#MIT CSAIL

[lou1306]

Frank Gehry, Stata Center. Home of CSAIL (CompSci & AI Lab) and Pretty Darn Weird Building 🤩 #boston #mit #csail #architecture #frankgehry (at Massachusetts Institute of Technology (MIT)) https://www.instagram.com/p/CocwACwM6V0/?igshid=NGJjMDIxMWI=

[pekasnugs]

Generating a realistic 3D world

🧬 ..::Science & Tech::.. 🧬 A new AI-powered, virtual platform uses real-world physics to simulate a rich and interactive audio-visual environment, enabling human and robotic learning, training, and experimental studies

[vlruso]

AI copilot enhances human precision for safer aviation

🚀 Exciting news for the aviation industry! MIT researchers have developed Air-Guardian, an AI system designed to act as a proactive copilot for pilots. 🛫 This innovative system uses eye-tracking and saliency maps to determine attention and identify potential risks, aiming to enhance safety and collaboration in aviation. Field tests have shown promising results, reducing flight risk and increasing success rates. 💪 But that's not all! The Air-Guardian system's adaptable nature opens doors to broader applications in other areas, such as autonomous vehicles and robotics. ��� Read the full blog post here to delve deeper into the details of this cutting-edge technology: [Link to the blog post](https://ift.tt/Lxa906u) If you're interested in the future of aviation and the integration of AI, this is a must-read! Let's continue to push the boundaries of safety and collaboration in the industry. #AI #TechInnovation #AviationSafety #MachineLearning #MITResearch List of Useful Links: AI Scrum Bot - ask about AI scrum and agile Our Telegram @itinai Twitter -  @itinaicom

[linguisticalities]

Perhaps “syllables” or “phonemes” would have been better terminology. If these discrete combinatory elements are real, it’s up the the researchers to label them with an alphabet or syllabary and transcribe the sequences they record. Nitpicky? Yes, but clarity is next to godliness, eh? 

[materialsscienceandengineering]

Using AI to discover stiff and tough microstructures

Innovative AI system from MIT CSAIL melds simulations and physical testing to forge materials with newfound durability and flexibility for diverse engineering uses.

Every time you smoothly drive from point A to point B, you're not just enjoying the convenience of your car, but also the sophisticated engineering that makes it safe and reliable. Beyond its comfort and protective features lies a lesser-known yet crucial aspect: the expertly optimized mechanical performance of microstructured materials. These materials, integral yet often unacknowledged, are what fortify your vehicle, ensuring durability and strength on every journey.  Luckily, MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) scientists have thought about this for you. A team of researchers moved beyond traditional trial-and-error methods to create materials with extraordinary performance through computational design. Their new system integrates physical experiments, physics-based simulations, and neural networks to navigate the discrepancies often found between theoretical models and practical results. One of the most striking outcomes: the discovery of microstructured composites — used in everything from cars to airplanes — that are much tougher and durable, with an optimal balance of stiffness and toughness. 

Read more.

[jcmarchi]

Interactive mouthpiece opens new opportunities for health data, assistive technology, and hands-free interactions

New Post has been published on https://thedigitalinsider.com/interactive-mouthpiece-opens-new-opportunities-for-health-data-assistive-technology-and-hands-free-interactions/

Interactive mouthpiece opens new opportunities for health data, assistive technology, and hands-free interactions

When you think about hands-free devices, you might picture Alexa and other voice-activated in-home assistants, Bluetooth earpieces, or asking Siri to make a phone call in your car. You might not imagine using your mouth to communicate with other devices like a computer or a phone remotely. 

Thinking outside the box, MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and Aarhus University researchers have now engineered “MouthIO,” a dental brace that can be fabricated with sensors and feedback components to capture in-mouth interactions and data. This interactive wearable could eventually assist dentists and other doctors with collecting health data and help motor-impaired individuals interact with a phone, computer, or fitness tracker using their mouths.

