An integrated framework for humanoid embodiment with a BCI

Abstract

This paper presents a framework to embody a user (e.g. disabled persons) into a humanoid robot controlled by means of brain-computer interfaces (BCI). With our framework, the robot can interact with the environment, or assist its user. The low frequency and accuracy of the BCI commands is compensated by vision tools, such as objects recognition and mapping techniques, as well as shared-control approaches. As a result, the proposed framework offers intuitive, safe, and accurate robot navigation towards an object or a person. The generic aspect of the framework is demonstrated by two complex experiments, where the user controls the robot to serve him a drink, and to raise his own arm.

Non-human Looking Robot Arms Induce Illusion of Embodiment

“…Our embodiment set-up [18,19,28], which used an HMD that provided first person perspective from the robot's body and robot's head movement control by the participant, enabled us to provide participants with a visual illusion where the robot arm was in the same location as the participant's real arm (Video S1), in turn enabling spatial coincidence between the visually perceived touch and the felt touch. We believe that this aspect of the experimental design, which differs from the traditional RHI experiment in which the real arm is in a different location than the rubber hand, contributed to enhance the sense of embodiment towards the robot's arm.…”

“…A novelty in our study, compared to previous rubber-hand illusion related experiments, is that we utilize a whole body embodiment set-up [18,19]. In our setup participants embody the humanoid robot using a head-mounted display (HMD) that provides vision of the arm from the robot's perspective (Video S1) and also control the robot's head movement (Fig.…”

Object Touch by a Humanoid Robot Avatar Induces Haptic Sensation in the Real Hand

“…Recent studies have shown that tactile feedback is important not just as a sensory modality but also in motor coordination and specifically effort perception (Ganesh, Osu, & Naito, ). Our findings thus have important implications in regard to user experience and task control in virtual reality systems and thought‐based teleoperated robots (Petit, Gergondet, Cherubini, & Kheddar, ). We believe that contactless pseudohaptic feedback stemming from the stimulation of other sensory modalities might be an important alternative to the limited haptic displays currently available in these systems.…”

Trained by demonstration humanoid robot controlled via a BCI system for telepresence

“…Synchronous BCI systems are also used in telepresence frequently. BCI system based on Steady State Visual Evoked Potentials (SSVEP) could have high accuracy results operating with short or even no training session [7], [8], [9]. SSVEP does not require a training algorithm for each individual and is respectively fast.…”