Archive 08.06.2022

Technologists from Accenture, NVIDIA, General Motors, Landing AI and Intel will offer insights and best practices on how businesses can take advantage of AI to enhance their automation processes and improve efficiencies and productivity overall.

Graduate students at the Georgia Institute of Technology have built the first graffiti-painting robot system that mimics the fluidity of human movement. Aptly named GTGraffiti, the system uses motion capture technology to record human painting motions and then composes and processes the gestures to program a cable-driven robot that spray paints graffiti artwork.

A paper published in the April 2022 issue of IEEE Robotics and Automation Letters outlines the AMBER team's method and represents the first instance of combining hybrid zero dynamics (HZD)—a mathematical framework for generating stable locomotion—with a musculoskeletal model to control a robotic assistive device for walking.

This article is a cutout of my forthcoming book that you can sign up for here: https://www.danrose.ai/book

When interviewing domain experts for artificial intelligence solutions, it's essential to avoid discussing a specific solution but instead focus on the business outcome and the problem at hand. When you interview experts, they sometimes settle on a particular solution too early, even without knowing it. As the solution architect, you might also do the same and miss out on better alternatives. I often catch myself doing that as finding the perfect solution is the most satisfying part of the discovery phase. To focus on the problem and business outcome, I use the following guide as inspiration for questions.

Question: Tell me about the last time you did X (E.g. forecasted sales or did shift planning at the ice cream store)

The question works better than "How do you do forecasting?". Asking this way will provide you with a polished best-case answer. The subject matter expert will tell you how everything is supposed to be done. We all want to present our best version of ourselves, and we can be a little afraid of admitting that we jump hoops when we are busy or things are a little messy. But we are all busy, and everyday work is messy. Teresa Torres has a great example in her book "Continues Discovery Habits.": When you ask people how they buy jeans, they will tell you that they go by brand and quality. When you ask them how they bought jeans the last time, they will tell you that there was a nice discount. 

When building AI, you are looking to identify all the mess and procedure bypassing. That is where you will face challenges, and can you decrease these with AI; you can provide much value.

Question: How will you use the information provided by the AI? (E.g. Information about how many ice creams are sold on a given day)

That question focuses on the business need and outcome and not just the wish for the information or the technical solution. The value in any AI can be found in what action we decide on based on the information provided by the model. Uncovering the intended actions reveals the potential value of the AI solution. It also exposes the reasoning (And sometimes the lack of) behind the need for the AI solution.

Question: How would the solution help your new colleague?

Experienced employees can have a hard time seeing the idea of assistance (from AI or not). They can always find a solution to challenges. They don't need help. But when their inexperienced colleagues become the subject, they have an easier time seeing the value and can explain how a solution will help them.

Question: Why can't you solve this problem in any other way than AI?

That will often result in the subject telling you how they think AI will solve the problem. It uncovers potential misunderstandings about what AI can and cannot do.

It also uncovers how well thought through the idea is. Is AI just solutions chosen due to the hype, or have alternatives seriously been considered? Don't be afraid to challenge the idea of using AI. Any good decision can stand that test and is it not a good decision, you will know at some point no matter what. Better sooner than later.

Question: Why will this solution fail?

Have you ever heard people say: "I knew that would fail"? If that is true, even occasionally, then asking this question can save you trouble. You might also know the feeling that you ignored the signs of challenges when you were too excited about a solution. I certainly do.

When asking this question, I often get the answer: "We will fail because we will try to solve everything and not get it done." That is a usual challenge and making the subjects say this brings some realism to the project.

Question: Show me how you do X?

Make the person show you how they do their work. Observing a subject's actions will uncover intangible knowledge. What has become type 1 and routine for the subject will confuse you, and you can point that out and ask what is going on.

Question: What will be hard about (X, Y, Z)?

I often ask questions such as "What will be hard about getting a high accuracy?" or "What will be hard about onboarding users to the solution?". Questions like that uncovers will uncover data features that might not be as trustworthy as you thought. Answers like "We changed the way we log data for X recently" are typical here.

For tips, sign up for the book here: https://www.danrose.ai/book

Tesla’s automation strategy has shifted over the last five years. By investigating where Tesla made mistakes and where it excelled, the reader will benefit from Tesla’s hard-earned lessons and gain an understanding of how to build an automation strategy.

Dr. Sihao Sun discusses his award-winning research in the area of controlling the flight of a drone when faced with a sudden rotor failure.

Typical research in this area addressed the case where one of the four rotors in a quadrotor suddenly, spontaneously stops working. This previous research does not take into full account real-life scenarios where rotor failure is common. This includes collisions with other drones, walls, birds, and operating in degraded GPS environments.

Dr. Sihao Sun

Dr. Sihao Sun is a postdoctoral research assistant at the Robotics and Perception Group (RPG) in University of Zurich directed by Prof. Davide Scaramuzza. Currently, he is working on control and perception for aerial robots (drones).

In December 2020, he received his PhD degree in Aerospace Engineering from the Control and Simulation Group of Delft University of Technology. His works on quadrotor fault-tolerant flight control have been featured by reputable media, such as IEEE Spectrum.

