Inspired by our bodies' sensory capabilities, researchers at the Harvard John A. Paulson School of Engineering and Applied Sciences and the Wyss Institute for Biologically Inspired Engineering have developed a platform for creating soft robots with embedded sensors that can sense movement, pressure, touch, and even temperature. The research is published in Advanced Materials. "Our research represents a foundational advance in soft robotics," said Ryan Truby, first author of the paper and recent Ph.D. graduate at SEAS. "Our manufacturing platform enables complex sensing motifs to be easily integrated into soft robotic systems." Integrating sensors within soft robots has been difficult in part because most sensors, such as those used in traditional electronics, are rigid. To address this challenge, the researchers developed an organic ionic liquid-based conductive ink that can be 3D printed within the soft elastomer matrices that comprise most soft robots.

While Moog has been making significant process improvements to reduce this workload, Professor Rai at University at Buffalo, part of the SUNY System, has been mastering the art of image recognition using artificial intelligence. Thanks to funding from the UB New York State Center of Excellence in Materials Informatics (CMI), Moog engineers and Professor Rai were able to apply convolutional neural networks to metal additively manufactured parts. The result is a highly trained computer algorithm that can recognize high-quality additive manufactured parts and reject the lower quality ones. The above diagram describes this algorithm and a sample resultant image from this work. This large image has been reconstructed from 144 sub-images that were individually evaluated and colored by the computer algorithm.

We are on the verge of transforming one of society's most fundamental building blocks: manufacturing. As new technologies enable manufacturers to customize everything, these same agents are quickly turning consumers into inventors. Following the agricultural revolution some 5,000 years ago, humanity made a huge breakthrough that allowed complex societies to flourish: we specialized. It made no sense for each of us to make all our everyday products and bear the cost of necessary building equipment. So soon enough, we had our neighborhood shoemaker, carpenter, silversmith, and tailor.

This incredible 3D-printed home was built by a robot in just 48 hours. Constructed using a special quick-drying mortar, the building is the first of its kind because it can be deconstructed and reassembled at a different location. The one-story home, which has been described as a'milestone' for 3D printing construction, covers 100 square meters (1,075 square feet) and features curved walls, a living area, bedroom, kitchen and bathroom. The Italian architects behind the project said it is just a proof-of-concept for now, and did not disclose how much it cost to build. They added that the house could one day be printed on the moon to house lunar colonies.

Machine learning techniques have been used in the past using Monte Carlo samples to construct predictors of the dynamic stability of power systems. In this paper we move beyond the task of prediction and propose a comprehensive approach to use predictors, such as Decision Trees (DT), within a standard optimization framework for pre- and post-fault control purposes. In particular, we present a generalizable method for embedding rules derived from DTs in an operation decision-making model. We begin by pointing out the specific challenges entailed when moving from a prediction to a control framework. We proceed with introducing the solution strategy based on generalized disjunctive programming (GDP) as well as a two-step search method for identifying optimal hyper-parameters for balancing cost and control accuracy. We showcase how the proposed approach constructs security proxies that cover multiple contingencies while facing high-dimensional uncertainty with respect to operating conditions with the use of a case study on the IEEE 39-bus system. The method is shown to achieve efficient system control at a marginal increase in system price compared to an oracle model.

Another such invention, 3-D printing, is now scaling up. All over the world, an impressive diversity of people and organizations, ranging from startups and hobbyists to construction and engineering firms, are successfully prototyping 3-D-printed buildings. The government of Dubai has set a goal of 3-D printing 25% of every new building by 2030. Prototype single-family dwellings have been 3-D-printed in China, Italy, Russia--and Texas. Global infrastructure firm AECOM ACM 2.59% uses 3-D printing to prefabricate jail cells and hospital rooms.

If you've been following 3D printing in recent years, you may have come across a "next new thing" that sounds like it was dreamed up for the twilight zone: 4D printing, so dubbed and promoted by Skylar Tibbits, director of MIT's Self-Assembly Lab. You unlock this technology, as Rod Serling would say, with the keys of chemistry, physics, engineering and materials science, and move into a realm of both molecular properties and computer-aided design (CAD). Then you cross over into programmable materials -- and that's the term that leads to most of the news made in this field since 2014. Once they're produced on 3D printers, objects made of programmable materials continue to take shape, folding, unfolding or assembling themselves in response to outside stimuli such as light, movement, heat, pressure or water. Tibbits' TED Talk videos demonstrate multimaterial, printed 2D strands that curl themselves into the letters "MIT," and printed flat sheets of programmable materials that, once robotically cut, transform themselves into shoes. Tibbits said 4D printing started as a way to "print" robots, but taking out all the electromechanical systems.

Senvol, a 3D printing data specialist based in New York City, is developing data-driven machine learning additive manufacturing (AM) software for the U.S. Navy's Office of Naval Research (ONR). The software will help the Navy cut out the process of trial and error during material development. New York's Senvol creates additive manufacturing software that analyzes the relationships between AM process parameters and material performance. With this software to hand, ONR will be able to develop what Senvol describes as "statistically substantiated material properties" in order to reduce the conventional material characterization and testing that is needed to develop design allowables (the statistically determined material property values ascertained from test data). "Our software's capabilities will allow ONR to select the appropriate process parameters on a particular additive manufacturing machine given a target mechanical performance," commented Senvol President Annie Wang.

First invented in the 1980s by Chuck Hull, an engineer and physicist, 3D printing technology – also called additive manufacturing – is the process of making an object by depositing material, one layer at a time. Similarly to how an inkjet printer adds individual dots of ink to form an image, a 3D printer adds material where it is needed, based on a digital file. Many conventional manufacturing processes involved cutting away excess materials to make a part, and this can lead to wastage of up to 30 pounds (13.6 kilograms) for every one pound of useful material, according to the Energy Department's Oak Ridge National Laboratory in Tennessee. By contrast, with some 3D printing processes about 98 per cent of the raw material is used in the finished part, and the method can be used to make small components using plastics and metal powders, with some experimenting with chocolate and other food, as well as biomaterials similar to human cells.

Robotic assistants are one of the most enduring features when we envision our technological future. Whether they're Roombas sweeping the floor or chauffeurs in the form of self-driving cars, our collective image of the future is almost always accented by machinic helpers. Now, a team of scientists is building a robotic assistant, not necessarily to help around the home, but to fabricate 3D digital designs in real time. Dubbed the Robotic Modeling Assistant (RoMA), the system combines augmented reality (AR) with robotic modeling, allowing users to design primitive 3D models on one side of a platform while the robotic arm fabricates the object on the other. "One of the most exciting things about RoMA is the combination of AR with fast 3D printing, which makes it possible for the designer to not only receive the visual cue of their design, but also the fast, in-situ tangible feedback that otherwise couldn't be possible," Huaishu Peng, an information science doctoral student at Cornell University who helped create RoMa, told Digital Trends.