To implement the telexistence of humans onto the humanoid robot iCub, we pursue research along with different directions and we exploit several technologies that combine the fundamental locomotion and manipulation capacities of the robot with virtual reality systems.
to exist elsewhere via
humanoid robot avatars.”
iCub3

It is 125 cm tall (50 inch), and weighs 52 kg (115 pound). It possesses in total 54 degrees of freedom including those in the fully articulated hands and in the eyes.
iCub3 features six-axis force/torque (F/T) sensors, tactile sensors that act as an artificial skin on the upper arm and the hands. It possesses two cameras, a microphone on both ears and a speaker behind the face cover. A set of LEDs define the robot’s facial expressions.
Why
Remote maintenance
Remote maintenance is nowadays a big challenge for many companies providing assistance to their services. Among the various forms of assistance, augmented reality systems may represent a valid solution for providing continuous maintenance.
In this case, off-situ knowledge workers can instruct in-situ operators about the steps to take to accomplish maintenance. Hydroelectric power plants, offshore platforms, and general power stations are only a few examples where augmented reality systems can be employed to achieve remote maintenance.
Augmented reality maintenance requires in-situ operators to be physically present at the moment of maintenance. Also, the likelihood of achieving successful maintenance operations relies on the capabilities of the in-situ operators to reproduce the manipulation and overall skills of the off-situ knowledge worker.
Emergency response
Another key requirement of remote maintenance through in-situ personnel is that the surrounding environment must be safe and not harmful for the human operator. There are cases, however, where the physical presence of human operators is allowed for a very limited amount of time, or even forbidden.
The Fukushima Daiichi nuclear disaster occurred in Japan on March, the 11th , 2011, for instance, reveals that there are situations where highly competent knowledge workers need to operate for long amount of time to avoid apocalyptic disasters.
In these cases, the locomotion, manipulation, and overall experience of knowledge workers are required for achieving effective operations, but human beings are not be allowed to operate safely or continuously due to the hazardous condition of the surrounding environment.
What
Humanoid robots can emulate many of the human capacities. Manipulation, walking, vision, and hearing are the common capacities and perception senses that humanoid robots possess. Furthermore, the human-like shape of humanoid robots is best suited for the human environment, thus rendering them good candidates for achieving tasks in place of humans.
Humanoid robots can then represent a valid solution for all those scenarios where remote maintenance and emergency response require physical interaction between knowledge operators and the surrounding environment.
Thus, we aim at providing human beings with the capacity of telexistence through the humanoid robot iCub by implementing advanced teleoperation systems. These teleoperation systems allow us to transfer human motions in terms of locomotion and manipulation onto the humanoid robot iCub. We research and deploy effective teleoperation systems for industrial setting and emergency response scenarios.


How
Research on humanoid robot motor control
To transfer, or more technically to re-target, the human motions onto the humanoid robot, fundamental motor control skills must be implemented on iCub. We work on the so-called whole-body torque control, and we aim at giving the robot balancing, locomotion, and manipulation skills that can be teleoperated via human being. To achieve this, we apply to fundamental tools of control theory
Whole-body balancing
The use of feedback linearisation control techniques framed in the context of quadratic programming optimisation leads to the emergence of balancing behaviors for the humanoid robot. In these cases, the robot uses its entire body, i.e., whole-body, to achieve the balancing while being compliant to human-robot interaction.
Whole-body walking
The use of predictive control techniques still framed in the context of quadratic programming optimisation leads to the emergence of walking behaviors for the humanoid robot. Again, the robot uses its entire body, i.e., whole-body, to achieve the walking task.
Whole-body jumping
Although iCub hardware is not optimised for jumping, we applied feedback linearisation control techniques still framed in the context of quadratic programming optimisation to make the humanoid robot jump. In emergency responce scenarios, the capacity of jumping may be fundamental to skip obstacles and to recover balancing quickly.
Integration of virtual reality devices
To allow a human being to exist into another place, we have to transfer some of the human capacities onto the humanoid robot (e.g., walking, manipulation), and also give some of the robot senses to the human being (e.g., hearing, vision).
For these reasons, we work on the integration of several virtual reality systems that achieve this transfer.
