(Page 2 of 2)
Once the robot had been given the software, the researchers found that it did indeed move like a human. When moving slowly, it passed close to an obstacle, because it knew that it could recalculate its path without changing course too much. When moving more quickly toward the target, the robot gave obstacles a wider berth since it had less time to calculate a new trajectory.
Robots that navigate using more conventional methods may be more efficient and reliable, says Antonio Frisoli of the PERCRO Laboratory at Scuola Superiore Sant'Anna, in Pisa, Italy, who led the team that built the robot's head. For example, a robot guided by laser range-finding and conventional route-planning algorithms would take the most direct path from point A to point B. But the team's goal was not to compete with the fastest, most efficient robot. Rather, the researchers wanted to understand how humans navigate. We, too, says Frisoli, "adapt our trajectory according to our speed of walking."
Applications of the technology could include "smart" wheelchairs that can navigate easily indoors, says Greenlee. A few members of the consortium have applied for a grant to follow up on this application, while one of the original partners, Cambridge Research Systems, in the U.K., is developing a head-mounted device based on the technology that could aid the visually impaired by detecting obstacles and dangers and communicating them to the wearer.
Tomaso Poggio, who heads MIT's Center for Biological and Computational Learning and studies visual learning and scene recognition, says of the EU project, "It seems to be a trend, from neuroscience to computer science, to look at the brain for designing new systems." He adds that we are "on the cusp of a new stage where artificial intelligence is getting information from neuroscience," and says that there are "definitely areas of intelligence like vision, or speech understanding, or sensory-motor control, where our algorithms are vastly inferior to what the brain can do."
They may help efforts to bring the Fukushima plant under control, but are generally expensive and problematic.
While hearing in machines lags far behind vision in machines, the potential is great, and researchers are beginning to make impressive progress.
At MIT, neuroscience and artificial intelligence are beginning to intersect.
No one serious in "AI" has been doing symbolic systems in logic for more than a decade. Rather, the field has moved to machine learning, probabilistic representations and for robotics, better sensors that have done things like win the Darpa Grand Challenge race across the desert, give reasonable search in Google, good image retrieval in Bing and allowed airlines to fly mostly full.
The article might be great work for testing theories of human intelligence, but maybe not so good for robotics, just read what it said:
" Robots that navigate using more conventional methods may be more efficient and reliable, says Antonio Frisoli "
That is, AI is already working better for navigation than this human centric approach. You can also see work by Willow Garage where a robot recently went 26 miles (a marathon) through an office environment navigating around chairs and people. It then followed this by 1 hour in which the robot had to find and plug in to 10 electrical outlets opening doors as needed along the way
http://www.willowgarage.com/blog/2009/06/03/watch-milestone-2
Well, don't tell this to the Cyc fanatics.
That is, AI is already working better for navigation than this human centric approach.
Better than other robots, certainly. Use this approach to replace cab drivers in NYC and all hell will break loose, I guarantee it. This does not mean that the human-centric approach is not the right approach. We have humans as existence proof that it works extremely well. It only means that researchers still don't know how humans do it. We need more research and more funding in this area.
I hope they make this, open source, so kids today can now upgrade their robots with this software and take it one more step to the next advance phase. Come on we need a jump start to compete with the genius of Japan engineers.
Manufacturing in the United States is in trouble. That's bad news not just for the country's economy but for the future of innovation.
This document is part of the “How-To Guide for Most Common Measurements” centralized resource portal. This tutorial provides a detailed guide for measurement and device considerations to take temperature measurements using thermocouples. Get an introduction to thermocouples, which are inexpensive sensing devices widely used with PC-based data acquisition systems. Also review some specific thermocouple examples and learn how thermocouples work and ways to integrate them into a data acquisition measurement system.
View full PDF >
Listen to story > 
On Twitter
Become a Fan on Facebook
Subscribe to the Feed
Mapou
357 Comments
Nice Article
I am glad to see AI research finally take a decisive step away from the flawed symbolic and logic-based approaches to AI of the last century. At the same time, I hope these AI scientists also incorporate into their own research some of the excellent psychological discoveries in behavioral learning and memory that occurred in the last fifty years.
Now, if these researchers are willing to use their newest findings to at least attempt to formulate a comprehensive theory of the brain and intelligence, that would really be money well spent.
Reply