Back
A Kernel-based Approach to Direct Action Perception
The direct perception of actions allows a robot to predict the afforded actions of observed novel objects. In addition to learning which actions are afforded, the robot must also learn to adapt its actions according to the object being manipulated. In this paper, we present a non-parametric approach to representing the affordance-bearing subparts of objects. This representation forms the basis of a kernel function for computing the similarity between different subparts. Using this kernel function, the robot can learn the required mappings to perform direct action perception. The proposed approach was successfully implemented on a real robot, which could then quickly learn to generalize grasping and pouring actions to novel objects.
@inproceedings{KroemerUOP2012, title = {A Kernel-based Approach to Direct Action Perception}, booktitle = {International Conference on Robotics and Automation (ICRA 2012)}, abstract = {The direct perception of actions allows a robot to predict the afforded actions of observed novel objects. In addition to learning which actions are afforded, the robot must also learn to adapt its actions according to the object being manipulated. In this paper, we present a non-parametric approach to representing the affordance-bearing subparts of objects. This representation forms the basis of a kernel function for computing the similarity between different subparts. Using this kernel function, the robot can learn the required mappings to perform direct action perception. The proposed approach was successfully implemented on a real robot, which could then quickly learn to generalize grasping and pouring actions to novel objects.}, pages = {2605--2610}, publisher = {IEEE}, month = may, year = {2012}, slug = {kroemeruop2012}, author = {Kroemer, O. and Ugur, E. and Oztop, E. and Peters, J.}, month_numeric = {5} }