Robotics  

A new video from the iCub project shows very preliminary results achieved in the whole-body control of the child-like humanoid robot when standing on a seesaw. The knowledge of the robot and seesaw dynamics along with the measurement of the external perturbations allow him to keep the equilibrium even when interacting with humans.

SOURCE  iCub HumanoidRobot

By 33rd Square

Embed

 Robotics  

In a new video, researchers at the Italian Institute of Technology display some amazing balancing done by the iCub humanoid robot.  The robot keeps its position on one leg even as the researchers prod and move it.

In the new video below, the latest results achieved in the whole-body control of the iCub, humanoid robot are showed off. Perhaps the researchers at the Italian Institute of Technology were inspired by ATLAS and Valkyrie.

Related articles Simplified Brain Lets The iCub Robot Learn Language  Towards Intelligent Humanoid Robots  David Hanson on The Future of Robotics

The video shows the iCub balancing when the robot stands on one foot. The knowledge of the robot dynamics and the measurement of the external perturbations allow for safely interacting with humans as well as controlling highly dynamic motions, according to the researchers.

The control of the robot is made by regulating the interaction forces between the robot and its surrounding environment. In particular, the force and torque exchanged between the robot's foot and the floor is regulated so that the robot keeps its balance even when strongly jostled by a person.

Also impressively, the robot maintains gaze stabilization, which makes the actions seem more human-like.

"These new capacities will be pivotal when iCub will cohabitate with human beings in domestic environments."

"These new capacities will be pivotal when iCub will cohabitate with human beings in domestic environments," claim the researchers.

The results have been achieved by the researches working at the Italian Institute of Technology and, in particular, by those funded by the European Projects CoDyCo and Koroibot with Dr. Francesco Nori as principal investigator.




SOURCE  iCub Humanoid Robot

By 33rd Square

Embed

 Robotics  

The research team behind the iCub project is now developing a new model, that will be ready for mass production, with the aim of bringing domestic robotic companions to elderly users for less than the price of a subcompact car.

Owning your own domestic robot may be on the verge of escaping from the realm of science fiction, but the goal which is preparing one of the most advanced robotics laboratories in the world.

"We just started the project that tends to develop low-cost technologies, in theory translatable to make robotics  products to be manufactured in series and able to enter our homes, '' Giorgio Metta, director of iCub Facility of the Italian Institute of Technology (IIT) has told ANSA.

Related articles Brian David Johnson Introduces The Open-Source Robot, Jimmy  Robotic Software Start-up Looks to Make Robots Learn  Simplified Brain Lets The iCub Robot Learn Language

The next step, requires the involvement of industry to ramp up the mass production of the robots. But before that it is essential to have the results of a project, called "Robot Badanti," (Robot Carers) just started IIT and that could end in a year and a half.

"We just started the project that tends to develop low-cost technologies, in theory translatable to make robotics  products to be manufactured in series and able to enter our homes."

The project involves developing the characteristics of future domestic robots, to reduce costs, unsustainable today for what promises to be the most sophisticated electrical appliances.

Metta and his team are behind the iCub, the 'robot baby' who knows how to learn and 'grow' and is now, walking on two legs.

iCub will not get into houses, but an anthropomorphic robot will soon according to Metta. His team is now designing the new domestic robot, said Metta, and, like the iCub, will look '' reassuring and pleasant."

Like the iCub, the new robot will come with two arms, but will  move on wheels to reduce costs.

"Today a robot costs about €250,000 and is of course out of any market. Robots of this type," explains Metta, "can only be used in laboratories. We would like to get to a product that does not cost more than a small car, which is below  €10,000 and if possibly even less. For this we are studying new plastic materials to replace the metal and designing components that can be produced on a large scale."

According to Metta, robot companions, are ideal for the elderly, which in advanced societies are likely to become more and more numerous, while fewer and fewer young people and adults will be able to assist them. "The robots we are working on will be able to perform simple tasks, like taking objects, picking them up off the ground, and bringing them to people," says Metta. "They will be also a communication tool, with functions similar to those of a smartphone."


SOURCE  ANSA 

By 33rd Square

Embed

 Robotics  

In a lecture recently made available, iCub Facility Director Giorgio Metta describes the history and philosophy behind the iCub project, and presents some recent results of work done on the child-like robot.

