http://WWW.ROBOTICS4U.IN
ROBOTICS 5ab356e70402d10aa42866f8 False 36 2
OK
background image not found
Found Update results for
'specific target'
5
Robot can pick up any object after inspecting it. Humans have long been masters of dexterity, a skill that can largely be credited to the help of our eyes. Robots, meanwhile, are still catching up. Certainly there's been some progress: for decades robots in controlled environments like assembly lines have been able to pick up the same object over and over again. More recently, breakthroughs in computer vision have enabled robots to make basic distinctions between objects, but even then, they don't truly understand objects' shapes, so there's little they can do after a quick pick-up. In a new paper, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), say that they've made a key development in this area of work: a system that lets robots inspect random objects, and visually understand them enough to accomplish specific tasks without ever having seen them before. The system, dubbed "Dense Object Nets" (DON), looks at objects as collections of points that serve as "visual roadmaps" of sorts. This approach lets robots better understand and manipulate items, and, most importantly, allows them to even pick up a specific object among a clutter of similar objects—a valuable skill for the kinds of machines that companies like Amazon and Walmart use in their warehouses. For example, someone might use DON to get a robot to grab onto a specific spot on an object—say, the tongue of a shoe. From that, it can look at a shoe it has never seen before, and successfully grab its tongue. "Many approaches to manipulation can't identify specific parts of an object across the many orientations that object may encounter, " says Ph.D. student Lucas Manuelli, who wrote a new paper about the system with lead author and fellow Ph.D. student Pete Florence, 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 orientations, like upright, or on its side." The team views potential applications 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're at work, or using an image of dishes so that the system puts your plates away while you're on vacation. What's also noteworthy is that none of the data was actually labeled by humans; rather, the system is "self-supervised, " so it doesn't require any human annotations. Two common approaches to robot grasping involve either task-specific 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 doesn't get specific enough to deal with the nuances of particular tasks, like putting objects in specific spots. The DON system, however, essentially creates a series of coordinates on a given object, which serve as a kind of "visual roadmap" of the objects, to give 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 system. It can then map different points together to visualize an object's 3-D shape, similar to how panoramic photos are stitched together from multiple photos. After training, if a person specifies a point on a object, the robot can take a photo of that object, and identify and match points to be able to then pick up the object at that specified point. This is different from systems like UC-Berkeley's DexNet, which can grasp many different items, but can't satisfy a specific request. Imagine an infant at 18-months old, who doesn't understand which toy you want it to play with but can still grab lots of items, versus a four-year old who can respond to "go grab your truck by the red end of it." 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 different configurations. This showed that, among other things, the system has the ability to distinguish left from right on symmetrical objects. When testing on a bin of different baseball hats, DON could pick out a specific target hat despite all of the hats having very similar designs—and having never seen pictures of the hats in training data before. "In factories robots often need complex part feeders to work reliably, " 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." In the future, the team hopes to improve the system to a place where it can perform specific tasks with a deeper understanding of the corresponding objects, like learning how to grasp an object and move it with the ultimate goal of say, cleaning a desk. The team will present their paper on the system next month at the Conference on Robot Learning in Zürich, Switzerland. Content gathered by BTM robotics training center, robotics in Bangalore, stem education in Bangalore, stem education in Bannerghatta road, stem education in JP Nagar, robotics training centres in Bannerghatta road, robotics training centres in JP Nagar, robotics training for kids, robotics training for beginners, best robotics in Bangalore.
