Humanoid robots fascinate us - they appear in nearly every science fiction universe. Compared to Mr. Data or C-3PO, humanoids in reality are rather disappointing. Not only do they lack anything resembling human-level intelligence, but even their walking is slow and fragile - most of them only work on perfectly even ground. While we still have to wait a long time for true artificial intelligence, the recent years have brought substantial progress with respect to motion.
In 2005, Boston Dynamics (now owned by Google) presented the Big Dog quadruped. Its motions no longer look like those of a robot, but rather like those of an animal. When faced with unexpected disturbances, such as being kicked, Big Dog does not shut down and fall over, but fights to maintain balance.
During the 2013 DARPA Grand Challenge, we saw bipedal robots with similar characteristics. The Japanese company Schaft (now also owned by Google) presented a robot which is, among other things, capable of walking over grass (see end of video).
Unfortunately, much of the work on humanoids is carried out in secret. To the best of our knowledge, there are no scientific papers about Big Dog, for example. Still, these robots teach us something very important: while the companies behind them may be able to pay for the finest technologies and the brightest engineers, they do not have access to positronic brains or room-temperature superconductors - in other words, they tell us that building advanced humanoids is feasible using today's technology.
The eXperimental Robot Project aims to become to humanoid robotics what RepRap is to 3d printing. We plan to produce a robot design that an ambitious amateur can replicate for maybe a few thousand Euros. More important, however, will we publish all the design documents, CAD drawings, schematics and source code; and we will try to document what we learned on the way.
Initially, we obviously will not be able to compete with the professional robots mentioned above. Our robot will not be built from state-of-the-art components, and cost will force us to cut corners in many ways. But it will allow everyone to look inside and to improve it, and maybe, one day, we will be able to build a truly impressive humanoid - just like the best open-hardware 3d printers now match or exceed the expensive proprietary printers in terms of build quality.
It needs to be stressed that this is a highly ambitious project, and it has only just begun. Trying to predict when (or, indeed, if ever) we will have a first prototype would be foolish. We try, however, to post regular status updates in our blog.