Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 5

Machine learning unravels quantum atomic vibrations in materials

Caltech scientists have developed an artificial intelligence (AI)–based method that dramatically speeds up calculations of the quantum interactions that take place in materials. In new work, the group focuses on interactions among atomic vibrations, or phonons—interactions that govern a wide range of material properties, including heat transport, thermal expansion, and phase transitions. The new machine learning approach could be extended to compute all quantum interactions, potentially enabling encyclopedic knowledge about how particles and excitations behave in materials.

Scientists like Marco Bernardi, professor of applied physics, physics, and at Caltech, and his graduate student Yao Luo (MS ‘24) have been trying to find ways to speed up the gargantuan calculations required to understand such particle interactions from first principles in real materials—that is, beginning with only a material’s atomic structure and the laws of quantum mechanics.

Last year, Bernardi and Luo developed a data-driven method based on a technique called singular value decomposition (SVD) to simplify the enormous mathematical matrices scientists use to represent the interactions between electrons and phonons in a material.

Machine learning and quantum chemistry unite to simulate catalyst dynamics

Catalysts play an indispensable role in modern manufacturing. More than 80% of all manufactured products, from pharmaceuticals to plastics, rely on catalytic processes at some stage of production. Transition metals, in particular, stand out as highly effective catalysts because their partially filled d-orbitals allow them to easily exchange electrons with other molecules. This very property, however, makes them challenging to model accurately, requiring precise descriptions of their electronic structure.

Designing efficient transition-metal catalysts that can perform under realistic conditions requires more than a static snapshot of a reaction. Instead, we need to capture the dynamic picture—how molecules move and interact at different temperatures and pressures, where atomic motion fundamentally shapes catalytic performance.

To meet this challenge, the lab of Prof. Laura Gagliardi at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME) and Chemistry Department has developed a powerful new tool that harnesses electronic structure theories and machine learning to simulate transition metal catalytic dynamics with both accuracy and speed.

New system dramatically speeds the search for polymer materials

MIT researchers developed a fully autonomous platform that can identify, mix, and characterize novel polymer blends until it finds the optimal blend. This system could streamline the design of new composite materials for sustainable biocatalysis, better batteries, cheaper solar panels, and safer drug-delivery materials.

AI-powered CRISPR could lead to faster gene therapies

Stanford Medicine researchers have developed an artificial intelligence tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help researchers—even those unfamiliar with gene editing—generate designs, analyze data and troubleshoot design flaws.

The model builds on a tool called CRISPR, a powerful gene-editing technology used to edit genomes and develop therapies for . But training on the tool to design an experiment is complicated and time-consuming—even for seasoned scientists. CRISPR-GPT speeds that process along, automating much of the experimental design and refinement. The goal, said Le Cong, Ph.D., assistant professor of pathology and genetics, who led the technology’s development, is to help scientists produce lifesaving drugs faster.

The paper is published in the journal Nature Biomedical Engineering.

Sam Altman’s longevity startup is testing a pill for a younger brain

I’ve just hopped on a video call with the CEO of Retro Biosciences, the Sam Altman-backed longevity company, when I mention it’s quite hot.

Joe Betts-LaCroix takes my passing comment as a cue to muse on the wonders of air conditioning, and how energy and heat were once synonymous — until they weren’t.

As a multi-hyphenate scientist, entrepreneur, and once-inventor of the world’s smallest computer, Betts-LaCroix is excited by paradigm change.

At the helm of what is essentially Altman’s playground for experimenting with pushing the limits of the human lifespan, Betts-LaCroix is hoping to engineer the same shift that air conditioning brought to hot summer days for your brain and body. Ideally, one day, decouple aging from decline and disease.

The experimental memory pill works by clearing out “gunk in the cells” linked to Alzheimer’s and Parkinson’s, Betts-LaCroix said. If the pill works, it will restart stalled autophagy processes in the body, cleaning up damage, “especially in the brain cells,” he said.

In contrast, other new Alzheimer’s drugs, like Eisai’s Leqembi and Eli Lilly’s Kisunla, slow down cognitive decline by flushing out sticky amyloid plaques that are a hallmark of the disease.

Continue reading “Sam Altman’s longevity startup is testing a pill for a younger brain” | >

Biohybrid crawlers can be controlled using optogenetic techniques

The body movements performed by humans and other animals are known to be supported by several intricate biological and neural mechanisms. While roboticists have been trying to develop systems that emulate these mechanisms for decades, the processes driving these systems’ motions remain very different.

Researchers at University of Illinois at Urbana-Champaign, Northwestern University and other institutes recently developed new biohybrid robots that combine living cells from mice with 3D printed hydrogel structures with wireless optoelectronics.

These robots, presented in a paper published in Science Robotics, have where the neurons can be controlled using optogenetic techniques, emulating the that support human movements.

US firm’s drone conducts strikes with next-gen loitering munition

A new military test has showcased potential that large drones can work as motherships for smaller loitering munitions. The plan could get a push following a recent air launch of a Switchblade 600 loitering munition (LM) from a General Atomics’ Block 5 MQ-9A unmanned aircraft system (UAS).

It marked the first time a Switchblade 600 has ever been launched from an unmanned aircraft.

The flight testing took place from July 22–24 at the U.S. Army Yuma Proving Grounds Test Range.

Ant swarm simulation unlocks possibilities in materials engineering, robot navigation and traffic control

Think twice about eliminating those pesky ants at your next family picnic. Their behavior may hold the key to reinventing how engineering materials, traffic control and multi-agent robots are made and utilized, thanks to research conducted by recent graduate Matthew Loges and Assistant Professor Tomer Weiss from NJIT’s Ying Wu College of Computing.

The two earned a best presentation award for their research paper titled “Simulating Ant Swarm Aggregations Dynamics” at the ACM SIGGRAPH Symposium for Computer Animation (SCA), and a qualifying poster nomination for the undergraduate research competition at the 2025 ACM SIGGRAPH (Special Interest Group on Computer Graphics and Interactive Techniques) conference.

Their study began with the observation that ant swarms behave in a manner similar to both fluid and . The duo began work in the summer of 2024. Loges became interested in research after he took an elective class with Weiss, IT 360 Computer Graphics for Visual Effects, at the Department of Informatics. This was his first project and research paper.

/* */