The iCub project was started 10 years ago within the field of Human Robotics, focused mostly on building models of cognitive behaviors. The goals of the project include understanding how the human brain resolves certain problems just to use this knowledge within robotics and build models that can allow robots to solve autonomously the same problems, hence become highly intelligent systems.

In the lecture above, iCub Facility director at the Italian Institute of Technology, Giorgio Metta describes the history and philosophy behind the iCub project, and presents some recent results. Slides for the presentation can download here.

"The focus of our research is in the implementation of biologically sound models of cognition in robots of humanoid shape," states Metta.

The two main goals of the iCub project are to further understanding of brain functions and to develop robot controllers that can learn
and adapt from their mistakes.

Twenty years ago neurophysiologists discovered special types of neurons called visuomotor neurons. This discovery triggered a shift in the way robots were programmed to learn and perceive as now, mirroring the function of these neurons, the goal was not only for the robot to perceive the surroundings but also to act upon the new information acquired, to carry out a task, solve a problem, imitate what a person would do when he or she perceives and processes external information.

To translate these goals into practice, first experiments where focused on registering human grasping actions via data gloves and trackers and then these registered actions, translated into images, were used to build a classifier which would aid the robot to predict better what action to carry out when perceiving certain information.

"The message is that we started a long time ago by observing nature, ending up here, understanding the basic blocks that make up complex behavior."

Furthermore, neuro studies showing that it is not that important to recognize the object to be grasped it but it’s enough to recognize it’s shape, helped Metta and his team build models that prepared the robot to recognize the shape of an object just before executing an action like grasping it.

This made possible for the robot to execute more complex behaviors such as recognize not only the objects to be grasped or pushed, but also to recognize tools which may help the robot to do something with the object in question. In one of the experiments lead by Metta, this was translated into an iCub grasping a tool to bring closer an object placed too far away from the robot, in order for the iCub to grasp it.

"The message is that we started a long time ago by observing nature, ending up here, understanding the basic blocks that make up complex behavior," Metta says.

Related articles Richard Gordon On Building Intelligent Machines  Towards Intelligent Humanoid Robots  Ultrahaptic Prototype Lets You Feel Gesture Controls In Mid-Air

Metta is currently on leave of absence from the University of Genoa (Italy) where he used to teach courses on Anthropomorphic Robotics and Intelligent Systems for the Bioengineering curricula. He holds a MSc cum laude (1994), and PhD (2000) in Electronic Engineering from the University of Genoa.

From 2001 to 2002 he was postdoctoral associate at the MIT AI-Lab . He has been assistant Professor at the University of Genoa since 2005 and he works at the Italian Institute of Technology where the iCub Facility is to be found since 2006. He is Professor of Cognitive Robotics at the University of Plymouth (UK) since 2012.

Giorgio Metta’s research activities are in the fields of biologically motivated and humanoid robotics and, in particular, in developing humanoid robots that can adapt and learn from experience. His research efforts have stemmed from collaborations with leading European and international scientists from different disciplines like neuroscience, psychology, computer science and robotics.

Metta has authored approximately 250 publications and has been working as principal investigator and research scientist in about a dozen international as well as national funded projects.


SOURCE  RoboHub, International Journal of Advanced Robotic Systems

By 33rd Square

Embed

  

 Robots  

The robotic platform initially set up to mimic a four year old child turns ten this year.  The iCub humanoid robot is now at work in 25 research units around the world.

The iCub is a humanoid robot shaped as a four years old child originally designed by a consortium of 11 partners guided by the Italian Institute of Technology. A decade on, and the robot is is still opening new doors to understanding.

The iCub has provided a platform for research in areas ranging from engineering to neurophysiology and developmental psychology within the RobotCub Integrated Project funded by European Commission through its Cognitive Systems and Robotics Unit.

Happy Birthday iCub!

Related articles Simplified Brain Lets The iCub Robot Learn Language  Towards Intelligent Humanoid Robots  Rodney Brooks on Robots in the Workplace

The iCub can crawl on all fours and sit up. Its hands allow dexterous manipulation and its head and eyes are fully articulated. It has visual, vestibular, auditory, and tactile sensory capabilities. In the past few years the community of researchers working on the iCub grew at a constant pace.

Today there are more than 25 iCub platforms in use worldwide. Simultaneously the platform evolved significantly in terms of its sensors and actuators. Thanks to the recent improvements the iCub is now equipped with: whole-body distributed tactile and force/torque sensing, series elastic actuators for compliant walking experiments and movable head with microphones, speaker, actuated eyes, eyelids and lips for speech and human-robot interaction studies.

