Dedicated to the acceptance, medical treatment, & legal protection of individuals in the process of correcting the misalignment of their anatomical sex, & supporting their transition into society.
Washington, DC, USA. A fundamental mechanism inhibits gene expression during translation or hinders the transcription of specific genes. Called RNA interference (RNAi), it targets RNA that is significant ...
New York, NY, USA. Cell division in humans is a process by which a parent cell divides into two or more daughter cells. There is a point of no return in the life of every cell. Once it enters the cell cyc...
Cambridge, MA, USA. New research findings have important implications for human cell types and tissues, including the brain, liver, and lung. While studying cell division, biologists discovered that proliferat...
Cincinnati, OH, USA. Our nervous system consists of a centralized brain and nerve cord (the CNS), as well as a peripheral sensory system (the PNS). They are intricately linked up to detect stimuli, process info...
Linköping, Sweden. Human beings can learn by emulating others, but exploring one's environment is an important part of the learning process. To grow up is to make mistakes, score successes, and learn from experience. What about robots? Can they learn the same way? And if they do, what can we humans learn from their experience and skills? A team of researchers have developed an artificial cognitive system that learns from experience and observation rather than relying on predefined rules and models.
Most schoolchildren struggle to learn geometry, but they are still able to catch a ball without first calculating its parabola. Why should robots be any different? Researchers led by Linköping University (Sweden) in the Cognitive Systems: Perception, Action, Learning (COSPAL) project wondered what basic elements of cognition and learning are common across and within the human species and robotic emulations.
Traditional robotics relies on having the robots carry out complex calculations, such as measuring the geometry of an object and its expected trajectory if moved. But COSPAL has turned this around, making the robots perform tasks based on their own experiences and observations of humans. This trial and error approach could lead to more autonomous robots and even improve our understanding of the human brain.
“Gösta Granlund, head of the Computer Vision Laboratory at Linköping University, came up with the concept that action precedes perception in learning. That may sound counterintuitive, but it is exactly how humans learn,” explains Michael Felsberg, coordinator of the EU-funded COSPAL.
Children, he notes, are “always testing and trying everything” and by performing random actions – poking this object or touching that one — they come to understand cause and effect and can apply that knowledge in the future. By experimenting, they quickly find out, for example, that a ball rolls and that a hole cannot be grasped. Children also learn from observing adults and copying their actions, gaining greater understanding of the world around them.
Learning from humans to learn like … humans
Applied in the context of an artificial cognitive system (ACS), the approach helps to create robots that learn much as humans do and can learn from humans, allowing them to continue to perform tasks even when their environment changes or when objects they are not pre-programmed to recognise are placed in front of them.
“Most artificial intelligence-based ACS architectures are quite successful in recognising objects based on geometric calculations of visual inputs.
Robot Violinist. A robot plays Pomp and Circumstance on the violin. The robot used its mechanical fingers to push the strings and bowed with its other arm.
The 152 cm (five foot) performer can perform a variety of tasks with its hands and arms, each of which has 17 joints.
Using precise control and coordination to achieve human-like agility, the robot could also be used to assist with domestic duties or nursing and medical care.
humans also perform such calculations to identify something, but I don’t think so. I think humans are just very good at recognising the geometry of objects from experience,” Felsberg says.
The COSPAL team’s ACS would seem to bear out that theory. A robot with no pre-programmed geometric knowledge was able to recognize objects simply from experience. And this was true even when its surroundings and the position of the camera through which it obtained its visual information changed.
Getting the right peg in the right hole
A shape-sorting puzzle of the sort used to teach small children was used to test the system. Through trial and error and observation, the robot was able to place cubes in square holes and round pegs in round holes with an accuracy of 2mm and 2 degrees. “It showed that, without knowing geometry, it can solve geometric problems,” Felsberg notes.
“In fact, I observed my 11-month-old son solving the same puzzle and the learning process you could see unfolding with both him and the robot was remarkably similar.”
Another test of the robot’s ability to learn from observation involved the use of a robotic arm that copied the movement of a human arm. With as few as 20 to 60 observations, the robotic arm was able to trace the movement of the human arm through a constrained space, avoiding obstacles on the way. In subsequent trials with the same robot, the learning period was greatly reduced, suggesting that the ACS was indeed drawing on memories of past observations.
In addition, by applying concepts akin to fuzzy logic, the team came up with a new means of making the robot identify corresponding signals and symbols such as colours. Most digital image processing applications specify three numbers to represent a red, green and blue component. Instead, the team made the system learn colours from pairs of images and corresponding sets of reference colour names (such as red, dark red, blue and dark blue). This is a representation known as channel coding. Similar to how colours are identified by the human brain with sets of neurons firing selectively to differentiate green from black, for example, channel coding offers a biologically inspired way of representing information.
“As humans, we can use reason to deduce what an object is by a process of elimination, i.e. we know that if something has such and such a property it must be this item, not that one. Though this type of machine reasoning has been used before, we have developed an advanced version for object recognition that uses symbolic and visual information to great effect,” Felsberg says.
The TS-Si News Service is a collaborative effort by TS-Si.org editors, contributors, and corresponding institutions. The sources can include the cited individuals and organizations, as well as TS-Si.org staff contributions. Articles and news reports do not necessarily convey official positions of TS-Si, its partners, or affiliates.
We welcome your comments. Use the form below to leave a public comment or send private correspondence via the TS-Si Contact Page. We will not divulge any personal details or place you on a mailing list without your permission.
After the explosion came the force of the overpressure rolling through the building and the rumble and shake of the building like an earthquake. The new windows held, the old windows broke and drew the overpressure and the flames away from me into the old , mostly vacant wing of the Pentagon.
“Gösta Granlund, head of the 
That may sound counterintuitive, but it is exactly how humans learn,” explains Michael Felsberg, coordinator of the EU-funded COSPAL. 
Subscribe to this comment's feed
Show/Hide comments
Show/Hide comment form
Copyright © 2005-2008 TS-Si, Inc. • Except where noted, this site is licensed under a Creative Commons Attribution-NoDerivs 2.5 License. • Some rights reserved. • TS-Si is a nonprofit organization dedicated to the acceptance, medical treatment, & legal protection of individuals in the process of correcting the misalignment of their anatomical sex, & supporting their transition into society.