Bad news for ophiophobes: Researchers at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) have developed a new and improved snake-inspired soft robot that is faster and more precise than its predecessor.
The robot is made using kirigami — a Japanese paper craft that relies on cuts to change the properties of a material. As the robot stretches, the kirigami surface “pops up” into a 3-D-textured surface, which grips the ground just like snake skin.
The first-generation robot used a flat kirigami sheet, which transformed uniformly when stretched. The new robot has a programmable shell, so the kirigami cuts can pop up as desired, improving the robot’s speed and accuracy.
“This is a first example of a kirigami structure with non-uniform pop-up deformations,” said Ahmad Rafsanjani, a postdoctoral fellow at SEAS and first author of the paper. “In flat kirigami, the pop-up is continuous, meaning everything pops at once. But in the kirigami shell, pop up is discontinuous. This kind of control of the shape transformation could be used to design responsive surfaces and smart skins with on-demand changes in their texture and morphology.”
The new research combined two properties of the material — the size of the cuts and the curvature of the sheet. By controlling these features, the researchers were able to program dynamic propagation of pop ups from one end to another, or control localized pop-ups.
This programmable kirigami metamaterial enables responsive surfaces and smart skins. Source: Harvard SEAS
In previous research, a flat kirigami sheet was wrapped around an elastomer actuator. In this research, the kirigami surface is rolled into a cylinder, with an actuator applying force at two ends. If the cuts are a consistent size, the deformation propagates from one end of the cylinder to the other. However, if the size of the cuts are chosen carefully, the skin can be programmed to deform at desired sequences.
“By borrowing ideas from phase-transforming materials and applying them to kirigami-inspired architected materials, we demonstrated that both popped and unpopped phases can coexists at the same time on the cylinder,” said Katia Bertoldi, the William and Ami Kuan Danoff Professor of Applied Mechanics at SEAS and senior author of the paper. “By simply combining cuts and curvature, we can program remarkably different behavior.”
Next, the researchers aim to develop an inverse design model for more complex deformations.
“The idea is, if you know how you’d like the skin to transform, you can just cut, roll, and go,” said Lishuai Jin, a graduate student at SEAS and co-author of the article.
This research was supported in part by the National Science Foundation. It was co-authored by Bolei Deng.
Using processed images, algorithms learn to recognize the real environment for autonomous driving. Source: understand.ai
Autonomous cars must perceive their environment accurately to move safely. The corresponding algorithms are trained using a large number of image and video recordings. Single image elements, such as a tree, a pedestrian, or a road sign must be labeled for the algorithm to recognize them. Understand.ai is working to improve and accelerate this labeling.
Understand.ai was founded in 2017 by computer scientist Philip Kessler, who studied at the Karlsruhe Institute of Technology (KIT), and Marc Mengler.
“An algorithm learns by examples, and the more examples exist, the better it learns,” stated Kessler. For this reason, the automotive industry needs a lot of video and image data to train machine learning for autonomous driving. So far, most of the objects in these images have been labeled manually by human staffers.
“Big companies, such as Tesla, employ thousands of workers in Nigeria or India for this purpose,” Kessler explained. “The process is troublesome and time-consuming.”
Accelerating training at understand.ai
“We at understand.ai use artificial intelligence to make labeling up to 10 times quicker and more precise,” he added. Although image processing is highly automated, final quality control is done by humans. Kessler noted that the “combination of technology and human care is particularly important for safety-critical activities, such as autonomous driving.”
The labelings, also called annotations, in the image and video files have to agree with the real environment with pixel-level accuracy. The better the quality of the processed image data, the better is the algorithm that uses this data for training.
“As training images cannot be supplied for all situations, such as accidents, we now also offer simulations based on real data,” Kessler said.
Although understand.ai focuses on autonomous driving, it also plans to process image data for training algorithms to detect tumors or to evaluate aerial photos in the future. Leading car manufacturers and suppliers in Germany and the U.S. are among the startup’s clients.
