Deep Learning for Detecting Robotic Grasps
Learning-based approaches in previous works have been succeesfully used for grasping novel objects, but required manual design of features for image and depth data. We use deep learning, which allow us to learn the basic features used by our algorithm directly from RGB-D data.
Our deep learning algorithm uses our novel structured multimodal regularization approach to encourage the learned features to use a subset of the input modalities. This leads to more robust RGB-D features, especially when surface normals are used as additional input modes.
- Deep Learning for Detecting Robotic Grasps, Ian Lenz, Honglak Lee, Ashutosh Saxena. To appear in International Journal of Robotics Research (IJRR), 2014. [PDF] Previous version appeared as a conference paper in RSS 2013
Data/CodeThe grasping rectangle dataset can be found here. Code for learning and detection is available here.
Code to run grasps on a Baxter robot is available here.
The readme should get you started, but let Ian (ianlenz at cs.cornell.edu) know if you have any questions.
|Ian Lenz||ianlenz at cs.cornell.edu|
|Shikhar Sharma||shikhars at iitk.ac.in|
|Honglak Lee||honglak at eecs.umich.edu|
|Ashutosh Saxena||asaxena at cs.cornell.edu|