Resembling an electronic retainer, MouthIO is a see-through brace that fits the specifications of your upper or lower set of teeth from a scan. The researchers created a plugin for the modeling software Blender to help users tailor the device to fit a dental scan, where you can then 3D print your design in dental resin. This computer-aided design tool allows users to digitally customize a panel (called PCB housing) on the side to integrate electronic components like batteries, sensors (including detectors for temperature and acceleration, as well as tongue-touch sensors), and actuators (like vibration motors and LEDs for feedback). You can also place small electronics outside of the PCB housing on individual teeth.

Play video

MouthIO: Fabricating Customizable Oral User Interfaces with Integrated Sensing and Actuation Video: MIT CSAIL

The active mouth

“The mouth is a really interesting place for an interactive wearable and can open up many opportunities, but has remained largely unexplored due to its complexity,” says senior author Michael Wessely, a former CSAIL postdoc and senior author on a paper about MouthIO who is now an assistant professor at Aarhus University. “This compact, humid environment has elaborate geometries, making it hard to build a wearable interface to place inside. With MouthIO, though, we’ve developed a new kind of device that’s comfortable, safe, and almost invisible to others. Dentists and other doctors are eager about MouthIO for its potential to provide new health insights, tracking things like teeth grinding and potentially bacteria in your saliva.”

The excitement for MouthIO’s potential in health monitoring stems from initial experiments. The team found that their device could track bruxism (the habit of grinding teeth) by embedding an accelerometer within the brace to track jaw movements. When attached to the lower set of teeth, MouthIO detected when users grind and bite, with the data charted to show how often users did each.

Wessely and his colleagues’ customizable brace could one day help users with motor impairments, too. The team connected small touchpads to MouthIO, helping detect when a user’s tongue taps their teeth. These interactions could be sent via Bluetooth to scroll across a webpage, for example, allowing the tongue to act as a “third hand” to open up a new avenue for hands-free interaction.

“MouthIO is a great example how miniature electronics now allow us to integrate sensing into a broad range of everyday interactions,” says study co-author Stefanie Mueller, the TIBCO Career Development Associate Professor in the MIT departments of Electrical Engineering and Computer Science and Mechanical Engineering and leader of the HCI Engineering Group at CSAIL. “I’m especially excited about the potential to help improve accessibility and track potential health issues among users.”

Molding and making MouthIO

To get a 3D model of your teeth, you can first create a physical impression and fill it with plaster. You can then scan your mold with a mobile app like Polycam and upload that to Blender. Using the researchers’ plugin within this program, you can clean up your dental scan to outline a precise brace design. Finally, you 3D print your digital creation in clear dental resin, where the electronic components can then be soldered on. Users can create a standard brace that covers their teeth, or opt for an “open-bite” design within their Blender plugin. The latter fits more like open-finger gloves, exposing the tips of your teeth, which helps users avoid lisping and talk naturally.

This “do it yourself” method costs roughly $15 to produce and takes two hours to be 3D-printed. MouthIO can also be fabricated with a more expensive, professional-level teeth scanner similar to what dentists and orthodontists use, which is faster and less labor-intensive.

Compared to its closed counterpart, which fully covers your teeth, the researchers view the open-bite design as a more comfortable option. The team preferred to use it for beverage monitoring experiments, where they fabricated a brace capable of alerting users when a drink was too hot. This iteration of MouthIO had a temperature sensor and a monitor embedded within the PCB housing that vibrated when a drink exceeded 65 degrees Celsius (or 149 degrees Fahrenheit). This could help individuals with mouth numbness better understand what they’re consuming.

In a user study, participants also preferred the open-bite version of MouthIO. “We found that our device could be suitable for everyday use in the future,” says study lead author and Aarhus University PhD student Yijing Jiang. “Since the tongue can touch the front teeth in our open-bite design, users don’t have a lisp. This made users feel more comfortable wearing the device during extended periods with breaks, similar to how people use retainers.”

The team’s initial findings indicate that MouthIO is a cost-effective, accessible, and customizable interface, and the team is working on a more long-term study to evaluate its viability further. They’re looking to improve its design, including experimenting with more flexible materials, and placing it in other parts of the mouth, like the cheek and the palate. Among these ideas, the researchers have already prototyped two new designs for MouthIO: a single-sided brace for even higher comfort when wearing MouthIO while also being fully invisible to others, and another fully capable of wireless charging and communication.

