Retargeting System for a Social Robot Imitation Interface

Bandera, Juan Pedro; Marfil, Rebeca; López, Royman; Toro, J.C. del; Palomino, A.; Sandoval, F.

doi:10.1142/9789812835772_0149

Cited by 1 publication

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This robot, named NOMADA, is a new 1.60 meters tall robot that is currently being developed in our research group [8]. The robot will be provided with two arms that has four degrees of freedom (DOF), plus 1 DOF in the waist and 3 DOF in the head.…”

Section: Resultsmentioning

confidence: 99%

“…As this HMC system is proposed to be used in a social robot, additional computation is required to translate, or retarget, the captured human motion to the robot motion space. This process is deeply described in [8]. The rest of this Section provides a brief description of all these algorithms, focusing on the elements that have been added or modified to ease integration.…”

Section: Methodsmentioning

confidence: 99%

“…As it has been mentioned above, the result of the retargeting module is a combination of both strategies, in which the weight of each factor depends on the amplitude of performed motion. A deeper explanation of this combined retargeting strategy can be found in [8].…”

Section: Methodsmentioning

confidence: 99%

“…Then, the HMC behaviour is executed and capture the upper-body motion of the closer human at about 15 frames per second. 3 This motion is translated to the robot using the previously described retargeting strategy, that is deeply evaluated in [8]. As Fig.…”

Section: Face Recognition and Human Motion Capturementioning

confidence: 99%

See 3 more Smart Citations

Visual Attention Mechanism for a Social Robot

Bandera

Marfil

Palomino

et al. 2012

Applied Bionics and Biomechanics

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes a visual perception system for a social robot. The central part of this system is an artificial attention mechanism that discriminates the most relevant information from all the visual information perceived by the robot. It is composed by three stages. At the preattentive stage, the concept of saliency is implemented based on 'proto-objects' [37]. From these objects, different saliency maps are generated. Then, the semiattentive stage identifies and tracks significant items according to the tasks to accomplish. This tracking process allows to implement the 'inhibition of return'. Finally, the attentive stage fixes the field of attention to the most relevant object depending on the behaviours to carry out. Three behaviours have been implemented and tested which allow the robot to detect visual landmarks in an initially unknown environment, and to recognize and capture the upper-body motion of people interested in interact with it.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Face Recognition and Human Motion Capturementioning

confidence: 99%

See 2 more Smart Citations