Links

• Download mp3 (16.9 MB)
• Subscribe to Robohub using iTunes, RSS, or Spotify
• Support us on Patreon

During the Automate 2022 trade show on June 6-9 in Detroit, Southwest Research Institute is introducing new automation technology that allows industrial robots to visually classify work and autonomously perform tasks.

Unmanned and master/slave are two terms that are offensive to many in the community. Such terms may once have been accepted by society, but not any longer, and we are pleased to see many organizations starting to use alternative terms.

We call on you in 2022 to remove words with negative connotations, like the ones listed below, from all materials, course descriptions, department names, products, forms, reports or articles. The benefit to you is in broadening your appeal to all the community members who find those terms, if not outrightly offensive, then at the least old-fashioned and representative of a mindset that has not engaged meaningfully with creating inclusive or modern robotics.

Women in Robotics has taken the lead in curating a list of best practices in inclusive terminology, in consultation with other groups, and now we would like to share the first draft of “Terminology for 21st Century Technologists” for comment. So far we’ve considered gender, ethnicity and some disability issues. Our goal is to create a comprehensive directory of terminology, which can go through an update process periodically, just as standards do. There is obviously a little more work to be done and we want to include sections on ‘how to retire terms’, ‘how to implement changes constructively’ and more information about the process. This is where you can help us.

Please send comments in response to the first draft by June 28 2022 to reports@womeninrobotics.org

In the future, cameras could spot blackbirds feeding on grapes in a vineyard and launch drones to drive off the avian irritants, then return to watch for the next invading flock. All without a human nearby.

The 39th edition of the IEEE International Conference on Robotics and Automation (ICRA) took place at the Pennsylvania Convention Center in Philadelphia (USA) and online May 23-27. ICRA 2022 brought together the world’s top researchers and companies to share ideas and advances in the fields of robotics and automation.

Nearly 8,000 participants from academia and industry, including 4700 in person, from a total of 97 countries, joined the largest conference in robotics. Indeed, these figures reflect the evolution of the field in the last 34 years, with the last ICRA in Philadelphia (1988) only welcoming around 300 participants and a few exhibitors.

“We were thrilled to see the robotics community respond so positively to the first in-person ICRA conference since the pandemic started,” ICRA 2022 General Co-Chair George J. Pappas (University of Pennsylvania) commented. “In addition to breaking numerous records, such as in-person attendance and number of countries represented, there was an incredible amount of energy and interaction among attendees, exhibitors, competitors, and other aspects of the technical program. By all accounts, ICRA 2022 has been a major success.”

Not only did ICRA 2022 have an impact on the robotics community worldwide, but also locally in the city of Philadelphia and the state of Pennsylvania. As ICRA 2022 General Co-Chair Vijay Kumar (University of Pennsylvania) stated, “ICRA 2022 showcased Philadelphia area robotics research and development activities in academia and industry, and exposed high school and university students to exciting STEM opportunities and cutting edge research in robotics.”

The main topic of ICRA 2022 was ‘Future of Work’, with dedicated discussion sessions such as the Future of Work Forum, which featured panelists Jeff Burnstein (A3), Erik Brynjolfssonn (Stanford), Moshe Vardi (Rice University), Michael Lotito (Littler), Bernd Liepert (EuRobotics), Cecilia Laschi (NUS), and Ioana Marinescu (University of Pennsylvania). The main take-home message of the session, Chaired by Henrik Christensen (University of California, San Diego), was that employment and robot sales are correlated. “When companies hire people, they also invest in new technology. An important aspect is how we train the workforce, and how we re-train to continue to have access to a competitive workforce,” as Henrik Christensen summarized. “The panel agreed that there is a need for a comprehensive view of how we provide training, invest in technology, and provide appropriate policies to continue to grow the economy,” he finished. Another five Forum sessions were organized, covering the topics of Industry, US National Robotics Programs, Investor/Venture Capital, Start-ups, and Autonomous Driving.

Plenary and Keynote sessions were an important part of the conference, with 12 top researchers from the robotics community being invited to share their reflections on topics such as Robots, Ethics, and Society (Ayanna Howard, Ohio State University, USA); Human-Machine Partnerships and Work of the Future (Julie Shah, MIT, USA); or the Embodied Intelligence Aporia (Antonio Bicchi, University of Pisa, Italy), among others. Many research contributions were also presented during ICRA 2022 by the robotics community during the 1,500 Technical presentations and 56 Workshop & Tutorial sessions, especially by students, who represented 46% of all participants. A total of 13 Awards were given to researchers to honor their outstanding contributions in topics such as Computer Vision and Pattern Recognition, Robot Grasping, Collaborative Transportation, Legged & Aerial Robot Subterranean Exploration, Monocopters, Human-Robot Interaction for Surgery, Manipulation, Track-leg & Wheel-leg Ground Robotics, Biomimetic Tactile Sensors, Visual Odometry, and Trajectory Optimization.

