Body Image Constructed From Motor and Tactile Images With Visual Information

Fuke, Sawa; Ogino, Masao; Asada, Minoru

doi:10.1142/s0219843607001096

Cited by 47 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In those examples, the number of DOFs of the arm is generally quite low (between two and five). Using self-organizing maps, Fuke et al 9 learn the correspondence between visual, proprioceptive and tactile informations in a simulated arm-face system. The work presented here differs from previous approaches in that the learning is performed entirely online and it can deal with a high number of DOFs.…”

Section: Related Workmentioning

confidence: 99%

Online Learning of the Body Schema

Hersch

Sauser

Billard

2008

Int. J. Human. Robot.

View full text Add to dashboard Cite

We present an algorithm enabling a humanoid robot to visually learn its body schema, knowing only the number of degrees of freedom in each limb. By "body schema" we mean the joint positions and orientations and thus the kinematic function. The learning is performed by visually observing its end-effectors when moving them. With simulations involving a body schema of more than 20 degrees of freedom, results show that the system is scalable to a high number of degrees of freedom. Real robot experiments confirm the practicality of our approach. Our results illustrate how subjective space representation can develop as a result of sensorimotor contingencies.

show abstract

Section: Related Workmentioning

confidence: 99%

Online Learning of the Body Schema

Hersch

Sauser

Billard

2008

Int. J. Human. Robot.

View full text Add to dashboard Cite

show abstract

“…This is in line with findings by Longo and Lourenco (2007) stating that when wielding a tool with the hand, the tool is integrated into the body schema which can be interpreted as a manipulation of the arm length and therefore extends the size of peripersonal space. A lot of research in robotics was inspired by the concept of an adaptive body schema which offers a mechanism to learn tool use and to save engineers from laborious work on predefining an artificial articulated agent's -possibly changing body structure (Nabeshima et al, 2006;Fuke et al, 2007). More recently, work with different approaches on connecting body schema learning with interpretations of peripersonal space for articulated agents have also been presented (Hersch et al, 2008;Fuke et al, 2009).…”

Section: 1mentioning

confidence: 99%

A computational model of cooperative spatial behaviour for virtual humans*

Nguyen¹,

Wachsmuth²

2013

Representing Space in Cognition

View full text Add to dashboard Cite

This chapter introduces a model which connects representations of the space surrounding a virtual humanoid's body with the space it shares with several interaction partners. This work intends to support virtual humans (or humanoid robots) in near space interaction and is inspired by studies from cognitive neurosciences on the one hand and social interaction studies on the other hand. We present our work on learning the body structure of an articulated virtual human by using data from virtual touch and proprioception sensors. The results are utilized for a representation of its reaching space, the so-called peripersonal space, a concept known from cognitive neuroscience.In interpersonal interaction involving several partners, their peripersonal spaces may overlap and establish a shared reaching space. We define it as their interaction space, where cooperation takes place and where actions to claim or release spatial areas have to be adapted, to avoid obstructions of the other's movements. Our model of interaction space is developed as an extension of Kendon's F-formation system, a foundational theory of how humans orient themselves in space when communicating. Thus, interaction space allows for measuring not only the spatial arrangement (i.e., body posture and orientation) between multiple interaction partners, but also the extent of space they share. Peripersonal and interaction space are modeled as potential fields to control the virtual human's behaviour strategy. As an example we show how the virtual human can relocate object positions toward or away from locations reachable for all partners, and thus facilitating cooperation in an interaction task. In this chapter we shall demonstrate how a virtual human can cooperate with a partner in building a toy tower together, as one aspect of computationally modelling shared space and spatial behaviour for action coordination. Virtual humans are autonomous agents with human-like appearance and usually human-like multi-modal behaviour like speech, gaze, gestures, and facial expressions. In three-dimensional virtual reality environments, virtual humans can interact with other virtual humans or with real humans. For example, virtual humans like Max (Kopp et al., 2003) can act as co-situated guides in a construction task, or Steve (Rickel and Johnson, 2000), who act as tutors demonstrating physical tasks to students.In the mentioned scenarios, overlapping workspaces were usually avoided by maintaining enough distance between the partners to avoid interferences between their movements. We believe that in natural interaction such interferences have to be dealt with to accomplish cooperative interaction tasks. Thus, we present our work on modelling a virtual human's spatial behaviour in shared near space interactions in order to facilitate the accomplishment of and the partner's engagement in the cooperative task.Spatial interaction in tasks carried out in distances near to the agent's body usually pose a great challenge to virtual humans. In contrast, humans seem to...

show abstract

“…One approach in simulation is spatio-temporal correlation, learning topographic sensor structures from more or less random input [1]. Other simulated systems purposively seek contact with known external objects [2] or known body parts [3] to probe the sensor locations. In [4] topographic structures are used to classify interactive scenarios, like hugging or hand-shaking of human with a real robot, but the system gains no information about its motor-space.…”

Section: A Motivationmentioning

confidence: 99%

Self-organizing sensory-motor map for low-level touch reactions

Mittendorfer

Cheng

2011

2011 11th IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

Abstract-In this paper, we present a new method to automatically transfer touch stimulation into controllable, reflex reactions for articulated robots -such as a humanoid robot. Our work has been motivated by the necessity to automate the reaction setup for an increasing number of our multimodal artificial sensor skin units (HEX-O-SKIN). Our method therefore evaluates the effect of isolated, sinusoidal degree of freedom (DoF) movements, around a current pose of the robot, towards the motion of each sensor unit. We do this by exploiting data from a 3-axis accelerometer -one of the multiple modalities located on every of our sensor units (SU). Direction and amplitude from all three axes enable us to generate signed weights, one per DoF and SU, leading to the partial construction of a sensory-motor map. In this paper, we focus on reactions towards lateral sensory modalitiessuch as a distance sensor. A higher acceleration along the surface normal thus leads to a higher lateral weight, while unwanted sideway movements decrease it. We then define a reaction controller at the level of each sensor unit. The sensorymotor map is used to map these local reactions, from units distributed all over the robot, into the robot's motor space. Through activation, inhibition or inversion it is possible to adapt these low-level controller instances to a given context. Here, we show experiments with a KUKA lightweight robotic arm reacting evasively or aggressively towards contact with a lateral distance sensor, emulating the sensation of light touch. In comparison to other related works, our method does not suffer from occlusion, complex touch situations or long calibration time.

show abstract

Body Image Constructed From Motor and Tactile Images With Visual Information

Cited by 47 publications

References 11 publications

Online Learning of the Body Schema

Online Learning of the Body Schema

A computational model of cooperative spatial behaviour for virtual humans*

Self-organizing sensory-motor map for low-level touch reactions

Contact Info

Product

Resources

About