Skip to content
Code for the paper "Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks"
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
.gitignore Added SVM for tables 2 and 4. Updates to plots. Nov 9, 2017

Semi-Supervised Haptic Material Recognition using GANs

Z. Erickson, S. Chernova, and C. C. Kemp, "Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks", 1st Annual Conference on Robot Learning (CoRL 2017), 2017.

Project webpage:

Download the MREO dataset

Compact dataset (1 GB) (can be used to compute tables 1, 2, 3, 4, and 6):
Full processed dataset (20 GB) (can be used to compute all tables in paper):
Raw data collected on the PR2 (10 GB):
Dataset details can be found on the project webpage.

Running the code

Our generative adversarial network is implemented in Keras and includes the feature matching technique presented by Salimans et al.
GAN results presented in tables 1, 3, and 6 can be recomputed using the command below (requires compact dataset). This takes several hours with a GPU.

python --tables 1 3 6

Neural network and SVM results from tables 2 and 4 can be recomputed using the commands below (requires compact dataset).

python --tables 2 4
python --tables 2 4

Recompute results presented in table 5 (requires full dataset).

python --tables 5

Generate plots. This requires plotly.


Collect new data with a PR2.

rosrun fingertip_pressure &
python &
python &
python -n fabric_khakishorts -s 100 -w 0.1 -l 0.1 -ht 0.06 -v
python -n plastic_fullwaterbottle -s 100 -l 0.03 -ht 0.08


Python 2.7
Keras 2.0.9
Librosa 0.5.1
Theano 0.9.0
Numpy 1.13.3
Plotly 2.0.11

You can’t perform that action at this time.