Jiang, Mueller, and Wessely’s co-authors include PhD student Julia Kleinau, master’s student Till Max Eckroth, and associate professor Eve Hoggan, all of Aarhus University. Their work was supported by a Novo Nordisk Foundation grant and was presented at ACM’s Symposium on User Interface Software and Technology.

[moremedtech]

Atlas of human brain blood vessels highlights changes in Alzheimer’s disease

Atlas of human brain blood vessels highlights changes in Alzheimer’s disease MIT researchers characterize gene expression patterns for 22,500 brain vascular cells across 428 donors, revealing insights for Alzheimer’s onset and potential treatments. Your brain is powered by 400 miles of blood vessels that provide nutrients, clear out waste products, and form a tight protective barrier — the blood-brain barrier — that controls which molecules can enter or exit. However, it has remained unclear how these brain vascular cells change between brain regions, or in Alzheimer’s disease, at single-cell resolution. To address this challenge, a team of scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), The Picower Institute for Learning and Memory, and The Broad Institute of MIT and Harvard recently unveiled a systematic molecular atlas of human brain vasculature and its changes in Alzheimer’s disease (AD) across six brain regions, in a paper published June 1 in Nature Neuroscience. Alzheimer's disease is a leading cause of death, affects one in nine Americans over 65, and leads to debilitating and devastating cognitive decline. Impaired blood-brain barrier (BBB) function has long been associated with Alzheimer’s and other neurodegenerative diseases, such as Parkinson's and multiple sclerosis. However, the molecular and cellular underpinnings of BBB dysregulation remain ill-defined, particularly at single-cell resolution across multiple brain regions and many donors.

Navigating vascular complexity

Embarking deep into the complexities of our gray matter, the researchers created a molecular atlas of human brain vasculature across 428 donors, including 220 diagnosed with Alzheimer's and 208 controls. They characterized over 22,514 vascular cells from six different brain regions, measuring the expression of thousands of genes for each cell. The resulting datasets unveiled intriguing changes in gene expression across different brain regions and stark contrasts between individuals afflicted with AD and those without. “Alzheimer's therapy development faces a significant hurdle — brain alterations commence decades before cognitive signs make their debut, at which point it might already be too late to intervene effectively,” comments MIT CSAIL principal investigator and electrical engineering and computer science (EECS) Professor Manolis Kellis. “Our work charts the terrain of vascular changes, one of the earliest markers of Alzheimer's, across multiple brain regions, providing a map to guide biological and therapeutic investigations earlier in disease progression.” Kellis is the study's co-senior author, along with MIT Professor Li-Huei Tsai, director of the Picower Institute and the Picower Professor in the Department of Brain and Cognitive Sciences.

The little cells that could

The threads of our human brain vasculature, and every part of our brain and body, are composed of millions of cells, all sharing the same DNA code, but each expressing a different subset of genes, which define its functional roles and distinct cell type. Using the distinct gene expression signatures of different cerebrovascular cells, the researchers distinguished 11 types of vascular cells. These included endothelial cells that line the interior surface of blood vessels and control which substances pass through the BBB, pericytes that wrap around small vessels and provide structural support and blood flow control, smooth muscle cells that form the middle layer of large vessels and whose contraction and relaxation regulates blood flow and pressure, fibroblasts that surround blood vessels and hold them in place, and they distinguished arteriole, venule, and capillary veins responsible for the different stages of blood oxygen exchange. The abundance of these vascular cell types differed between brain regions, with neocortical regions showing more capillary endothelial cells and fewer fibroblasts than subcortical regions, highlighting the regional heterogeneity of the BBB.

