Thanks for your comment, Machinesforu. I also think it's quite interesting how quickly technology is moving ahead in this field, and the prevalence of human-robot interaction is growing. I think it won't be long before humans and robots working side by side is a very common thing indeed.
Thanks, mrdon. I agree this is an interesting approach, too, though as you point out, it is different from Rethink's. But I think it will take a few approaches to make it safe for humans and robots to work together and anything that can help facilitate this in a safe and meaningful way is heading in a good direction.
Thanks for your comment, far911. The precautions historically taken to separate robots and humans have definitely been necessary and I think you're right that this is a good step in breaking down those barriers. I think robots like Baxter show that someday humans and robots will work side by side in a factory setting, so using virtual reality first to smooth this transition and make it absolutely safe is definitely a good idea.
I agree. I find the concept of training the robot in the virtual world very interesting. I can see how this method of training will minimize the amount of errors in the industrial environment. Although the approach Rethink Robotics has taken to teach the robot using planned motion, this VR technique seems easy to program a robot as well. Good article and video.
Elizabeth, the VR environment is perfect for the first pass of training a robot. Is there an additional iteration after the first training where the paths are optimised?
In the video, one can see subtle yet seemingly wasted motion as the robot's arm moves from one point to another. This is a credit to the VR training environment, faithfully reproducing every single minute movement the human makes. Would a second pass eliminate human jitters?
A robot may not injure a human being or, through inaction, allow a human being to come to harm.
A robot must obey any orders given to it by human beings, except where such orders would conflict with the First Law.
A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
These three laws of robotics determine the idea of safe interaction. The closer the human and the robot get and the more intricate the relationship becomes, the more the risk of a human being injured rises. Nowadays in advanced societies, manufacturers employing robots solve this issue by not letting humans and robot share the workspace at any time. This is achieved by the extensive use of safe zones and cages. Thus the presence of humans is completely forbidden in the robot workspace while it is working.
So i say that this virtual reality is certainly interesting and seems wise.
I think this is an interesting use of virtual reality, especially in an era when robot artificial intelligence is getting smarter and more intuitive and we are starting to transition to a world when humans and robots will work side by side. This type of interaction historically has been unthinkable, but with innovations like this it can one day become a reality in not just the factory setting, but in restaurants, healthcare facilities and homes. It's in its early stages and you do have instances in which robots and humans work closely, but simulating this type of interaction like Johns Hopkins is doing and bringing that into the real world will accelerate this type of interaction I think.
Focus on Fundamentals consists of 45-minute on-line classes that cover a host of technologies. You learn without leaving the comfort of your desk. All classes are taught by subject-matter experts and all are archived. So if you can't attend live, attend at your convenience.