Modeling Peripersonal Action Space for Virtual Humans Using Touch and Proprioception

Abstract

Abstract. We propose a computational model for building a tactile body schema for a virtual human. The learned body structure of the agent can enable it to acquire a perception of the space surrounding its body, namely its peripersonal space. The model uses tactile and proprioceptive informations and relies on an algorithm which was originally applied with visual and proprioceptive sensor data. In order to feed the model, we present work on obtaining the nessessary sensory data only from touch sensors and the motor system. Based on this, we explain the learning process for a tactile body schema. As there is not only a technical motivation for devising such a model but also an application of peripersonal action space, an interaction example with a conversational agent is described.

A computational model of cooperative spatial behaviour for virtual humans*

“…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). Our current research 8 addresses this aspect (Nguyen and Wachsmuth, 2009), which is reconsidered in more detail in this chapter.…”

“…In previous work (Nguyen and Wachsmuth, 2009), we developed and technically realized touch receptors for Max's whole virtual body. These receptors allow for differentiating between different qualities of tactile stimulation.…”

“…For each posture he perceives proprioceptive data from his joints and tactile stimuli when randomly touching positions on his body (see Figure 3). As described in our previous work (Nguyen and Wachsmuth, 2009) we consider the body schema as a tree of rigid transformations. In our case this kinematic tree is prescribed by the skeleton of the virtual human Max.…”