The Kynix Blog - Robots

In this internet-connected age, all of our devices are constantly communicating with each other. Chances are you've got a phone, a laptop, a television, a car radio, maybe a smart home device or some other WiFi-capable appliance, along with a smartwatch or Bluetooth speaker. All of these devices are talking with each other and the wider world constantly. This is all done through radio signals. All of your devices communicate by sending and receiving radio signals at specific frequencies. But why don't cellphone calls collide against Wi-Fi signals? Mostly, it's because there are agreed-upon standards for what devices get to broadcast at what frequency. The radio spectrum is heavily partitioned so different kinds of traffic stay in their own lanes and all the data gets where it needs to go. A similar situation is playing out underwater. Under the sea, there are submarines, research vessels, robots, buoys, and tracking tags on animals, and they've all got to communicate. But radio signals don't work underwater, so the established radio communication standards are useless. Instead, underwater signals are sent via acoustic waves, but until recently there was no standard for which frequencies to use. That's all been changed now, thanks to a new standard being pioneered by NATO. Called JANUS—after the Roman god of gateways—the new system partitions the range of possible underwater communication frequencies and lets everything communicate with everything else. The JANUS protocol establishes a single frequency—11.5 kilohertz—that is reserved for initial communication between two systems, as well as frequencies for announcing a system's presence to everyone nearby. Once two crafts or robots make contact with each other, they can switch to a different frequency for extended communication. JANUS is opening the door to a better way to communicate underwater. Because of this new standard, all kinds of new collaborations are now possible. Entire fleets of robots can communicate with each other at a distance, communications buoys can send signals from the air into the water, and everyone can finally talk to one another. Considering the ocean floor is less explored than outer space, it's about time we figured out a way to communicate from there. Ref.CC3000MODRESP8266

Detecting temperature is an important function of skin. Snakes can use their skin to track warm-blooded prey, even in the dark. Now a highly sensitive, flexible sensor film could also make this characteristic available for robots and prosthetics. Whether in factories, the office or the kitchen: Robots continue to encroach on various aspects of our lives. When it comes to safety, that increases requirements for the “man-machine interface” considerably. Which is why developing sensitive robot skins has become a hot topic in robot research. After all, “collisions” can only be avoided if you can “see” your counterpart—as quickly and accurately as possible. Methods for doing so range from image processing using mechanical devices to contact-free sensor solutions. For example, scientists at the Technical University of Munich (TUM) have been working on artificial skin made of small hexagon plates with infrared, temperature and acceleration sensors. The infrared sensors register when things come close to the robot. Researchers at ETH Zurich and the California Institute of Technology (Caltech) are pursuing a more natural approach. Their temperature sensor is based on the plant material pectin. Like the snake’s extremely sensitive pit organ that can sense a mammal’s warm body up to a meter away, it can precisely measure temperatures to one hundredth of a degree. That is twice as sensitive as human skin.(A highly sensitive sensor film for robots measures temperatures with an accuracy of one hundredth of a degree. .)(Image: Caltech) “Cyber wood” as a temperature sensorDiscovering the artificial “snake organ” was actually a coincidence. It turns out that the electrical conductivity of cell walls in trees depends on temperature. That is because of the plant material pectin, which can also be used in the kitchen as a gelling agent for puddings and jams. Measurements that were taken on a type of “cyber wood” made of pectin and carbon nanotubes revealed that the higher the temperature, the more free calcium ions were formed at the contact points between two sugar molecules. Electrical conductivity increases proportionally. That is how the sensor idea was born. All that was missing was the “skin”. The answer: A 20-micrometer-thick film made of simple pectin gel laced with a calcium solution. Safe human-robot collaborationInitial testing revealed that the ultrathin transparent film that can be formed into nearly any shape can measure temperatures from 10 to 50 degrees Celsius with a precision of one hundredth of a degree. Supposedly, the “prey” that was used was a teddy bear—fresh from the microwave. To spatially resolve hot or cold sensations like human skin, researchers attached several electrodes along the long and short sides of a piece of “skin” measuring 25 square centimeters. The resulting grid made it possible to determine the position of temperature changes at specific locations. The “snake skin” is extremely easy to make and is more robust and less prone to interference than existing flexible temperature sensors equipped with transistors. After improving the computer algorithms used to analyze the electrode signals and improving the electrical contacts, the “snake skin” should be ready for a field trial in robotics or prosthetics. Ref.KY32-DS18B20KY45-LM61CIM3XKY45-LM35DT

