Motion Planning
ClearanceNet is a neural network that estimates minimum separation distance, conditioned on joint robot-workspace pose. ClearanceNet is trained using large-scale hyperparameter...
