Since they conquered the task of programming "observer" robots to track "target" robots, Stanford computer scientists are tackling the more difficult problem of getting their observers to stalk robots on the move. The autonomous observer does more than follow its target around at a discreet distance. The spy robot continuously calculates where it needs to be to ensure that the target doesn't disappear behind a column or down a hallway. The robot measures distances to walls and furniture with a horizontal laser range sensor and uses this information to create a two-dimensional floor plan. A built-in horizontal video camera creates a series of overlapping three-dimensional views of the space. The robot combines this information into a 3D rendering of the area. The robot has a second camera focused on the ceiling to help it track its position. The target robot doesn't stand a chance of blending in, with a black-and-white pattern stenciled on every side. In an associated project with Professor Ruzena Bajcsy's group at the University of Pennsylvania, Chairman of Stanford's Computer Science Department, Jean-Claude Latombe and his students are developing an observer robot that can identify and track unmarked robots and people. The 4-ft tall spies are built by Nomadic Technologies (Mountain View, CA) resemble an upright tank vacuum cleaner without the hose. An additional grant from the Army will give the researchers four more robots. These smaller additions will allow the researchers to devise methods for deploying multiple observers. E-mail: firstname.lastname@example.org, or FAX: (650) 725-1449.
Are they robots or androids? We're not exactly sure. Each talking, gesturing Geminoid looks exactly like a real individual, starting with their creator, professor Hiroshi Ishiguro of Osaka University in Japan.
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This discussion will examine what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.