We introduce Action Chunking with Transformers (ACT). The key design choice is to predict a sequence of actions ("an action chunk") instead of a single action like standard Behavior Cloning. The ACT policy (figure: right) is trained as the decoder of a Conditional VAE (CVAE), i.e. a generative model. It synthesizes images from multiple viewpoints, joint positions, and style variable \(\mathcal{z}\) with a transformer encoder, and predicts a sequence of actions with a transformer decoder. The encoder of CVAE (figure: left) compresses action sequence and joint observation into \(\mathcal{z}\), the "style" of the action sequence.

The video below looks back at a remarkable six decades of artificial intelligence work at Stanford University. Stanford has been a leader in AI almost since the day the term was dreamed up by John McCarthy in the 1950s. McCarthy would join the Stanford faculty in 1962 and found the Stanford Artificial Intelligence Lab (SAIL), initiating a six-decades-plus legacy of innovation. Over the years, the field has grown to welcome a diversity of researchers and areas of exploration, including robotics, autonomous vehicles, medical diagnostics, natural language processing, and more. All the while, Stanford has been at the forefront in research and in educating the next generation of innovators in AI.

From the gridiron to the battlefield, the study of traumatic brain injury has exploded in recent years. Crucial to understanding brain injury is the ability to model the mechanical forces that compress, stretch, and twist the brain tissue and causing damage that ranges from fleeting to fatal. Models discovered by the Constitutive Artificial Neural Network outperform existing models for brain tissue. Researchers at Stanford University now say they have tapped artificial intelligence to produce a profoundly more accurate model of how deformations translate into stresses in the brain and believe that their approach could reveal a more definitive understanding of when and why concussion sometimes leads to lasting brain damage, and other times not. "The problem in brain modeling to date is that the brain is not a homogeneous tissue – it's not the same in every part of the brain. Yet, trauma is often pervasive," said Ellen Kuhl, professor of mechanical engineering, director of the Living Matter Lab, and senior author of a new study appearing in the journal, Acta Biomaterialia.

As a mechanical engineering graduate student, Alison Marsden studied how to make submarines more stealthy. Moving through the ocean, submarines make sounds that can reveal their location. While earning her PhD at Stanford University in the early 2000s, Marsden conducted U.S. Navy-funded research that used sophisticated computer modeling to optimize the shape of the submarines' hydrofoils, which work like airplane wings, generating lift and stabilizing the submarine underwater. Her aim: to minimize telltale churning sounds and enable the vessels to cruise subsurface, undetected. Marsden has always loved the science of fluid mechanics and she enjoyed the technical aspects of her submarine research, but she knew national defense work would not sustain her interest long-term.

An impressive set of robotic exoskeleton boots developed by Stanford University researchers are providing a boost to users' strides in the real world thanks to years' worth of of machine learning laboratory tests. The "exoskeleton assistance" device, first revealed on October 12 in a paper published in Nature, showcases groundbreaking results from the Stanford Biomechatronics Laboratory that could alleviate mobility issues both in senior and mobility impaired communities. "This exoskeleton personalizes assistance as people walk normally through the real world," Steve Collins, an associate professor of mechanical engineering heading the Biomechatronics Lab, said in a Stanford news release yesterday, adding that recent tests "resulted in exceptional improvements in walking speed and energy economy." To put some concrete numbers to it--people who wore the exoskeleton boots were able to walk 9 percent faster while simultaneously expending 17 percent less energy per distance traveled, according to Collins, who later explained their developments present the "largest improvements in the speed and energy of economy walking of any exoskeleton to date." Check out a video of the boots made for more than just a-walkin' below: To design the new kicks that reportedly feel like walking sans a 30-pound backpack, Stanford researchers turned to machine learning for the latest strides in exoskeleton wearables.

Some of the most exciting robotics breakthroughs are happening in the exoskeleton space. Sure, any robotic system worth its salt has the potential to effect change, but this is one of the categories where such changes can be immediately felt -- specifically, it's about improving the lives of people with limited mobility. A team out of Stanford's Biomechatronics Laboratory just published the results of years-long research into the category in Nature. The project began life -- as these things often do -- through simulations and laboratory work. The extent of the robot boot's real-world testing has thus far been limited to treadmills.

Thanks to an explosion in research in recent years exoskeletons, devices designed to augment and enhance mobility, are fast becoming a reality. But one obstacle to widespread adoption is the need for careful calibration. To work best, these devices need to be personalised to their users in a lab, and that's a problem if you want to produce a tool that can be used quickly and easily'out of the box'. Now, a team of researchers at Stanford University have developed an ankle exoskeleton that can adapt its assistance, while being worn by a user.

This study only tested the exoskeleton on healthy adults in their mid-20s, so there's still a long way to go to confirm if it can help people who need additional assistance, like older adults who walk slowly or people who work in physically demanding jobs like warehouse workers. And the device is a prototype -- there's still a long way to go before it'd be available. It's not clear how much an exoskeleton like this might cost as a medical or consumer product. Still, showing that an exoskeleton can improve movement in a real-world environment is a first for robotics, the research team said.

The human brain is an amazing computing machine. Weighing only three pounds or so, it can process information a thousand times faster than the fastest supercomputer, store a thousand times more information than a powerful laptop, and do it all using no more energy than a 20-watt lightbulb. Researchers are trying to replicate this success using soft, flexible organic materials that can operate like biological neurons and someday might even be able to interconnect with them. Eventually, soft "neuromorphic" computer chips could be implanted directly into the brain, allowing people to control an artificial arm or a computer monitor simply by thinking about it. Like real neurons -- but unlike conventional computer chips -- these new devices can send and receive both chemical and electrical signals.

Despite its small size, this soft robot can manoeuvre on solid ground and through water (pictured). A pea-sized origami robot can fold, unfold and perform a range of acrobatic moves -- potentially making it useful for many biomedical applications1. All prices are NET prices. VAT will be added later in the checkout. Tax calculation will be finalised during checkout.