We present a probabilistic model for joint representation of several sensory modalities and action parameters in a robotic grasping scenario. Our non-linear probabilistic latent variable model encodes relationships between grasp-related parameters, learns the importance of features, and expresses confidence in estimates. The model learns associations between stable and unstable grasps that it experiences during an exploration phase. We demonstrate the applicability of the model for estimating grasp stability, correcting grasps, identifying objects based on tactile imprints and predicting tactile imprints from object-relative gripper poses. We performed experiments on a real platform with both known and novel objects, i.e., objects the robot trained with, and previously unseen objects. Grasp correction had a 75% success rate on known objects, and 73% on new objects. We compared our model to a traditional regression model that succeeded in correcting grasps in only 38% of cases.
|Title of host publication||2016 IEEE International Conference on Robotics and Automation (ICRA 2016)|
|Subtitle of host publication||Proceedings of a meeting held 16-21 May 2016, Stockholm, Sweden|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||8|
|Publication status||Published - Aug 2016|