Constrained LAtent Shape Projection (CLASP) combines a shape completion neural network with contact measurements from a robot. This repo also contains the full paper and additional plots.

1. Set up ROS
2. Clone this repo in your ROS path. Rebuild (e.g. catkin build), re-source
3. Install dependencies
4. Download datasets and pretrained models by running shape_completion_training/scripts/download_pretrained.py

Trial results are in ./evaluations To recreate the plots from the paper using the pre-run trials, contact_completion_evaluation.py --plot

To rerun shape completion experiments using the robot motion and contacts as recorded from the paper, in separate terminals run:

1. roslaunch shape_completion_visualization live_shape_completion.launch (Rviz will start)
2. roslaunch shape_completion_visualization transforms.launch (Sets transforms between robot and shape objects)
3. contact_completion_evaluation.py --plot --regenerate (You will see many shape being generated and updates. Will take over an hour to complete)

The full experimental setup requires running a simulated, or real robot, which moves and contacts objects. To build the software stack used in the experiments, set up the dependencies.

Detailed instructions are in the subfolder [https://github.com/UM-ARM-Lab/contact_shape_completion/tree/main/contact_shape_completion]

Then run

1. roslaunch shape_completion_visualization live_shape_completion.launch (Rviz will start)
2. Launch the robot stack (see detailed instructions in subfolder)
3. store_simulation_examples --trial [PRETRAINED_NETWORK_NAME] --scene [SCENE_NAME] --store