Lifeboat Foundation

A new method allows MIT’s Mini Cheetah to learn how to run fast and adapt to walking on challenging terrain. This learning-based method outperforms previous human-designed methods and allowed the Mini Cheetah to set a record for speed.
More info: https://news.mit.edu/2022/3-questions-how-mit-mini-cheetah-learns-run-fast-0317
Visit the project page at https://sites.google.com/view/model-free-speed/

The work was supported by DARPA Machine Common Sense Program, Naver Labs, MIT Biomimetic Robotics Lab, and the NSF AI Institute of AI and Fundamental Interactions. The research was conducted at the Improbable AI Lab.

Video edited by Tom Buehler.

Let your cargo follow you while you travel comfortably with the gita plus cargo carrying robot. Double the size of the gita mini robot, this robot comes with pedestrian etiquette. In fact, this robot is perfect for families who need larger cargo space, business owners, or anyone who wants an extra set of hands. The sleek design looks unique and one of a kind. In fact, this robot also has a built-in speaker. It allows you to use the mygita app to stream music from your smartphone. With the help of cameras and radar technology, this robot can see its surroundings and pair with its user. In fact, it takes just one tap for the gita plus to pair to you. It stands and self-balances, braking automatically when needed and adjusting its speed to keep pace along the way.

What does this mean for the field of robotics?

Some inventions are so strange they simply cannot help but catch the eye. Such is the case with David Bowen’s plant machete, first reported by designboom.

Robotics have come a long way as this project of an arm being controlled by the electric noises produced by a plant. Could this application be scaled up to allow for brain-controlled movement?

Continue reading “This machete is controlled by a plant yielding a robot arm” »

The last decade has brought a lot of attention to the use of microscopic robots (microrobots or nanorobots) for biomedical applications. Now, nanoengineers have developed microrobots that can swim around in the lungs and deliver medication to be used to treat bacterial pneumonia. A new study shows that the microrobots safely eliminated pneumonia-causing bacteria in the lungs of mice and resulted in 100% survival. By contrast, untreated mice all died within three days after infection.

The results are published Nature Materials in the paper, “Nanoparticle-modified microrobots for in vivo antibiotic delivery to treat acute bacterial pneumonia.”

The microrobots are made using click chemistry to attach antibiotic-loaded neutrophil membrane-coated polymeric nanoparticles to natural microalgae. The hybrid microrobots could be used for the active delivery of antibiotics in the lungs in vivo.

Scientists have been able to direct a swarm of microscopic swimming robots to clear out pneumonia microbes in the lungs of mice, raising hopes that a similar treatment could be developed to treat deadly bacterial pneumonia in humans.

The microbots are made from algae cells and covered with a layer of antibiotic nanoparticles. The algae provide movement through the lungs, which is key to the treatment being targeted and effective.

In experiments, the infections in the mice treated with the algae bots all cleared up, whereas the mice that weren’t treated all died within three days.

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here.

For decades, enterprises have jury-rigged software designed for structured data when trying to solve unstructured, text-based data problems. Although these solutions performed poorly, there was nothing else. Recently, though, machine learning (ML) has improved significantly at understanding natural language.

Continue reading “How to choose the right NLP solution” »

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here.

Over the last 10 years, neural networks have taken a giant leap from recognizing simple visual objects to creating coherent texts and photorealistic 3D renders. As computer graphics get more sophisticated, neural networks help automate a significant part of the workflow. The market demands new, efficient solutions for creating 3D images to fill the hyper-realistic space of the metaverse.

But what technologies will we use to construct this space, and will artificial intelligence help us?

The future of neural network computing could be a little soggier than we were expecting.

A team of physicists has successfully developed an ionic circuit – a processor based on the movements of charged atoms and molecules in an aqueous solution, rather than electrons in a solid semiconductor.

Since this is closer to the way the brain transports information, they say, their device could be the next step forward in brain-like computing.

Juncal Arbelaiz Mugica is a native of Spain, where octopus is a common menu item. However, Arbelaiz appreciates octopus and similar creatures in a different way, with her research into soft-robotics theory.

More than half of an octopus’ nerves are distributed through its eight arms, each of which has some degree of autonomy. This distributed sensing and information processing system intrigued Arbelaiz, who is researching how to design decentralized intelligence for human-made systems with embedded sensing and computation. At MIT, Arbelaiz is an applied math student who is working on the fundamentals of optimal distributed control and estimation in the final weeks before completing her PhD this fall.

Continue reading “Wiggling toward bio-inspired machine intelligence” »