Developmental learning model for joint attention

Nagai, Yukie; Asada, Minoru; Hosoda, Koh

doi:10.1109/irds.2002.1041510

Cited by 17 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the validity of their model has not been verified through implementation in an artificial agent. Nagai et al (2002) proposed a constructive model by which a robot learns joint attention through interactions with a human caregiver. They showed that a robot was able to acquire the ability of joint attention based on task evaluation from a caregiver, and the learning process became more efficient owing to the development of the robot's and the caregiver's internal mechanisms.…”

Section: Introductionmentioning

confidence: 99%

A constructive model for the development of joint attention

Nagai¹,

Hosoda²,

Morita³

et al. 2003

Connection Science

183

View full text Add to dashboard Cite

This paper presents a constructive model by which a robot acquires the ability of joint attention with a human caregiver based on its embedded mechanisms of visual attention and learning with self-evaluation. The former is to look at a salient object in the robot's view, and the latter is to learn sensorimotor co-ordination when visual attention has succeeded. Since the success of visual attention does not always correspond to the success of joint attention, the robot has incorrect learning data for joint attention as well as correct data. However, the robot is expected statistically to lose incorrect data as outliers since such data do not have any correlation in the sensorimotor co-ordination while correct data have a correlation. The robot consequently acquires the ability of joint attention by finding the correlation in the sensorimotor co-ordination even if multiple objects are placed at random positions in an environment and a human caregiver does not provide any task evaluation to the robot. The experimental results show that the proposed model makes the robot reproduce the developmental process of infants' joint attention. Therefore, the proposed model could be one of the models to explain how infants develop the ability of joint attention.

show abstract

Section: Introductionmentioning

confidence: 99%

A constructive model for the development of joint attention

Nagai¹,

Hosoda²,

Morita³

et al. 2003

Connection Science

183

View full text Add to dashboard Cite

show abstract

“…; is there a pattern of learning consistent with N-shaped or U-shaped development as noted in developing infants 31 ? ; does this developmental approach towards face learning offer advantages in generalizability, such as was shown in Nagai et al 32 for joint attention representation? A purely engineering approach misses the underlying complexity of the developmental process.…”

Section: Example -Face Recognitionmentioning

confidence: 95%

Pitfalls in the Modeling of Developmental Systems

Shic

Scassellati

2007

Int. J. Human. Robot.

View full text Add to dashboard Cite

Computational models of development aim to describe the mechanisms that underlie the acquisition of new skills or the emergence of new capabilities. The strength of a model is judged by both its ability to explain the phenomena in question as well as its ability to generate new hypotheses, generalize to new situations, and provide a unifying conceptual framework. Although often constructed using traditional engineering methodologies, evaluating the performance of a computational model of development in terms of traditional perspectives is a flawed approach. This paper addresses the fundamental issues that confound quantitative analysis of computational models of developmental systems. In particular we focus on the following recommendations: 1) don't equate the success of a developmental model with its peak performance at some task; 2) don't employ purely subjective or vague measures of model fitness; and 3) don't hide or reject variation as found in the computational model. Along the way, we discuss the aspects of computational models of development that lead to the requirements for specialized methods of analysis.

show abstract

“…For instance, in [18], a NN is employed for modeling the visual system of a robot, where there are different layers representing the input, retina, visual cortex, and output. Since the problem of establishing joint attention is particularly difficult under these additional constraints, the contextual information must be employed.…”

Section: Related Workmentioning

confidence: 99%

Joint Attention by Gaze Interpolation and Saliency

Yücel

Salah

Meriçli

et al. 2013

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of the experimenter's eye region requires stability and high-resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then, we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human-robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur), show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention.

show abstract

Developmental learning model for joint attention

Cited by 17 publications

References 12 publications

A constructive model for the development of joint attention

A constructive model for the development of joint attention

Pitfalls in the Modeling of Developmental Systems

Joint Attention by Gaze Interpolation and Saliency

Contact Info

Product

Resources

About