Clues and suspects

Armed with these annotations, the next phase was studying how each of these cell types change in AD, revealing 2,676 genes whose expression levels change significantly. They found that capillary endothelial cells, responsible for transport, waste removal, and immune surveillance, showed the most changes in AD, including genes involved in clearance of amyloid beta, one of the pathological hallmarks of AD, providing insights on the potential mechanistic implications of vascular dysregulation on AD pathology. Other dysregulated processes included immune function, glucose homeostasis, and extracellular matrix organization, which were all shared among multiple vascular cell types, and also cell-type-specific changes, including growth factor receptors in pericytes, and transporter and energy in endothelial cells, and cellular response to amyloid beta in smooth muscle cells. Regulation of insulin sensing and glucose homeostasis in particular suggested important connections between lipid transport and Alzheimer’s regulated by the vasculature and blood-brain-barrier cells, which could hold promise for new therapeutic clues. “Single-cell RNA sequencing provides an extraordinary microscope to peer into the intricate machinery of life, and ‘see’ millions of RNA molecules bustling with activity within each cell,” says Kellis, who is also a member of the Broad Institute. “This level of detail was inconceivable just a few years ago, and the resulting insights can be transformative to comprehend and combat complex psychiatric and neurodegenerative disease."

Maestros of dysregulation

Genes do not act on a whim, and they do not act alone. Cellular processes are governed by a complex cast of regulators, or transcription factors, that dictate which groups of genes should be turned on or off in different conditions, and in different cell types. These regulators are responsible for interpreting our genome, the ‘book of life,’ and turning it into the myriad of distinct cell types in our bodies and in our brains. These regulators might be responsible when something goes wrong, and they could also be critical in fixing things and restoring healthy cellular states. With thousands of genes showing altered expression levels in Alzheimer’s disease, the researchers then sought to find the potential masterminds behind these changes. They asked if common regulatory control proteins target numerous altered genes, which may provide candidate therapeutic targets to restore the expression levels of large numbers of target genes. Indeed, they found several such ‘master controllers,’ involved in regulating endothelial differentiation, inflammatory response, and epigenetic state, providing potential intervention points for drug targets against AD.

Cellular murmurings

Cells do not function in isolation; rather, they rely on communication with each other to coordinate biological processes. This intercellular communication is particularly complex within the cellular diversity of the brain, given the many factors involved in sensing, memory formation, knowledge integration, and consciousness. In particular, vascular cells have intricate interactions with neurons, microglia, and other brain cells, which take on heightened significance during pathological events, such as in Alzheimer's disease, where dysregulation of this cellular communication can contribute to the progression of the disease. The researchers found that interactions from capillary endothelial cells to neurons, microglia, and astrocytes were highly increased in AD, while interactions in the reverse direction, from neurons and astrocytes to capillary endothelial cells, were decreased in AD. This asymmetry could provide important cues for potential interventions targeting the vasculature and specifically capillary endothelial cells, with ultimate broad positive impacts on the brain. “The dynamics of vascular cell interactions in AD provide an entry point for brain interventions and potential new therapies,” says Na Sun, an EECS graduate student and MIT CSAIL affiliate and first author on the study. “As the blood-brain barrier prevents many drugs from influencing the brain, perhaps we could instead manipulate the blood-brain barrier itself, and let it spread beneficiary signals to the rest of the brain. Our work provides a blueprint for cerebrovasculature interventions in Alzheimer's disease, by unraveling how cellular communication can mediate the impact of genetic variants in AD."

Going off script: genetic plot twists

Disease onset in our bodies (and in our brains) is shaped by a combination of genetic predispositions and environmental exposures. On the genetic level, most complex traits are shaped by hundreds of minuscule sequence alterations, known as single-nucleotide polymorphisms (or SNPs, pronounced snips), most of which act through subtle changes in gene expression levels. No matter how subtle their effects might be, these genetic changes can reveal causal contributors to disease, which can greatly increase the chance of therapeutic success for genetically-supported target genes, compared to targets lacking genetic support. To understand how genetic differences associated with Alzheimer’s might act in the vasculature, the researchers then sought to connect genes that showed altered expression in Alzheimer’s with genetic regions associated with increased Alzheimer’s risk through genetic studies of thousands of individuals. They linked the genetic variants (SNPs) to candidate target genes using three lines of evidence: physical proximity in the three-dimensional folded genome, genetic variants that affect gene expression, and correlated activity between distant regulatory regions and target genes that go on and off together between different conditions. This resulted in not just one hit, but 125 genetic regions, where Alzheimer’s-associated genetic variants were linked to genes with disrupted expression patterns in Alzheimer’s disease, suggesting they might mediate these causal genetic effects, and thus may be good candidates for therapeutic targeting. Some of these predicted hits were direct, where the genetic variant acted directly on a nearby gene. Others were indirect when the genetic variant instead affected the expression of a regulator, which then affected the expression of its target genes. And yet others were predicted to be indirect through cell-cell communication networks.