Eight years ago, Ted Adelson’s research group at MIT’s CSAIL unveiled a new sensor technology, called GelSight, that uses physical contact with an object to provide a remarkably detailed 3D map of its surface. Now, by mounting GelSight sensors on the grippers of robotic arms, two MIT teams have given robots greater sensitivity and dexterity. The researchers presented their work in two papers at the International Conference on Robotics and Automation.In one paper, Adelson’s group uses the data from the GelSight sensor to enable a robot to judge the hardness of surfaces it touches — a crucial ability if household robots are to handle everyday objects.In the other, Russ Tedrake’s Robot Locomotion Group at CSAIL uses GelSight sensors to enable a robot to manipulate smaller objects than was previously possible.The GelSight sensor is, in some ways, a low-tech solution to a difficult problem. It consists of a block of transparent rubber — the “gel” of its name — one face of which is coated with metallic paint. When the paint-coated face is pressed against an object, it conforms to the object’s shape.The metallic paint makes the object’s surface reflective, so its geometry becomes much easier for computer vision algorithms to infer. Mounted on the sensor opposite the paint-coated face of the rubber block are three colored lights and a single camera.“[The system] has colored lights at different angles, and then it has this reflective material, and by looking at the colors, the computer … can figure out the 3D shape of what that thing is,” explains Adelson, the John and Dorothy Wilson Professor of Vision Science in the Department of Brain and Cognitive Sciences.In both sets of experiments, a GelSight sensor was mounted on one side of a robotic gripper, a device somewhat like the head of a pincer, but with flat gripping surfaces rather than pointed tips.For an autonomous robot, gauging objects’ softness or hardness is essential to deciding not only where and how hard to grasp them but how they will behave when moved, stacked, or laid on different surfaces. Tactile sensing could also aid robots in distinguishing objects that look similar.In previous work, robots have attempted to assess objects’ hardness by laying them on a flat surface and gently poking them to see how much they give. But this is not the chief way in which humans gauge hardness.Rather, our judgments seem to be based on the degree to which the contact area between the object and our fingers changes as we press on it. Softer objects tend to flatten more, increasing the contact area.The MIT researchers adopted the same approach. Wenzhen Yuan, a graduate student in mechanical engineering and first author on the paper from Adelson’s group, used confectionary molds to create 400 groups of silicone objects, with 16 objects per group. In each group, the objects had the same shapes but different degrees of hardness, which Yuan measured using a standard industrial scale.Then she pressed a GelSight sensor against each object manually and recorded how the contact pattern changed over time, essentially producing a short movie for each object. To both standardise the data format and keep the size of the data manageable, she extracted five frames from each movie, evenly spaced in time, which described the deformation of the object that was pressed.Finally, she fed the data to a neural network, which automatically looked for correlations between changes in contact patterns and hardness measurements. The resulting system takes frames of video as inputs and produces hardness scores with very high accuracy.Yuan also conducted a series of informal experiments in which human subjects palpated fruits and vegetables and ranked them according to hardness. In every instance, the GelSight-equipped robot arrived at the same rankings. Ref:KY45-AT42QT1110-AUKY45-STMPE1208SQTRKY45-MPR032EPR2

Lattice Semiconductor has introduced its first embedded vision development kit for mobile designs that require low power image processing.  The low power processing comes from the firm’s ECP5 FPGA, which is combined with an HDMI chip and CrossLink pASSP mobile bridging device.According to Lattice product marketing director, Deepak Boppana, the low power  mobile applications include machine vision, smart surveillance cameras, robotics, AR/VR, drones and Advanced Driver Assistance Systems (ADAS).The CrossLink input board includes dual-camera HD image sensors supporting the MIPI CSI-2 interface, eliminating the need for external video sources.The ECP5 base board enables low-power pre/post processing and includes support for HD image signal processing IP from Helion Vision.Also included is a NanoVesta connector to support external image sensor video inputs. The HDMI output board based on the Sil1136 non-HDCP version enables connectivity to standard HDMI displays.Ref:KY32-LFSCM3GA25EP1-6F900CKY32-ICE65L04F-TCS63I

 A team of Harvard University researchers with expertise in 3D printing, mechanical engineering, and microfluidics has demonstrated the first autonomous, untethered, entirely soft robot. This small, 3D-printed robot—nicknamed the octobot—could pave the way for a new generation of completely soft, autonomous machines.Soft robotics could revolutionize how humans interact with machines. But researchers have struggled to build entirely compliant robots. Electric power and control systems—such as batteries and circuit boards—are rigid and until now soft-bodied robots have been either tethered to an off-board system or rigged with hard components.Robert Wood, the Charles River Professor of Engineering and Applied Sciences and Jennifer A. Lewis, the Hansjorg Wyss Professor of Biologically Inspired Engineering at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) led the research. Lewis and Wood are also core faculty members of the Wyss Institute for Biologically Inspired Engineering at Harvard University."One long-standing vision for the field of soft robotics has been to create robots that are entirely soft, but the struggle has always been in replacing rigid components like batteries and electronic controls with analogous soft systems and then putting it all together," said Wood. "This research demonstrates that we can easily manufacture the key components of a simple, entirely soft robot, which lays the foundation for more complex designs.""Through our hybrid assembly approach, we were able to 3D print each of the functional components required within the soft robot body, including the fuel storage, power and actuation, in a rapid manner," said Lewis. "The octobot is a simple embodiment designed to demonstrate our integrated design and additive fabrication strategy for embedding autonomous functionality."Octopuses have long been a source of inspiration in soft robotics. These curious creatures can perform incredible feats of strength and dexterity with no internal skeleton.Harvard's octobot is pneumatic-based, i.e., it is powered by gas under pressure. A reaction inside the bot transforms a small amount of liquid fuel into a large amount of gas, which flows into the octobot's arms and inflates them like a balloon."Fuel sources for soft robots have always relied on some type of rigid components," said Michael Wehner, a postdoctoral fellow in the Wood lab and co-first author of the paper. "The wonderful thing about hydrogen peroxide is that a simple reaction between the chemical and a catalyst—in this case platinum—allows us to replace rigid power sources."To control the reaction, the team used a microfluidic logic circuit based on pioneering work by co-author and chemist George Whitesides, the Woodford L. and Ann A. Flowers University Professor and core faculty member of the Wyss. The circuit, a soft analog of a simple electronic oscillator, controls when hydrogen peroxide decomposes to gas in the octobot."The entire system is simple to fabricate, by combining three fabrication methods—soft lithography, molding and 3D printing—we can quickly manufacture these devices," said Ryan Truby, a graduate student in the Lewis lab and co-first author of the paper.The simplicity of the assembly process paves the way for more complex designs. Next, the Harvard team hopes to design an octobot that can crawl, swim and interact with its environment."This research is a proof of concept," Truby said. "We hope that our approach for creating autonomous soft robots inspires roboticists, material scientists and researchers focused on advanced manufacturing."Reference:DS1260-50DS90340I-PCXM4Z28-BR00SH1 

