'MacGyver' Robot Can Use Found Objects to Solve Problems
Need to MacGyver your way out of a tough spot? Golem Krang, a robot designed by researchers at Georgia Tech, may soon be able to help. A Navy grant is funding work by researchers to create an algorithm that would give the robot the ability to use objects in its environment as tools to solve problems, such as the one pictured in a simulated scenario. (Source: Georgia Tech)
Good point, William. My colleague Beth pointed out potential drawbacks to this type of robot in a comment below. It definitely remains to be seen how this is executed to determine how successful and, as you pointed out, how creative a robot can be given various scenarios.
The robot may be able to do more and better than the specific task that it's tooling was intended for, which could be very useful in an un-anticipated situation. BUT the creativity of the remote operator is what will be the really vital part. That is similar to the way a good engineer is able to use good engineering tools, but a poor engineer is only able to look at the tools. IT is all about creativity and insight, of course the more adaptive robot will wind up being much more useful.
Unfortunately the Macgyver guy used to routinely violate all kinds of physical realities. CReative? Certainly, but Correct? Very Seldom.
Watson did win against Ken Jenning, and the other champion whose name I can't remember. The game was fairly structured, but still required sifting through a lot of facts very quickly. But Watson was the size of a room, not a mobile robot.
Thanks, Watashi, that's funny. I also think there are some unwarranted, anthropomorphizing assumptions in the comments here about how much independence a machine can actually have. It's one thing to use an algorithm, perhaps as simple as a decision-tree type of analysis, for assessing simple physics (levers, e.g.), amounts of force required, etc. It's quite another to assume, or posit, that a machine can have a separate sense of self and self-awareness.
It was always the cartoonish departures from real physical reality that bothered me. But my wife always watched it because of the guy's looks. Go figure.
Robots won't become an agressive threat until they become self-aware. Likewise, people unable to pay attention long enough to become self-aware are very easy to enslave. That is the reasoning behind the training of the current generation to not be able to focus attention for more than a second or two. They won't be able to discover that they are slaves. Think about that, and become uneasy!
You're right about that, Nadine. The robot is a fascinating step forward, even if it requires mammoth tweaking. The ability of the robot to manipulate tools and the ability of the robot to "think" is quite something.
The difference will be that the robot won't be able to violate all kinds of physical laws and limitations. It will never connect a scuba tank to a garden hose to inflate an air matteres to bust open a hatchway. But a robot that was aware enough of it's surroundings to use a pipe as a lever to pry an object off of somebody would be quite an accomplishment. Of course, that would also be a big accomplishment for a whole lot of our population today. The advantages are clear but the level of creative thinking required is beyond most of our population, and probably beyond all programmers, so it will be amazing to see what gets developed.
The downside is that a robot that smart may want to replace us humans. That could be a problem.
At the Design News webinar on June 27, learn all about aluminum extrusion: designing the right shape so it costs the least, is simplest to manufacture, and best fits the application's structural requirements.
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 radio show will show what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.