ApoE4 and cognitive decline

While most genetic effects are subtle, both in Alzheimer’s and nearly all complex disorders, exceptions do exist. One such exception is FTO in obesity, which increases obesity risk by one standard deviation. Another one is apolipoprotein E (ApoE) in Alzheimer’s disease, where the E4 versus E3 allele increases risk more than 10-fold for carriers of two risk alleles — those who inherited one ‘unlucky’ copy from each parent. With such a strong effect size, the researchers then asked if ApoE4 carriers showed specific changes in vascular cells that were not found in ApoE3 carriers. Indeed, they found abundance changes associated with the ApoE4 genotype, with capillary endothelial cells and pericytes showing extensive down-regulation of transport genes. This has important implications for potential preventive treatments targeting transport in ApoE4 carriers, especially given the cholesterol transporter roles of ApoE, and the increasingly recognized role of lipid metabolism in Alzheimer’s disease. "Unearthing these AD-differential genes gives us a glimpse into how they may be implicated in the deterioration or dysfunction of the brain's protective barrier in Alzheimer's patients, shedding light on the molecular and cellular roots of the disease's development," says Kellis. "They also open several avenues for therapeutic development, hinting at a future where these entry points might be harnessed for new Alzheimer's treatments targeting the blood-brain barrier directly. The possibility of slowing or even halting the disease's progression is truly exciting.” Translating these findings into viable therapeutics will be a journey of exploration, demanding rigorous preclinical and clinical trials. To bring these potential therapies to patients, scientists need to understand how to target the discovered dysregulated genes safely and effectively and determine whether modifying their activity can ameliorate or reverse AD symptoms, which requires extensive collaborations between medical doctors and engineers across both academia and industry. “This is a tour de force impressive case series,” says Elizabeth Head, vice chair for pathology research and pathology professor at the University of California at Irvine, who was not involved in the research. “A novel aspect of this study was also the methodological approach, which left the vasculature intact, as compared to previous work where blood vessel enrichment protocol was applied. Manolis Kellis and his colleagues show clear evidence of neurovascular unit dysregulation in AD and it is exciting to see known and novel pathways being identified that will accelerate discoveries at the protein level. Many DEGs associated with AD are linked to lipid/cholesterol metabolism, to AD genetic risk factors (including ApoE) and inflammation. The potential for the ApoE genotype in mediating cerebrovascular function will also lead to possible new mouse models that will capture the human phenotype more closely with respect to the vascular contributions to dementia in humans. The regional differences in DEGs are fascinating and will guide future neuropathology studies in the human brain and drive novel hypotheses.” "The predominant focus in AD research over the past 10 years has been on studying microglia, the resident macrophage-like cells of the brain,” adds Ryan Corces, an assistant professor of neurology at the University of California at San Francisco who was also not involved in the work. “While microglia certainly play a key role in disease pathogenesis, it has become increasingly clear through studies such as this one that vascular cells may also be critically involved in the disease. From blood-brain barrier leakage to an enhanced need for debris clearance, the vascular cells of the brain play an important part in this complex disease. This study, and others like it, have begun picking apart the underlying molecular changes that occur in vascular cells, showing which genes appear dysregulated and how those changes may interact to alter vascular cell functions. Together with the mounting evidence of vascular involvement in AD, this work provides an important foundation for guiding therapeutic interventions against blood-brain barrier dysfunction in AD, especially during the preclinical or prodromal stages of the disease, where the blood-brain barrier may be playing a central role.” Sun, Kellis, and Tsai wrote the paper alongside Leyla Anne Akay, Mitchell H. Murdock, Yongjin Park, Fabiola Galiana-Melendez, Adele Bubnys, Kyriaki Galani, Hansruedi Mathys, Xueqiao Jiang, and Ayesha P. Ng of MIT and David A. Bennett of the Rush Alzheimer’s Disease Center in Chicago. This work was supported, in part, by National Institutes of Health grants, the Cure Alzheimer’s Foundation CIRCUITS consortium, the JPB Foundation, Robert A. and Renee Belfer, and a Takeda Fellowship from the Takeda Pharmaceutical Company. Source: MIT Read the full article