The key advantage of the iCub is that it is an integrated platform that allows the study of complex tasks that require speech and auditory perception, vision as well as proper coordination and integration of sensory data and control. The developers believe that this, more than ever, requires that researchers with different expertise join forces and start working together. Having platforms with compatible software and hardware is clearly a unique opportunity for collaboration.

Happy Birthday iCub!



SOURCE  iCub Humanoid Robot

By 33rd Square

Embed

 Robotics

The iCub robot project has recently upgraded the child-like robot with legs equipped with force-feedback sensors that have allowed the android to stand and balance on its own.  Previously the research robot could only crawl along just like a child.

I t has been a while since we checked in with iCub, the robot designed for research into human cognition and artificial intelligence through embodied cognition.

That is the hypothesis that human-like manipulation plays a vital role in the development of human cognition. As a baby learns many cognitive skills by interacting with its environment and other humans using its limbs and senses, and consequently its internal model of the world is largely determined by the form of the human body, the robot was designed to test this hypothesis by allowing cognitive learning scenarios to be acted out by an accurate reproduction of the perceptual system and articulation of a small child so that it could interact with the world in the same way that such a child does.

Just like a child, iCub did not initially stand on its own, and was only able to crawl.

Now as seen in the video below, iCub just "learnt" to balance while standing on two legs. A first experiment based on a new iCub sense adjusting actuators it its limbs.  Presumably the robot's "baby steps" may soon also be made.

With Roboy also in development in Switzerland, there is a great deal of work currently underway exploring embodiment for artificial intelligence.  What is so striking about iCub though is the naturalness and eerie similarity the robot has to the movements of an actual child.




SOURCE  iCub Humanoid Robot

By 33rd Square

Subscribe to 33rd Square

 Robots

Based on what was on display at Europe's largest robotics expedition in Lyon, France, Innorobo 2012, it is clear that it's only a matter of time before robots populate our homes, schools, hospitals, and cities. —

T hey can dance, check your heart rate, vacuum your room, make dinner, or wash the dishes -- all without complaining, or asking for a raise. A new generation of robots not only looks human, but is taking on human tasks.

In the embedded video below, Constantino De Miguel reports from Europe's largest robotics expedition in Lyon, France, Innorobo 2012 where it is clear that it's only a matter of time before robots populate our homes, schools, hospitals, and cities.

According to Innorovo, robotics is already part of our lives and is the near future for many sectors of the economy. It is not only a vertical industry, but also a transversal dynamic that impacts a great variety of fields of activity.

Innorobo's aim is to support the service robotics industry and to accelerate its awareness and business development.  The organization also addresses other impacted industries in search of growth through diversification, investments or for a boost of their innovations.

SOURCE  LinkTV

By 33rd Square

Subscribe to 33rd Square

 Robots

The humanoid robot iCub is now being taught how to play with rolling objects.  By using kinematic control, the robot is able to correctly roll toys that are placed on a table in front of it.

Only certain objects roll well, and to make them roll requires matching the an action to the object's pose in an suitable manner. Researchers are now teaching these factors to the robot iCub.

The iCub is the humanoid robot developed at IIT as part of the EU project RobotCub and subsequently adopted by more than 20 laboratories worldwide. It has 53 motors that move the head, arms & hands, waist, and legs. It can see and hear, it has the sense of proprioception (body configuration) and movement (using accelerometers and gyroscopes).

Unlike other robotic systems that are programmed like a computer, iCub is programmed mainly via interaction.  In this way, the robot is intended to 'learn' as a human child would.

We have previously shown the robot iCub learning objects, and the researchers at iCub.org have also uploaded very impressive videos of the robot learning about toys and how to pick them up.

The humanoid robot can locate familiar objects through vision and tap them from different directions using kinematic control.

In order to get the rolling distance, iCub segments the object and finds its orientation to then track it using a particle filter. To learn the rolling affordance the Least-squares support vector machine (LSSVM) technique is employed.

Once iCub has explored this affordance it is asked to tap the object to attain the maximum rolling distance. Watch the video below to see the iCub in action.




SOURCE  robotcub

By 33rd Square

Subscribe to 33rd Square

martinpeniak.com

Peter Dominey at the Stem-cell and Brain Research Institute recently uploaded this video of iCub.   The iCub learns to associte novel names with novel objects, both in the context of explicit naming, and more interestingly, when a novel name is used during an interaction.