If I were to ask you to form a dream team to build a robot that will behaves like a human, how would you form your team? Would you pick scientists from different fields like : neuroscience, cognitive science, robotics, or would you rather want all your scientists be from robotics field ?
Obviously, if you need to mimic human brain your scientist would need to know it very well, so you can’t just pick all scientists from robotics field. The point here is that it makes a lot of sense to take interdisciplinary approach towards robotics. After all whatever clever algorithm we think of, for copying a human action, our brain already have one that it used, successfully, for millions of years, so why not take advantage of that?
A good example of successful interdisciplinary work in robotics was recently seen in European Commission, Information Society Technologies project called Decision in Motion. Scientists from neuroscience, robotics, computer science, and other disciplines were able to create an autonomously moving robot that uses human-like visual processing.
The important word here is “human-like”. In past, we have successfully built autonomous robots that have even crossed 152 mile of desert (in DARPA Grand Challenge);however, they did not use a model of our visual system. Most of them simply used internal maps of the environments.
For this new robot, scientists have created new algorithm that mimics human visual system more closely. They have trained neural networks that determines its location based on the environment. In addition, it has two cameras, and the ability to measure its speed relative to the environment.
Because it mimics human visual processing very closely, it behaves like human while navigating a path. For example, it leaves more space between itself and obstacles if it is moving fast, and less space otherwise.
This robot can be extended to server many practical purposes as outlined below:
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.source
This project seems to be very promising, and hopefully in the near future it produces robots that we can use in everyday lives. Perhaps, we will see that “smart” wheelchair very soon. However, we should note that behind this project was interdisciplinary work -this should the future for robotics.