[chavisory]

[Image description: Tweet from MIT CSAIL depicts an IBM slide from 1979, which reads: “A computer can never be held accountable.

Therefore a computer must never make a management decision.”]

[sunaleisocial]

Advancing urban tree monitoring with AI-powered digital twins

New Post has been published on https://sunalei.org/news/advancing-urban-tree-monitoring-with-ai-powered-digital-twins/

Advancing urban tree monitoring with AI-powered digital twins

The Irish philosopher George Berkely, best known for his theory of immaterialism, once famously mused, “If a tree falls in a forest and no one is around to hear it, does it make a sound?”

What about AI-generated trees? They probably wouldn’t make a sound, but they will be critical nonetheless for applications such as adaptation of urban flora to climate change. To that end, the novel “Tree-D Fusion” system developed by researchers at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), Google, and Purdue University merges AI and tree-growth models with Google’s Auto Arborist data to create accurate 3D models of existing urban trees. The project has produced the first-ever large-scale database of 600,000 environmentally aware, simulation-ready tree models across North America.

“We’re bridging decades of forestry science with modern AI capabilities,” says Sara Beery, MIT electrical engineering and computer science (EECS) assistant professor, MIT CSAIL principal investigator, and a co-author on a new paper about Tree-D Fusion. “This allows us to not just identify trees in cities, but to predict how they’ll grow and impact their surroundings over time. We’re not ignoring the past 30 years of work in understanding how to build these 3D synthetic models; instead, we’re using AI to make this existing knowledge more useful across a broader set of individual trees in cities around North America, and eventually the globe.”

Tree-D Fusion builds on previous urban forest monitoring efforts that used Google Street View data, but branches it forward by generating complete 3D models from single images. While earlier attempts at tree modeling were limited to specific neighborhoods, or struggled with accuracy at scale, Tree-D Fusion can create detailed models that include typically hidden features, such as the back side of trees that aren’t visible in street-view photos.

The technology’s practical applications extend far beyond mere observation. City planners could use Tree-D Fusion to one day peer into the future, anticipating where growing branches might tangle with power lines, or identifying neighborhoods where strategic tree placement could maximize cooling effects and air quality improvements. These predictive capabilities, the team says, could change urban forest management from reactive maintenance to proactive planning.

A tree grows in Brooklyn (and many other places)

The researchers took a hybrid approach to their method, using deep learning to create a 3D envelope of each tree’s shape, then using traditional procedural models to simulate realistic branch and leaf patterns based on the tree’s genus. This combo helped the model predict how trees would grow under different environmental conditions and climate scenarios, such as different possible local temperatures and varying access to groundwater.

Now, as cities worldwide grapple with rising temperatures, this research offers a new window into the future of urban forests. In a collaboration with MIT’s Senseable City Lab, the Purdue University and Google team is embarking on a global study that re-imagines trees as living climate shields. Their digital modeling system captures the intricate dance of shade patterns throughout the seasons, revealing how strategic urban forestry could hopefully change sweltering city blocks into more naturally cooled neighborhoods.

“Every time a street mapping vehicle passes through a city now, we’re not just taking snapshots — we’re watching these urban forests evolve in real-time,” says Beery. “This continuous monitoring creates a living digital forest that mirrors its physical counterpart, offering cities a powerful lens to observe how environmental stresses shape tree health and growth patterns across their urban landscape.”

