Parental action modification highlighting the goal versus the means

Nagai, Yukie; Rohlfing, Katharina J.

doi:10.1109/devlrn.2008.4640796

Cited by 10 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These changes to the way that infants process different types of information might increase infants' attention to the physical properties of objects relevant to object function, induce development of motor activities related to object manipulation (e.g., reaching, manipulating, fingering), and motivate infants to increase their exploration of objects in their environment. Indeed, investigations of computer vision algorithms have shown that functional features of objects are visually salient, particularly when seen in events in which actors manipulate objects, even to a viewer (i.e., a computer vision algorithm) that cannot act on objects itself (Nagai & Rohlfing, 2008, 2009.…”

Section: Discussionmentioning

confidence: 99%

Investigating the Relation Between Infants' Manual Activity With Objects and Their Perception of Dynamic Events

Baumgartner¹,

Oakes²

2013

Infancy

View full text Add to dashboard Cite

We examined the relation between 6‐ and 7‐month‐old infants' (N = 60) manual activity with objects during free play and their perception of the features of dynamic, multimodal events. Infants were habituated to a single event in which a hand reached for and manipulated a colorful, multifeatured object, and a sound was heard (e.g., a hand squeezed a purple round object, causing a whistling sound) and then their response to events that involved a change in the appearance of the object, the action, or the sound was assessed. Infants responded least to changes in the appearance of the objects, and their sensitivity to this feature was related to their manual activity with objects during free play. Infants' responding to changes in the sound or action was unrelated to motor activity, suggesting that at this age motor achievements related to object exploration are associated with infants' perception of some, but not all, object features.

show abstract

Section: Discussionmentioning

confidence: 99%

Investigating the Relation Between Infants' Manual Activity With Objects and Their Perception of Dynamic Events

Baumgartner¹,

Oakes²

2013

Infancy

View full text Add to dashboard Cite

show abstract

“…Another interesting issue from a developmental perspective is to analyze different tasks as well as different teaching-learning scenarios. My hypothesis is that key points in a demonstrated action will be extracted differently depending on the goal-orientedness of the task and on the ability of learners [23]. Such analytical studies employing bottom-up architectures would contribute to uncovering human development.…”

Section: Discussionmentioning

confidence: 99%

“…The author has investigated parental scaffolding for infants' action learning as well as for robots' [18], [23]. The focus of this experiment, however, is on the evaluation of the proposed system rather than on the analysis of parental teaching.…”

Section: Object and Motion Associationmentioning

confidence: 99%

“…It enables robots to autonomously explore the environment [14], [15], detect and interact with humans [16]- [18], and learn to recognize objects and their own bodies in their visual field [19], [20]. It has also contributed to uncovering the development of human attention [21]- [23]. Bottom-up attention is supposed to play an important role Y. Nagai is with the Research Institute for Cognition and Robotics, Bielefeld University, 33594 Bielefeld, Germany (e-mail: yukie@techfak.unibielefeld.de).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From bottom-Up visual attention to robot action learning

Nagai

2009

2009 IEEE 8th International Conference on Development and Learning

Self Cite

View full text Add to dashboard Cite

This research addresses the challenge of developing an action learning model employing bottom-up visual attention. Although bottom-up attention enables robots to autonomously explore the environment, learn to recognize objects, and interact with humans, the instability of their attention as well as the poor quality of the information detected at the attentional location has hindered the robots from processing dynamic movements. In order to learn actions, robots have to stably attend to the relevant movement by ignoring noises while maintaining sensitivity to a new important movement. To meet these contradictory requirements, I introduce mechanisms for retinal filtering and stochastic attention selection inspired by human vision. The former reduces the complexity of the peripheral vision and thus enables robots to focus more on the currently-attended location. The latter allows robots to flexibly shift their attention to a new prominent location, which must be relevant to the demonstrated action. The signals detected at the attentional location are then enriched based on the spatial and temporal continuity so that robots can learn to recognize objects, movements, and their associations. Experimental results show that the proposed system can extract key actions from human action demonstrations. Index Terms-learning from demonstration, bottom-up visual attention, what to imitate, key actions

show abstract

“…Investigations in the field of parent-infant research [17], [18], which are partly based on a model proposed by [19] showed that parents modify their actions when teaching their children tasks, such as stacking cups. Parents start the interaction by highlighting and shaking the important object that is involved in the task and begin their demonstration when the child focuses on the object.…”

Section: A Attention-based Criterionmentioning

confidence: 99%

Automatic selection of task spaces for imitation learning

Mühlig

Gienger

Steil

et al. 2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Previous work [1] shows that the movement representation in task spaces offers many advantages for learning object-related and goal-directed movement tasks through imitation. It allows to reduce the dimensionality of the data that is learned and simplifies the correspondence problem that results from different kinematic structures of teacher and robot. Further, the task space representation provides a first generalization, for example wrt. differing absolute positions, if bi-manual movements are represented in relation to each other. Although task spaces are widely used, even if they are not mentioned explicitly, they are mostly defined a priori. This work is a step towards an automatic selection of task spaces. Observed movements are mapped into a pool of possibly even conflicting task spaces and we present methods that analyze this task space pool in order to acquire task space descriptors that match the observation best. As statistical measures cannot explain importance for all kinds of movements, the presented selection scheme incorporates additional criteria such as an attention-based measure. Further, we introduce methods that make a significant step from purely statistically-driven task space selection towards model-based movement analysis using a simulation of a complex human model. Effort and discomfort of the human teacher is being analyzed and used as a hint for important task elements. All methods are validated with realworld data, gathered using color tracking with a stereo vision system and a VICON motion capturing system.

show abstract

Parental action modification highlighting the goal versus the means

Cited by 10 publications

References 19 publications

Investigating the Relation Between Infants' Manual Activity With Objects and Their Perception of Dynamic Events

Investigating the Relation Between Infants' Manual Activity With Objects and Their Perception of Dynamic Events

From bottom-Up visual attention to robot action learning

Automatic selection of task spaces for imitation learning

Contact Info

Product

Resources

About