Look, up in the sky! It's Disney's new autonomous acrobatic robot. Disney's animatronics are coming a long way from drunken pirates waving flagons of ale or hippos that wiggle their ears. In the (relatively) near future, robotic versions of Iron Man or Buzz Lightyear could be performing autonomous acrobatics overhead in Disney theme parks, thanks to the newly-unveiled Stuntronics robot. Animatronic characters have populated Disney parks for more than half a century, albeit often just looping a specific movement over and over. In recent years Disney Research has tried to make the robots more agile and interactive, developing versions that can grab objects more naturally and even juggle and play catch with visitors. Back in May, the company unveiled a prototype called Stickman. Basically a mechanical stick with two degrees of freedom, the robot could be flicked into the air like a trapeze artist, where it used a suite of sensors to tuck and roll in midair, perform a couple of backflips, and unfurl for landing. Impressive as that is, Stickman was far more stick than man. In just a few short months, the project has evolved into Stuntronics, a robot that's noticeably more human. Designed to be a kind of robotic stunt double for a human actor, the Stuntronics robot can perform the same kind of autonomous aerial stunts thanks to a similar load of sensors as Stickman, including an accelerometer, gyroscope array and laser range finding. But unlike Stickman, Stuntronics can stick its landing too. The former bot tended to land flat on its back, but the new version can land feet-first, and hit what looks like a smaller target. Not only that, it can strike a heroic pose in the air, before tucking back up ready for landing. Disney Research scientists said that during a stage show or ride, other animatronics or human actors could perform the up-close, static scenes before the Stuntronics robot is wheeled out when the character needs to fly (or fall with style). Of course, there's no guarantee that this kind of thing will ever get off the ground (literally or figuratively), but it's always exciting to peek behind the curtain at Disneyland. Content gathered by BTM robotics training center, robotics in Bangalore, stem education in Bangalore, stem education in Bannerghatta road, stem education in JP nagar, robotics training centers in Bannerghatta road, robotics training centers in JP nagar, robotics training for kids, robotics training for beginners, best robotics in Bangalore,
AI robots being fitted with special software that lets them adapt to injury like animals. It’s hard to believe that there once was a time when highly advanced robots only existed in Hollywood movies and comic books. Now, technology has reached a point where robots can do many things that human beings can do – in some cases, the two are even indistinguishable. An essay published in the International Journal of Science described an algorithm that has been specifically designed to allow robots to adapt to damage and ultimately reduce fragility. “Here we introduce an intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans, ” wrote the essay’s authors, Antoine Cully, Jeff Clune, Danesh Tarapore and Jean-Baptiste Mouret. Content gathered by BTM robotics training centre, robotics in Bangalore, stem education in Bangalore, stem education in Bannerghatta road, stem education in JP Nagar, robotics training centres in Bannerghatta road, robotics training centres in JP Nagar, robotics training for kids, robotics training for beginners, best robotics in Bangalore.
SAY HI TO CIMON, THE FIRST AI-POWERED ROBOT TO FLY IN SPACE. When you thought that Artificial Intelligence (AI) is redefining life on Earth, think again! Meet CIMON, the first AI-powered robot who was launched into space from Florida on Friday, June 29th to join the crew and assist astronauts of the International Space Station (ISS). CIMON was launched by a SpaceX rocket carrying food and supplies for the crew aboard the International Space Station. At CIMON’s pre-launch news conference, Kirk Shireman, NASA’s International Space Station (ISS) program manager, addressed that the knowledge base and ability to tap into AI in a way that is useful for the task that is done is really critical for having humans further and further away from the planet. CIMON or (Crew Interactive Mobile Companion) is programmed to answer voice commands in English. The AI-powered robot is roughly the size of a volleyball and weighs 5 kilograms. CIMON will float through the zero-gravity environment of the space station to research a database of information about the ISS. In addition to the mechanical tasks assigned, the AI-powered CIMON can even assess the moods of its human crewmates at the ISS and interact accordingly with them. An Intelligent Astronaut CIMON is the brainchild of the European aerospace company Airbus. With the artificial intelligence inside powered by IBM, AI-Powered CIMON was initially built for the German space agency. Alexander Gerst, a German astronaut currently aboard the ISS, assisted with the design of CIMON’s screen prompts and vocal controls. As per the mission description written by Airbus representatives, CIMON’s mission calls for the AI-Powered astronaut robot to work with Gerst on three separate investigations. Cimon’s tasks at ISS include experimenting with crystals, working together with Gerst to solve the Rubik’s cube and performing a complex medical experiment using itself as an ‘intelligent’ flying camera. CIMON can interact with anyone at ISS; the AI-powered robot will nod when any command is spoken in English. However, CIMON is programmed to specifically help Gerst during its first stay on the ISS. Alexander Gerst can make CIMON work by speaking commands in English like, ‘CIMON, could you please help me perform a certain experiment? or could you please help me with the procedure?'” In response, CIMON will fly towards Alexander Gerst, to start the communication. An Interactive Step Forward CIMON knows whom it is talking to through its inbuilt facial-recognition software. If you thought that CIMON would look like a mechanical robot, you are wrong. CIMON has a face of its own, a white screen with a smiley face. The astronaut AI assistant will be able to float around, by sucking air in and expelling it out through its special tubes once it is aboard the ISS. CIMON’s mission to space demonstrates researchers, the collaboration of humans and AI-powered technology for further explorations. However, it will be a long way before intelligent robots are ready to undertake principal tasks in the final frontier including helping astronauts repair damaged spacecraft systems or treating sick crewmembers. But a beginning has been made with CIMON and that day will probably be a reality soon. In its first space mission, CIMON will stay in space for a few months and is scheduled to return to earth in December. Post its return, scientists will study and assess its abilities for future implementations. With the launch of CIMON, a lifelong space-exploration association between humans and machine may have just begun. Content gathered by BTM robotics training centre, robotics in Bangalore, stem education in Bangalore, stem education in Bannerghatta road, stem education in JP Nagar, robotics training centres in Bannerghatta road, robotics training centres in JP Nagar, robotics training for kids, robotics training for beginners, best robotics in Bangalore.