AI-based tree modeling has emerged as an ally in the quest for environmental justice: By mapping urban tree canopy in unprecedented detail, a sister project from the Google AI for Nature team has helped uncover disparities in green space access across different socioeconomic areas. “We’re not just studying urban forests — we’re trying to cultivate more equity,” says Beery. The team is now working closely with ecologists and tree health experts to refine these models, ensuring that as cities expand their green canopies, the benefits branch out to all residents equally.

It’s a breeze

While Tree-D fusion marks some major “growth” in the field, trees can be uniquely challenging for computer vision systems. Unlike the rigid structures of buildings or vehicles that current 3D modeling techniques handle well, trees are nature’s shape-shifters — swaying in the wind, interweaving branches with neighbors, and constantly changing their form as they grow. The Tree-D fusion models are “simulation-ready” in that they can estimate the shape of the trees in the future, depending on the environmental conditions.

“What makes this work exciting is how it pushes us to rethink fundamental assumptions in computer vision,” says Beery. “While 3D scene understanding techniques like photogrammetry or NeRF [neural radiance fields] excel at capturing static objects, trees demand new approaches that can account for their dynamic nature, where even a gentle breeze can dramatically alter their structure from moment to moment.”

The team’s approach of creating rough structural envelopes that approximate each tree’s form has proven remarkably effective, but certain issues remain unsolved. Perhaps the most vexing is the “entangled tree problem;” when neighboring trees grow into each other, their intertwined branches create a puzzle that no current AI system can fully unravel.

The scientists see their dataset as a springboard for future innovations in computer vision, and they’re already exploring applications beyond street view imagery, looking to extend their approach to platforms like iNaturalist and wildlife camera traps.

“This marks just the beginning for Tree-D Fusion,” says Jae Joong Lee, a Purdue University PhD student who developed, implemented and deployed the Tree-D-Fusion algorithm. “Together with my collaborators, I envision expanding the platform’s capabilities to a planetary scale. Our goal is to use AI-driven insights in service of natural ecosystems — supporting biodiversity, promoting global sustainability, and ultimately, benefiting the health of our entire planet.”

Beery and Lee’s co-authors are Jonathan Huang, Scaled Foundations head of AI (formerly of Google); and four others from Purdue University: PhD students Jae Joong Lee and Bosheng Li, Professor and Dean’s Chair of Remote Sensing Songlin Fei, Assistant Professor Raymond Yeh, and Professor and Associate Head of Computer Science Bedrich Benes. Their work is based on efforts supported by the United States Department of Agriculture’s (USDA) Natural Resources Conservation Service and is directly supported by the USDA’s National Institute of Food and Agriculture. The researchers presented their findings at the European Conference on Computer Vision this month. 

[fromdevcom]

