December 23, 2024

Crushing It: Autonomous AI Robot Creates a Shock-Absorbing Shape No Human Ever Could

Boston Universitys robot MAMA BEAR autonomously produces and evaluates energy-absorbing structures, recently accomplishing a record 75% effectiveness, with applications ranging from shipping materials to military gear. Credit: Devin Hahn, Boston University ProductionsAn autonomous robotic created a shock-absorbing shape no human ever could. Learn what it indicates for creating much safer helmets, packaging, car bumpers, and more.Within the boundaries of a laboratory in Boston Universitys College of Engineering, a robotic arm drops little, plastic things into a box specifically put on the floor to catch them as they fall. One by one, these small item– feather-light, cylindrical pieces, no larger than an inch high– fill the box. Some are blue, others red, purple, green, or black.Each of these structures is the outcome of an experiment in robotic autonomy. Operating separately and adjusting through ongoing learning, the robotic is on a mission to produce the most efficient energy-absorbing shape to ever exist.The Process of InnovationTo do this, the robotic creates a little plastic structure with a 3D printer, tape-records its sizes and shape, moves it to a flat metal surface– and after that squashes it with a pressure equivalent to an adult Arabian horse standing on a quarter. The robotic then determines just how much energy the structure taken in, how its shape changed after being compressed, and records every detail in a huge database.Then, it drops the crushed item into the box and cleans the metal plate clean, all set to print and evaluate the next piece. It will be ever-so-slightly various from its predecessor, its style and measurements modified by the robotics computer algorithm based on all previous experiments– the basis of whats called Bayesian optimization. Experiment after experiment, the 3D structures get better at absorbing the effect of getting crushed.Inside a laboratory in Boston Universitys College of Engineering, a robotic arm drops little, plastic things into a box placed perfectly on the flooring to catch them as they fall. One by one, these tiny structures– feather-light, cylindrical pieces, no larger than an inch high– fill package. Some are red, others blue, purple, green, or black. Each things is the result of an experiment in robotic autonomy. On its own, discovering as it goes, the robot is searching for, and trying to make, an object with the most effective energy-absorbing shape to ever exist. Credit: Devin Hahn, Boston University ProductionsContinuous Improvement and ApplicationsThese unrelenting iterations are possible because of the work of Keith Brown, an ENG partner professor of mechanical engineering, and his team in the KABlab. The robotic, called MAMA BEAR– brief for its prolonged full title, Mechanics of Additively Manufactured Architectures Bayesian Experimental Autonomous Researcher– has progressed considering that it was first conceived by Brown and his lab in 2018. By 2021, the laboratory had actually set the machine on its mission to make a shape that takes in the most energy, a home called its mechanical energy absorption performance. This current iteration has run continuously for over 3 years, filling dozens of boxes with more than 25,000 3D-printed structures.Practical Implications and AchievementsWhy many shapes? There are numerous uses for something that can efficiently absorb energy– say, cushioning for fragile electronics being shipped throughout the world or for knee pads and wrist guards for professional athletes. “You could draw from this library of information to make much better bumpers in a cars and truck, or product packaging devices, for example,” Brown says.To work preferably, the structures have to strike the ideal balance: they cant be so strong that they trigger damage to whatever theyre supposed to protect, however need to be strong enough to absorb impact. Before MAMA BEAR, the finest structure anyone ever observed was about 71 percent efficient at soaking up energy, states Brown. However on a cold January afternoon in 2023, Browns lab viewed their robotic hit 75 percent performance, breaking the known record. The results were just released today (May 21) in the journal Nature Communications.” When we started out, we didnt understand if there was going to be this record-breaking shape,” says Kelsey Snapp (ENG 25), a PhD student in Browns lab who oversees MAMA BEAR. “Slowly but definitely we kept inching up, and broke through.” Record-Breaking Design and Further InnovationsThe record-breaking structure looks like absolutely nothing the scientists would have expected: it has 4 points, formed like thin flower petals, and is taller and narrower than the early styles.” Were thrilled that theres so much mechanical information here, that were utilizing this to learn lessons about style more generally,” Brown says.Their substantial information is currently getting its first real-life application, helping to notify the design of brand-new helmet cushioning for United States Army soldiers. Brown, Snapp, and project partner Emily Whiting, a BU College of Arts & & Sciences associate professor of computer system science, worked with the United States Army and went through field screening to ensure helmets using their patent-pending cushioning are comfortable and offer sufficient protection from effect. The 3D structure utilized for the padding is different from the record-breaking piece– with a softer center and much shorter stature to aid with comfort.The Expanding Role of Autonomous Robots in ResearchMAMA BEAR is not Browns only autonomous research robotic. His laboratory has other “BEAR” robotics performing different jobs– like the nano BEAR, which studies the way materials act at the molecular scale utilizing an innovation called atomic force microscopy. Brown has actually likewise been dealing with Jörg Werner, an ENG assistant professor of mechanical engineering, to develop another system, understood as the PANDA– short for Polymer Analysis and Discovery Array– BEAR to check thousands of thin polymer products to discover one that works finest in a battery.” Theyre all robotics that do research study,” Brown says. “The philosophy is that theyre using maker knowing together with automation to help us study much quicker.”” Not just faster,” adds Snapp. “You can do things you couldnt usually do. We can reach a structure or objective that we wouldnt have actually been able to accomplish otherwise, since it would have been lengthy and too expensive.” He has worked closely with MAMA BEAR given that the experiments began in 2021, and gave the robotic its capability to see– called device vision– and tidy its own test plate.The Future of Autonomous ResearchThe KABlab is wishing to further demonstrate the importance of autonomous research. Brown wishes to keep working together with scientists in various fields who need to test exceptionally big numbers of structures and options. Even though they currently broke a record, “we have no capability to know if weve reached the maximum effectiveness,” Brown states, suggesting they could potentially break it once again. MOM BEAR will keep on running, pushing boundaries further, while Brown and his team see what other applications the database can be beneficial for. Theyre also checking out how the more than 25,000 crushed pieces can be unwound and refilled into the 3D printers so the material can be recycled for more experiments.” Were going to keep studying this system, since mechanical efficiency, like so lots of other product homes, is only accurately determined by experiment,” Brown states, “and using self-driving laboratories helps us choose the very best experiments and perform them as quick as possible.” Reference: “Superlative mechanical energy taking in effectiveness discovered through self-driving lab-human collaboration” 21 May 2024, Nature Communications.DOI: 10.1038/ s41467-024-48534-4.

Running independently and adapting through continuous knowing, the robotic is on a mission to develop the most efficient energy-absorbing shape to ever exist.The Process of InnovationTo do this, the robotic produces a little plastic structure with a 3D printer, tape-records its shape and size, moves it to a flat metal surface area– and then crushes it with a pressure equivalent to an adult Arabian horse standing on a quarter. The robotic, named MAMA BEAR– short for its prolonged full title, Mechanics of Additively Manufactured Architectures Bayesian Experimental Autonomous Researcher– has developed since it was first conceptualized by Brown and his lab in 2018. On a cold January afternoon in 2023, Browns lab saw their robotic hit 75 percent effectiveness, breaking the known record. The 3D structure used for the cushioning is various from the record-breaking piece– with a softer center and much shorter stature to assist with comfort.The Expanding Role of Autonomous Robots in ResearchMAMA BEAR is not Browns only autonomous research study robot.” Theyre all robotics that do research study,” Brown says.