自主机器人

The ability to learn is a precondition for autonomy. With this in mind, Siemens researchers are developing knowledge networks based on deep learning-related simulated neurons and connections. Such networks can be used to generalize information by identifying associations between extraordinarily complex realms, such as the publicly accessible Internet and a company’s internal information systems. Far-reaching and generic, this technology appears to hold the potential of mimicking what humans call intuition.

The second-generation Robonaut, Robonaut 2 is a torso bolted to a pedestal and is connected to the station with wires for power and control. NASA wanted a solution to make the robot wireless so that it can move freely throughout the station and be more useful, and save astronauts' precious time.

As each mast section needs a total of 222 reliable welds, manufacturing them is an extremely labor intensive process.Until recently, STROS had to use highly skilled welders to make these sections. Although it has been using robots for 25 years, these machines could not manage the complex arc welds in narrow spaces needed for these particular components. Consequently, in order to produce a satisfactory number of mast sections it had to employ three welders per shift at three separate workstations to make these pieces. Apart from the obvious outlay this required in terms of manpower and space, STROS found it increasingly difficult to recruit the highly qualified welders needed for this work. That's why in 2007 the company decided to hold a tender for the complete robotization of its manufacturing process for mast sections. Of the four firms who participated, only the ABB group could fulfill all its requirements.