We always like when a designer does something different. After all, it is easy just to do what everyone else is doing. But to see things a different way is always interesting to us. When you think of a battle bot, you probably think of a robot with wheels or tracks, attacking other robots in an arena. But [Shea Waffles Johns] created Big Cookie, a combat bot with no wheels. Instead, it is a spinning wheel of death that moves relatively slowly. The robot makes up for that by having a mini-robot helper that brings Big Cookie its prey.
With no wheels and motors for locomotion, the robot can focus on armor and weapon force. It certainly looks dangerous spinning on the floor.
Training robots to execute tasks in the real world requires data — the more, the better. The problem is that creating these datasets takes a lot of time and effort, and methods don’t scale well. That’s where Robot Learning with Semantically Imagined Experience (ROSIE) comes in.
The basic concept is straightforward: enhance training data with hallucinated elements to change details, add variations, or introduce novel distractions. Studies show a robot additionally trained on this data performs tasks better than one without.
This robot is able to deposit an object into a metal sink it has never seen before, thanks to hallucinating a sink in place of an open drawer in its original training data.
Suppose one has a dataset consisting of a robot arm picking up a coke can and placing it into an orange lunchbox. That training data is used to teach the arm how to do the task. But in the real world, maybe there is distracting clutter on the countertop. Or, the lunchbox in the training data was empty, but the one on the counter right now already has a sandwich inside it. The further a real-world task differs from the training dataset, the less capable and accurate the robot becomes.
ROSIE aims to alleviate this problem by using image diffusion models (such as Imagen) to enhance the training data in targeted and direct ways. In one example, a robot has been trained to deposit an object into a drawer. ROSIE augments this training by inpainting the drawer in the training data, replacing it with a metal sink. A robot trained on both datasets competently performs the task of placing an object into a metal sink, despite the fact that a sink never actually appears in the original training data, nor has the robot ever seen this particular real-world sink. A robot without the benefit of ROSIE fails the task.
Shape shifters have long been the stuff of speculative fiction, but researchers in China have developed a magnetoactive phase transitional matter (MPTM) that makes Odo slipping through an air vent that much more believable.
Soft robots can squeeze into small spaces or change shape as needed, but many of these systems aren’t as strong as their more mechanically rigid siblings. Inspired by the sea cucumber’s ability to manipulate its rigidity, this new MPTM can be inductively heated to a molten state to change shape as well as encapsulate or release materials. The neodymium-iron-boron (NdFeB) microparticles suspended in gallium will then return to solid form once cooled.
Applications in drug delivery, foreign object removal, and smart soldering (video after the break) probably have more real world impact than the LEGO minifig T1000 impersonation, despite how cool that looks. While a pick-and-place can do better soldering work on a factory line, there might be repair situations where a magnetically-controlled solder system could come in handy.
Doctor Who eventually made light of the fact that the Daleks were critically impaired when it came to staircases. This rover from [WildWillyRobots] doesn’t share that issue, thanks to a smart suspension design.
The rover itself is built using 3D printed components for everything from the enclosure, to the suspension system, as well as the wheels themselves. It uses a rocker-bogie design, which NASA designed for Mars-bound rovers and we often see copied for terrestrial applications. Gear motors are used for their plentiful torque, and they are placed directly within the wheels. Servos allow the individual wheels to be steered, allowing the rover to crab sideways and perform zero-radius turns.
The rocker-bogie setup does a great job of keeping the rover’s wheels touching the ground, even over rough terrain. It readily tackles a random pile of bricks with ease, in a way that many four-wheeled designs would struggle to match. Given its trials on Mars, it’s easy to call the rocker-bogie setup a thoroughly-proven design.
Too busy playing video games to have a social life? No worries. In 1985, Nintendo introduced R.O.B. — otherwise known as the Robotic Operating Buddy. It was made to play Nintendo with you. In Japan, apparently, it was the Family Computer Robot. We suppose ROB isn’t a very Japanese name. The robot was in response to the video game market crash of 1983 and was meant to keep the new Nintendo Entertainment System (NES) from being classified as a video game, which would have been a death sentence at the time of its release.
Since you might not have heard of R.O.B., you can probably guess it didn’t work out very well. In fact, the whole thing tanked in two years and resulted in only two games.
With laser cutters and 3D printers in our arsenal as well as the global toy shop of mass-produced parts and single-board computers, building a robotic project has almost never been easier. In times past though, there was more of a challenge, with a computer likely meaning a chunky desktop model and there being no plethora of motors at low prices, a robot arm required more ingenuity. [Marius Taciuc] shares with us an arm he built from the most minimal of parts back in 2003, and it’s a beautiful exercise in creative reuse.
The arm itself uses metal and FR4 for its structure, and borrows extensively from cassette tape mechanisms for motors and gears. The stronger motor for the forearm is a geared unit from a heating system, and to control all this, a relay board is hooked up to a computer’s parallel port. This last assembly is particularly ingenious, having no optocouplers handy he made his own by coupling LEDs to metal can transistors with their lids removed.
The arm was entered in a competition, and he relates a tale with which we’ll all be familiar — at the critical moment, it didn’t work. Fortunately a last-minute accidental covering of the board with a floppy disk solved the problem, as it turned out that enough light was leaking into those home-made optocouplers to trigger them. The prize was won not just on the strength of the arm, but on his explanation of the lessons learned along the way.
Back in 2019, Giant Food Stores announced it would outfit each of its 172 stores in the United States with their own robot — at the time, the largest robotic deployment in retail. The six foot (1.8 meter) tall robot, nicknamed “Marty”, was designed to roam autonomously around the store looking for spills and other potential hazards. In an effort to make these rolling monoliths a bit less imposing in their stores, Giant decided to outfit them with large googly eyes.
The future of shopping is mildly terrifying.
Perhaps it was those wide eyes, seduced by the fleeting glimpses of the wider world outside the store’s sliding doors, which lead one of these bots to break out of its retail hell and make a mad dash across the parking lot. Well, about as mad a dash as such a thing is capable of making, anyway. As this technology is still in its infancy, it’s hard to say if Giant should be congratulated or chastised for keeping a robot uprising at bay as long as it did — no doubt we’ll have more data points in the coming years.
A video posted to Facebook shows the towering bot moving smoothly between rows of cars outside the Giant in Hellertown, Pennsylvania. Staff from the store were able to stop Marty from leaving the property, and at the end of the video can be seen pushing the dejected automaton back into the store.
According to the local ABC news affiliate, a representative from Giant said Marty was “on a fresh air break” and didn’t provide any details on how this exceptionally conspicuous machine could manage to roll out the front door without anyone noticing. We’d wager Marty had a human accomplice for this caper, perhaps somebody looking to cause some mischief as a statement against robots in the workforce.
It’s worth noting that Walmart decided not to move forward with their own Marty-style robot in 2020, partly because they found shoppers didn’t like the machines moving around while they were in the store. We’d like to think it was actually because the robots kept staging increasingly daring escape attempts.