Researchers and companies were able to show their robots in action in the 10 Competitions that were organized, including robots understanding where they are and moving or flying around obstacles, battling robots, robots setting dinner tables, and even examining the ethics of robots doing tasks for humans. A wide range of international teams competed in challenges like the ‘10th F1TENTH Grand Prix’ (winning place went to University of Pennsylvania students), where competitors had to build a 1:10 scaled autonomous race car, and write software for it to race head-to-head with the rest of the cars, minimizing lap time without crashing. Other competitions like the ‘FIRST LEGO League Challenge’ featured younger students, where local teams of 4th-8th graders had to design, build, and program a LEGO robot to complete autonomous missions. “Competitions provide an excellent way to validate research. Robotics research results often show great progress, but it is hard to compare different methods unless they are on the same playing field literally,” ICRA 2022 Chair of Competitions Mark Yim (University of Pennsylvania) stated. “There are also the outreach components. Competitions provide an exciting mechanism to show students and the general population what is involved in robotics,” Mark added.

On the industry side of the conference, a robot exhibition hall was prepared with nearly 100 Exhibitors offering robot displays, Tech Huddles, and demos from companies like Dyson, Motional, Built Robotics, Exyn, Ghost Robotics, NVIDIA, Technology Innovation Institute, Boston Dynamics, Pal-Robotics, KUKA Robotics, Amazon Science, Toyota Research Institute, or Tesla, among others. As ICRA 2022 Accessibility Chair Andra Keay (Silicon Valley Robotics), who also Chaired the Startup Forum, commented, “It was incredibly exciting to see such a strong participation from industry at ICRA 2022. Companies were able to showcase their technologies, recruit talented candidates, network with their peers, and discover the latest advances in robotics. Startups also were able to showcase to investors and potential customers. Tech Huddles were a great addition to the program because they gave students and faculty more opportunities to network with industry.”

As everyone could not attend ICRA 2022 in person, the Organizing Committee, the IEEE Robotics and Automation Society and OhmniLabs teamed up to offer access to the OhmiLab’s telepresence robots that were on site. Three OhmniBots were in the main exhibition hall (with all the other robots) from opening to closing from Tuesday to Thursday, with time slots aligning with Poster Sessions, networking breaks and Expo Hall hours.

ICRA 2022 continued exploring innovative ways to generate impact on robotics and automation through its partnership with the RAD Lab and several Philadelphia-based art galleries to offer a central space for art in its program. Building on the previous ICRA robotic art programs, this year’s installment explored aesthetic and creative influences on robot motion through interactive, expressive, and meditative robotic art installations. When artist-in-residence from the RAD Lab Kate Ladenheim was interviewed by David Garzón Ramos (IRIDIA) -one of the four ICRA 2022 Science Communication Awardees- about the intersection of robotics and art, she answered, “Roboticists and artists both engage in really intensive creative processes in order to make their work come to life. If a roboticist is trying to make something with a high level of intellectual and conceptual rigor, with an output that is not necessarily commercial in nature but is one that is meant to enrich the lives of people around it, then I think it crosses the realm from a project into a project that is artistic.”

This year’s edition of ICRA was a record-breaking gathering of the top roboticists and stakeholders from academia and industry, having a huge impact on the local and international community. Preparations are already in place for the 40th edition of the conference. ICRA 2023 will take place at ExCeL London between 29 May – 2 June 2023. Kaspar Althoefer (Queen Mary University of London), General Chair of ICRA 2023, stated, “We are looking forward to building on the wonderful success of ICRA 2022 in Philadelphia with the ICRA 2023 conference. The theme of the congress is ‘Embracing the Future. Making Robots for Humans’, and we are planning a wide range of workshops, sessions, networking events and tours to fit in with this theme. We are looking forward to welcoming everyone to London next year!”

We would like to thank ICRA 2022 Partners, which have also supported us in record numbers this year, as well as all participants, organization members and volunteers. Thank you for coming together again in person and online after a few years apart to imagine a new future where humans and robots work together!

We tend to take our sense of touch for granted in everyday settings, but it is vital for our ability to interact with our surroundings. Imagine reaching into the fridge to grab an egg for breakfast. As your fingers touch its shell, you can tell the egg is cold, that its shell is smooth, and how firmly you need to grip it to avoid crushing it. These are abilities that robots, even those directly controlled by humans, can struggle with.

Robots are learning to walk and work. While robot dogs are not yet man's best friend, real autonomy and reasoning will make them useful companions in industry, search and rescue and even space exploration. But you must walk before you can run and machines are learning lessons from biology for better walking robots.

Autonomous mobile robots are already being tested and used for such applications as the delivery of parcels, surveillance, search and rescue missions, planetary/space exploration, and the monitoring of the environment. For these robots to successfully complete their missions, they need to be able to operate safely and reliably in uneven outdoor terrains, without colliding with nearby obstacles.

With forecasters at NOAA's Climate Prediction Center (a division of the National Weather Service) predicting above-average hurricane activity this year, a paper published in the peer review magazine Oceanography shows that robotic ocean observing platforms can improve intensity forecasts for hurricanes and tropical storms and should be supported as a crucial component of the ocean infrastructure designed to protect the lives of coastal residents and mitigate the economic impact from storms.

When you visit us at booth 3323 , you will be able to experience a live demo of our robotic tool changer system, as well as live presentations throughout each day.