Inside a secretive AI nonprofit backed by Elon Musk and other Silicon Valley figures, a handful of robots designed to help out in warehouses are gradually learning how to do useful household chores.OpenAI, which was created to do basic AI research, is reprogramming robots developed by Fetch Robotics, a company that supplies warehouse automation hardware. Researchers at OpenAI are equipping the robots with software that lets them train themselves through trial and error.The effort reflects a bet that innovations in software and machine learning, rather than breakthroughs in hardware, are the way to give robotics remarkable new capabilities. Fetch makes a range of robots for warehouses, including systems that follow workers around a building, carrying items dropped into a basket. OpenAI is using a system that features a mobile base but also 3-D depth sensors, a 2-D laser scanner, and a robotic arm with seven degrees of freedom.In April, OpenAI recruited Pieter Abbeel, a professor at the University of California, Berkeley, and a leading expert on robot learning. Abbeel has shown how robots can use a machine-learning approach called deep reinforcement learning to acquire completely new skills that would be hard to program by hand, such as folding towels or retrieving items from a refrigerator. Google DeepMind, an AI subsidiary based in the U.K., uses this technique to get computers to play computer games at a superhuman level (see “Google’s AI Masters Space Invaders”).Abbeel’s robots learn tasks from scratch, using a neural network that receives sensor input and controls physical movement. The network adjusts its parameters automatically as it inches closer to its goal. A robot might try thousands of grips, for instance, in the process of learning how to hold a certain object.“If this goal can be achieved, then there will be economic and industrial benefits,” says Marc Deisenroth, an expert on reinforcement learning at Imperial College London. “Imagine a Roomba not only cleaning your floor but also doing the dishes, ironing the shirts, cleaning the windows, preparing breakfast.”Deisenroth says using off-the-shelf robots could drive costs down. “Currently, the software seems to be the bottleneck,” he adds. “However, independent of this, better hardware could also lead to substantial improvements.” Soft manipulators and elastic feet similar to a monkey’s feet are concepts that researchers have started working on, he says.Some manufacturers, including the Japanese company Fanuc, are testing reinforcement learning as a way to train industrial robots quickly in new tasks such as learning to grasp unfamiliar objects. When many robots work in parallel, the training time required is reduced accordingly. Robot researchers at Google are testing similar learning techniques.“Moving away from having to program robots by hand by endowing robots to learn autonomously is a key element for the future of robotics,” says Jens Kober, an expert on robot learning at Delft University of Technology in the Netherlands. Kober says having robots share the information they have learned will be crucial.While robots such as those made by Fetch are finding their way into many factories and warehouses, domestic robot helpers remain the stuff of science fiction. Performing seemingly simple tasks like washing dishes or folding laundry in a messy home setting is incredibly hard for a machine. A robot programmed the conventional way can easily be thrown off by an unfamiliar object or a slight variation in lighting.OpenAI confirmed that it is working with the robots from Fetch, but it declined to comment further. Melonee Wise, the company’s founder, couldn’t be reached for comment (see “Innovators Under 35: Melonee Wise”).OpenAI was created by Musk and a handful of well-known (and well-heeled) Silicon Valley entrepreneurs, including investor Peter Thiel, Y Combinator president Sam Altman, and the incubator’s cofounder Jessica Livingston. The nonprofit’s backers have committed $1 billion in funding to the project, and it is being led by Ilya Sutskever, a prominent AI researcher who left Google to join the project, and Greg Brockman, an early employee at the high-profile digital payment company Stripe.While OpenAI has committed to making the technology it develops publicly available, it could certainly benefit companies backed by Musk and Thiel, as well as those emerging from Y Combinator.