The startup’s main office is in Karlsruhe, Germany, and some of its more than 50 employees work at offices in Berlin and San Francisco. Last year, understand.ai received $2.8 million (U.S.) in funding from a group of private investors.
In 2012, Kessler started to study informatics at KIT, where he became interested in AI and autonomous driving when developing an autonomous model car in the KITCar students group. Kessler said his one-year tenure at Mercedes Research in Silicon Valley, where he focused on machine learning and data analysis, was “highly motivating” for establishing his own business.
“Nowhere else can you learn more within a shortest period of time than in a startup,” said Kessler, who is 26 years old. “Recently, the interest of big companies in cooperating with startups increased considerably.”
He said he thinks that Germany sleepwalked through the first wave of AI, in which it was used mainly in entertainment devices and consumer products.
“In the second wave, in which artificial intelligence is applied in industry and technology, Germany will be able to use its potential,” Kessler claimed.
What makes a robotics cluster successful? Proximity to university research and talent, government support of entrepreneurship, and a focus on industry end users are all important. Around the world, regions have proclaimed initiatives to become “the next Silicon Valley.” However, there have been relatively few metrics to describe robotics hubs — until now.
This week, Odense Robotics in Denmark released a report on the economic returns generated by its member companies. Both the amount of exports and the number of employees have increased by about 50 percent, according to Mikkel Christoffersen, business manager at Odense Robotics.
At the same time, the report is realistic about the ongoing challenges facing every robotics cluster, including finding qualified job candidates. As locales from India to Israel and Canada to China look to stimulate innovation, they should look at their own mixes of people, partnerships, and economic performance.
Membership and money
The Odense robotics cluster currently has 129 member companies and more than 10 research and educational institutions. That’s up from 85 in 2015 and comparable with Massachusetts, which is home to more than 150 robotics companies. The Massachusetts Robotics Cluster said it had 122 members as of 2016.
Silicon Valley Robotics says it has supported 325 robot startups, and “Roboburgh” in Pittsburgh includes more than 50 organizations..
In terms of economic performance, the Odense robotics cluster had 763 million euros ($866.3 million U.S.) in turnover, or revenue, in 2017. It expects another 20 percent increase by 2021.
Odense has been friendly to startups, with 64 founded since 2010. The Odense Robotics StartUp Hub has helped to launch 15 companies. Seventy companies, or 54 percent, of those in the Odense area have fewer than 10 employees.
Total investments in the Danish robotics cluster have risen from 322 million euros ($365.6 million) in 2015 to 750 million euros ($851.7 million) last year, with 42 percent coming from investors rather than public funding or loans.
Source: Odense Robotics
In addition, 71 local companies were robotics producers, up from 58 in 2017. The next largest category was integrators at 23. The region also boasted 509 million euros ($577.9 million) in exports in 2017, and 66 percent of its members expect to begin exports.
Market focus
The Odense Robotics report notes that a third of its member companies work with collaborative and mobile robots, representing its focus on manufacturing and supply chain customers. Those are both areas of especially rapid growth in the wider robotics ecosystem.
The global collaborative robotics market will experience a compound annual growth rate (CAGR) of 49.8 percent between 2016 and 2025, compared with a CAGR of 12.1 percent for industrial robots, predicts ABI Research. Demand from small and midsize enterprises will lead revenues to exceed $1.23 billion in 2025, said ABI.
Both Universal Robots and MiR have broadened their international reach, thanks to ownership by Teradyne Inc. in North Reading, Mass.
Robotics cluster must address talent shortage
Odense Robotics said that its robotics cluster employs 3,600 people today and expects that figure to rise to 4,900 by next year. In comparison, the Massachusetts robotics cluster employed about 4,700 people in 2016.