Robotics, a field at the intersection of computer science, engineering, and artificial intelligence, has seen exponential growth in recent years. As the demand for skilled robotics engineers and researchers continues to rise, choosing the right university to pursue a robotics degree is more crucial than ever. Here, we explore some of the best universities worldwide known for their excellence in robotics education and research. Massachusetts Institute of Technology (MIT), USA When it comes to robotics, MIT is often the first name that comes to mind. The university's Computer Science and Artificial Intelligence Laboratory (CSAIL) is a powerhouse of innovation, conducting groundbreaking research in areas such as autonomous vehicles, robotic manipulation, and human-robot interaction. MIT's hands-on approach and access to cutting-edge technology make it a top choice for aspiring roboticists. Stanford University, USA Stanford University is renowned for its research in artificial intelligence and robotics. The Stanford Robotics Lab is at the forefront of developing robots capable of interacting with humans in dynamic environments. The university's location in Silicon Valley also provides students with unparalleled opportunities to collaborate with leading tech companies and startups. Carnegie Mellon University (CMU), USA Carnegie Mellon University has a long-standing reputation for excellence in robotics. CMU's Robotics Institute is one of the largest and most comprehensive robotics research centers in the world. The university offers a variety of robotics programs, including undergraduate, master's, and PhD degrees, all of which emphasize interdisciplinary research and real-world applications. University of Tokyo, Japan Japan has been a leader in robotics for decades, and the University of Tokyo is at the heart of this innovation. The university's Department of Mechano-Informatics is known for its work in humanoid robotics and robotic systems. The university's close ties with Japan's robotics industry provide students with unique opportunities to engage in cutting-edge research and development. ETH Zurich, Switzerland ETH Zurich is one of Europe's top universities for engineering and technology, and its robotics program is no exception. The university's Autonomous Systems Lab focuses on developing intelligent systems that can operate in complex and dynamic environments. ETH Zurich's strong emphasis on research and collaboration with industry partners makes it a top destination for students interested in robotics. University of Cambridge, UK The University of Cambridge is known for its rigorous academic programs, and its robotics research is no different. The university's Department of Engineering offers a range of robotics courses and research opportunities, with a focus on autonomous systems and machine learning. Cambridge's strong connections with the UK robotics industry provide students with valuable hands-on experience. Technical University of Munich (TUM), Germany Germany is a global leader in engineering, and TUM is at the forefront of robotics research in Europe. The university's Institute for Cognitive Systems conducts cutting-edge research in areas such as robot perception, learning, and human-robot collaboration. TUM's robotics programs are known for their interdisciplinary approach and strong industry partnerships. National University of Singapore (NUS), Singapore NUS is a leading university in Asia and has rapidly gained a reputation for its robotics research. The university's Advanced Robotics Centre focuses on developing innovative robotic systems for various applications, including healthcare, manufacturing, and urban environments. NUS's strategic location in Singapore, a hub for technology and innovation, provides students with excellent opportunities for collaboration and research. Conclusion Choosing the right university for robotics is a critical step in shaping your future in this exciting and rapidly evolving field.

The universities listed above are among the best in the world, offering top-notch education, cutting-edge research opportunities, and strong industry connections. Whether you're interested in autonomous vehicles, humanoid robots, or intelligent systems, these institutions provide the resources and environment necessary to excel in robotics.

[cascadingcascade]

Why MIT CSAIL is (afaik) not on Tumblr, I want to reblog this so badly

[kspacesite]

Particle learning system could help robots make sushi

It may be too soon to expect robots to replace sushi chefs, but MIT CSAIL is training a two-fingered robot named RiceGrip to lift and shape delicate objects!

[vlruso]

AI copilot enhances human precision for safer aviation

📢 Exciting news! MIT researchers have developed Air-Guardian, an AI copilot system that enhances human precision for safer aviation. 🛩️✨ Air-Guardian uses eye-tracking and saliency maps to determine pilots' attention and identify potential risks. With the ability to adapt to different situations, it creates a balanced partnership between humans and machines. Field tests have already proven its effectiveness, reducing risks and increasing navigation success rates. Find out more about this groundbreaking collaboration between human expertise and machine learning in aviation safety. Check out the blog post here: https://ift.tt/hpJksu7 💡 Action Items: 1️⃣ Learn more about the Air-Guardian system and its applications beyond aviation. 2️⃣ Dive into the optimization-based cooperative layer and liquid closed-form continuous-time neural networks (CfC) used in the Air-Guardian system. 3️⃣ Explore the potential for using visual attention metrics in other AI systems and applications. 4️⃣ Consider refining the human-machine interface for a more intuitive indicator when the guardian takes control. 5️⃣ Gather feedback and opinions from pilots and aviation experts on the effectiveness and potential improvements of the Air-Guardian system. 6️⃣ Discover the funding sources for the Air-Guardian research and evaluate their impact on collaborations or partnerships. Join us in revolutionizing aviation safety with innovative AI technologies that work hand in hand with human expertise. 🌟✈️ #AI #AviationSafety #MITResearch #Innovation [Image Source: MIT News] List of Useful Links: AI Scrum Bot - ask about AI scrum and agile Our Telegram @itinai Twitter -  @itinaicom