The AlphaGo computer has been in the news recently for beating the top Go player in the world in four out of five games. This evolution in computing is a giant leap from the 90s when computers were still struggling to beat humans at chess. The landscape has indeed changed, as [Folkert] shows us with his chess computer based on a Raspberry Pi 3 and (by his own admission) too many LEDs.
The entire build is housed inside a chess board with real pieces (presumably to aid the human player) and an LED on every square. When the human makes a move, he or she inputs it into the computer via a small touch screen display. After that, the computer makes a move, indicated by lighting up the LEDs on the board and printing the move on the display. The Raspberry Pi is running the embla chess program, which has an Elo strength of about 1600.
While the computer isn’t quite powerful enough to beat Magnus Carlsen, we can only imagine how much better computers will be in the future. After all, this credit-card sized computer is doing what supercomputers did only a few decades ago. With enough Raspberry Pis, you might even be able to beat a grandmaster with your chess computer. Computer power aside, think of the advancements in fabrication technology (and access to it) which would have made this mechanical build a wonder back in the 90s too.
Continue reading “Chess Computers Improve Since 90s”
[Malte Ahlers] from Germany, After having completed a PhD in neurobiology, decided to build a human sized humanoid robot torso. [Malte] has an interest in robotics and wanted to show case some of his skills.The project is still in its early development but as you will see in the video he has achieved a nice build so far.
A1 consists of a Human sized torso with two arms, each with five (or six, including the gripper) axes of rotation, which have been based on the robolink joints from German company igus.de. The joints are tendon driven by stepper motors with a planetary gear head attached. Using an experimental controller which he has built, [Malte] can monitor the position of the axis by monitoring the encoders embedded in the joints.
The A1 torso features a head with two degrees of freedom, which is equipped with a Microsoft Kinect sensor and two Logitech QuickCam Pro 9000 cameras. With this functionality the head can spatially ”see” and ”hear”. The head also has speakers for voice output, which can be accompanied by an animated gesture on the LCD screen lip movements for example. The hands feature a simple gripping tool based on FESTO FinGripper finger to allow the picking up of misc items.
Researchers at Georgia Tech have developed a biologically inspired system to control cameras on board robots that simulate the Saccadic optokinetic system of the human eye. Its similarity to the muscular system of the human eye is uncanny.
Joshua Schultz, a Ph.D candidate, says that this system has been made possible in part to piezoelectric cellular actuator technology. Thanks to the actuators developed in their laboratory it is now possible to capture many of the characteristics associated with muscles of the human eye and its cellular structure.
The expectation is that the piezoelectric system could be used for future MRI-based surgery, furthering our ability to research and rehabilitate the human eye.