Popcorn-Driven Robotic Actuators Popcorn is a cheap, biodegradable way to actuate a robot (once) People toss around the word “novel” fairly often in robotics papers, but this right here is the definition of a novel mechanism, and it might be one of the most creative ideas I’ve seen presented at a robotics conference in a long time. This is not to say that popcorn is going to completely transform robotic actuation or anything, but it’s weird enough that it might plausibly end up in some useful (if very specific) robotic applications. Why use popcorn to power an actuator? You can think of unpopped kernels of popcorn as little nuggets of stored mechanical energy, and that energy can be unleashed and transformed into force and motion when the kernel is heated. This is a very useful property, even if it’s something that you can only do once, and the fact that popcorn is super cheap and not only biodegradable but also edible are just bonuses. The “pop” in popcorn happens when enough heat is applied to vaporize the moisture inside the kernel. Over 900 kPa of internal pressure causes the yummy goo inside of the kernel to explode out through the shell, expand, and then dry. Relative to the size of the original kernel, the volume of a popped piece of popcorn has increased by a factor of at least five, although it can be much more, depending on the way the kernel was heated. Because of this variability, the first step in this research was to properly characterize the popcorn, and to do this the researchers, from Cornell’s Collective Embodied Intelligence Lab, picked up some Amish Country brand popcorn (chosen for lack of additives or postharvest treatment) in white, medium yellow, and extra small white. They heated each type using hot oil, hot air, microwaves, and direct heating with a nichrome resistance wire. The extra small white kernels, which were the cheapest at the US $4.80 per kilogram, also averaged the highest expansion ratio, exploding to 15.7 times their original size when popped in a microwave. Here’s what the researchers suggest that popcorn might be useful for in a robotics context: • Jamming actuator. “Jamming” actuators are compliant actuators full of a granular fluid (coffee grounds, for example) that will bind against itself and turn rigid when compressed, most often by applying a vacuum. If you use popcorn kernels as your granular fluid, popping them will turn the actuator rigid. It’s irreversible but effective: In one experiment, the researchers were able to use a jamming actuator filled with 36 kernels of popcorn to lift a 100-gram weight as it popped. • Elastomer actuator. An elastomer actuator is a hollow tube made out of an elastic material that’s constrained in one direction, such that if the tube is expanded, it will bend. Usually, these soft actuators are inflated with air, but you can do it with popcorn, too, and the researchers were able to use a trio of these actuators to make a sort of three-fingered hand that could grip a ball. • Origami actuator. Like elastomer actuators, origami actuators are constrained in one dimension to curling as they expand, but the origami structure allows this constraint to be built into the structure of the actuator as it’s folded. The researchers used recycled Newman’s Own Organic Popcorn bags to make their origami actuators, and 80 grams of popped kernels were able to hold up a 4 kg kettlebell. • Rigid-link gripper. Popcorn can be used indirectly as a power source by putting un-popped kernels in a flexible container in between two plates with wires attached to them. As the popcorn pops, the plates are forced apart, pulling on the wires. This can be used to actuate whatever you want, including a gripper. It’s certainly true that you could do most of these things completely reversibly by using air instead of popcorn. But, using air involves a bunch of other complicated hardware, while the popcorn only needs to be heated to work. Popcorn is also much easier to integrate into robots that are intended to be biodegradable (DARPA has been working on this), and it’s quite cheap. It’s probably best not to compare popcorn actuators directly to other types of robotic actuators, but rather to imagine situations in which a cheap or disposable robot would need a reliable single-use actuator, to open or deploy something. Content gathered by BTM robotics training centre, robotics in Bangalore, stem education in Bangalore, stem education in Bannerghatta road, stem education in JP Nagar, robotics training centres in Bannerghatta road, robotics training centres in JP Nagar, robotics training for kids, robotics training for beginners, best robotics in Bangalore.
1
false