The Danish robotics cluster is a significant employer. Source: Odense Robotics
Even as the numbers of people grow at larger robotics companies (with 50 or more employees) or abroad, businesses in southern Denmark have to look far afield to meet their staffing needs. More than a third, or 39 percent, said they expect to hire from outside of Denmark, and 78 percent said that finding qualified recruits is the biggest barrier to growth.
The average age of employees in the Odense robotics cluster reflects experience, as well as difficulty recruiting. Fifty-five percent of them are age 40 to 60, while only 18 percent are under 30.
This reflects a larger problem for robotics developers and vendors. Even with STEM (science, technology, engineering, and mathematics) programs and attention paid to education, the demand for hardware and software engineers worldwide outstrips the available pool.
The University of Southern Denmark (SDU) is working to address this. It has increased admissions for its bachelor’s degrees in engineering and science and master’s of science programs from 930 in 2015 to 1,235 last year. The university also launched a bachelor’s in engineering for robot systems, admitting 150 students since 2017.
The Danish Technological Institute is expanding its facilities in Odense this year. Source: DTI
Another positive development that other robotics clusters can learn from Odense is that 41 percent of workers at robotics firms there went to vocational schools rather than universities.
Partnerships and prospects
Close collaboration with research institutions, fellow robotics cluster members, and international companies has helped the Odense hub grow. Seventy eight percent of cluster members collaborate among themselves, according to the report. Also, 38 percent collaborate with more than 10 companies.
The Odense robotics cluster grew out of a partnership between shipping giant Maersk A/S and SDU. The Maersk Mc-Kinney Moller Institute at SDU continues to conduct research into robotics, artificial intelligence, and systems for healthcare and the energy industry. It recently added aerial drones, soft robotics, and virtual reality to its portfolio.
Last year, the institute invested 13.4 million euros ($15.22 million) in an Industry 4.0 laboratory, and an SDU team won in the industrial robot category at the World Robot Summit Challenge in Japan.
Examples such as Universal Robots and MiR, as well as Denmark’s central position in Northern Europe, are encouraging companies to look for partners. Collaborating with companies inside and outside the Odense robotics cluster is a top priority of members, with 98 percent planning to make it a strategic focus in the next three years.
It’s only through collective action around robotics clusters that smart regions, large and small, can find their niches, build talent, and maximize the returns on their investments.
Editor’s note: A panel at the Robotics Summit & Expo in Boston on June 5 and 6, 2019, will feature speakers from different robotics clusters. Register now to attend.
The “Robat” is a fully autonomous, four-wheeled terrestrial robot with bat-like qualities that uses echolocation, also called bio sonar, to move through novel environments while mapping them based only on sound. It was developed at Tel Aviv University (TAU). Bats use echolocation to map novel environments, navigating them by emitting sound then extracting information from…
Researchers at the U.S. Army Research Laboratory (ARL) and the Robotics Institute at Carnegie Mellon University developed a new technique to quickly teach robots novel traversal behaviors with minimal human oversight. The technique allows mobile robots to navigate autonomously in environments while carrying out actions a human would expect of the robot in a given…
Brain Corp, an AI company specializing in the development of self-driving technology for robots, will lead a presentation on the specific steps required to move autonomous roboticss from the lab to live, real-world environments along with other relevant topics at the upcoming Robotics Summit & Showcase in Boston. Taking place May 23-24, 2018 and organized…
In the constantly changing landscape of today’s global digital workspace, AI’s presence grows in almost every industry. Retail giants like Amazon and Alibaba are using algorithms written by machine learning software to add value to the customer experience. Machine learning is also prevalent in the new Service Robotics world as robots transition from blind, dumb…
Robotics is undergoing fundamental change in three core areas: collaboration, autonomous mobility and increasing intelligence. Autonomous mobility technology is entering the industrial vehicle marketplace of AGVs, forklifts and tugs with new products, better navigation technologies and lower costs. Forecasters Grandview Research and IDTechEx suggest that autonomous forklifts and tugs will emerge as the standard from…
Keynotes
