2009 Ieee 8th International Conference on Development and Learning

Citations in the corpus

Deep learning for detecting robotic grasps (2013, background): “Recent works have employed richer features and learning methods, allowing robots to grasp known objects which might be partially occluded (Jared Glover, 2008) or in an unknown pose (Detry et al., 2009) as well as fully novel objects which the system has not seen before (Saxena et al.”
The Curious Robot: Learning Visual Representations via Physical Interactions (2016, background): “Most initial work focused on using human annotators [21] but in this work we are more interested in building a self-supervision system [22,23,24,25].”
Data-Driven Grasp Synthesis—A Survey (2013, methodology): “[38] model the object as a constellation of local multi-modal contour descriptors.”
Learning robust, real-time, reactive robotic grasping (2019, methodology): “Some techniques work with known items, associating good grasp points with an offline database of object models or shapes (Detry et al., 2009; Goldfeder et al., 2007; Miller et al., 2003), or familiar items, based on object classes (Saxena et al., 2008) or object parts (El-Khoury and Sahbani, 2008),…”
Abstraction Levels for Robotic Imitation: Overview and Computational Approaches (2010, background): “Perception-action maps have appeared in several forms such as the Q-function of a reinforcement learning algorithm [155]; a pure regression map from object features to image points based labelled examples [125, 126] and self-experimentation [39, 92]; or as the correct position of a”
Learning Visual Representations for Interactive Systems (2009, methodology): “In a pilot study, we tracked human grasps with a ViconTM motion capture system [5].”
Learning visual representations for perception-action systems (2011, methodology): “We describe this method in the context of grasping objects (Detry et al. 2009a), a fundamental skill of autonomous agents.”
Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach (2018, background): “Some techniques work with known items, associating good grasp points with an offline database of object models or shapes [6, 8, 23], or familiar items, based on object classes [29] or object parts [7], but are unable to generalise to new objects.”