Page 8
www.us-tech.com
September, 2018
IF PERFORMANCE COUNTS,
IF RELIABILITY COUNTS,
INTERCONNECTS COUNTS A LOT.
THEN YOUR CHOICE OF
Maintaining a seamless, uninterrupted signal is the objective for any electronic system. Regardless of how elegantly designed or sophisticated the individual components might be, continuity and reliability will only be as good as the interconnects that link them. Machined pin receptacles from Mill-Max can make the difference between a product that only performs adequately and an exceptional product that lasts.
To learn more, download our new white paper at
www.mill-max.com/design.
Robots Visually Inspect and Understand Objects
Continued from page 1
up a specific object among a clutter of similar objects — a valuable skill for the kinds of machines that compa- nies like Amazon and Walmart use in their warehouses. For example, someone might
use DON to make a robot grab onto a specific spot on an object — say, the tongue of a shoe. From that, it can look at a shoe that it has never seen before, and successfully grab its tongue.
“Many approaches to ma-
nipulation can’t identify specif- ic parts of an object across the many orientations that object may encounter,” says PhD stu- dent Lucas Manuelli, who wrote a new paper about the system with lead author and fellow PhD student Pete Flo- rence, alongside MIT professor Russ Tedrake. “For example, existing algorithms would be unable to grasp a mug by its handle, especially if the mug could be in multiple orienta- tions, like upright, or on its side.” The team views potential appli-
The DON system, however, es-
sentially creates a series of coordi- nates on a given object, which serve as a visual roadmap, giving the robot a better understanding of what it needs to grasp, and where. The team trained the system to
look at objects as a series of points that make up a larger coordinate sys- tem. It can then map different points together to visualize an object’s 3D shape, similar to how panoramic
With the DON system, a robot can look at objects that it has never seen before and grasp them in specific ways.
cations not just in manufacturing settings, but also in homes. Imagine giving the system an image of a tidy house, and letting it clean while you are at work, or using an image of dishes so that the system puts your dishes away automatically. What is also noteworthy is that
none of the data was actually labeled by humans. Rather, the system is “self-supervised,” so it does not re- quire any human annotations.
Easy to Grasp Two common approaches to ro-
bot grasping involve either task-spe- cific learning, or creating a general grasping algorithm. These techniques both have obstacles: task-specific methods are difficult to generalize to other tasks, and general grasping does not get specific enough to deal with the nuances of particular tasks, like putting objects in specific spots.
photos are stitched together from multiple images. After training, if a person specifies a point on an object, the robot can take a photo of that ob- ject, and identify and match points to be able to then pick up the object at the specified point. In one set of tests done on a soft
caterpillar toy, a Kuka robotic arm powered by DON could grasp the toy’s right ear from a range of differ- ent configurations. This showed that, among other things, the system has the ability to distinguish left from right on symmetrical objects. “In factories, robots often need
complex part feeders to work reli- ably,” says Manuelli. “But a system like this that can understand objects’ orientations could just take a picture and be able to grasp and adjust the object accordingly.” Web:
www.csail.met.edu r
To see the robot in action, visit:
https://www.youtube.com/watch?v= OplLXzxxmdA&t=2s
Trapping Light... Continued from page 1
washing machines to aircraft. A commercially available, low-
cost USB memory stick already con- tains several billion transistors. In the future, the single-atom transistor developed by Schimmel and his team at KIT’s Institute of Applied Physics (APH) might considerably enhance energy efficiency in information tech- nology.
“This quantum electronics ele- Maximum Reliability. MillMaxMfg MillMaxMfg MILL-MAX MFG. CORP. Mill-Max Mfg. Corp. • 190 PINE HOLLOW ROAD OYSTER BAY, NY 11771 • (516) 922-6000
ment enables switching energies smaller than those of conventional silicon technologies by a factor of 10,000,” says Schimmel, who con- ducts research at the APH, the Insti- tute of Nanotechnology (INT), and KIT’s Material Research Center for Energy Systems (MZE). In the journal Advanced Materi-
als, the KIT researchers present the transistor that reaches the limits of miniaturization. The scientists pro- duced two minute metallic contacts. Between them, there is a gap as wide as a single metal atom. “By an electric control pulse, we
position a single silver atom into this gap and close the circuit,” Schimmel explains. “When the silver atom is
removed again, the circuit is inter- rupted.” The world’s smallest transistor
switches current through the con- trolled reversible movement of a single atom. Contrary to conventional quan- tum electronics components, the sin- gle-atom transistor does not only work at extremely low temperatures near absolute zero, but also at room tem- perature. This is a huge advantage. The single-atom transistor is
based on an entirely new technical approach. The transistor consists ex- clusively of metal, no semiconductors are used. This results in extremely low electric voltages and, as a result, extremely low energy consumption. Thus far, KIT’s single-atom
transistor had used a liquid elec- trolyte. Schimmel and his team de- signed a transistor that works in a solid electrolyte. The gel electrolyte produced by gelling an aqueous sil- ver electrolyte with pyrogenic silicon dioxide combines the advantages of a solid with the electrochemical prop- erties of a liquid. This way, both safe- ty and handling of the single-atom transistor are improved. Web:
www.kit.edu r
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124
