Bird-Inspired Robot Swims and Flies

Researchers from MIT and EPFL have developed a lightweight flapping-wing robot inspired by diving birds such as puffins, petrels, and kingfishers that can both swim underwater and transition directly into flight. By studying the biomechanics of these birds, the team designed a robot with flexible wings, a steerable tail, and a waterproof body that can efficiently move through two vastly different environments. Experiments in water tanks and Lake Geneva showed that the robot could reliably swim, leap out of the water, and continue flying without requiring propellers, folding mechanisms, or paddling feet.

The breakthrough could enable a new generation of aerial-aquatic robots for environmental monitoring and ocean exploration. Unlike conventional drones or underwater vehicles, the robot could rapidly fly to remote locations, dive underwater to collect measurements or samples, and return with the data at a fraction of the cost of traditional methods. The researchers are now working to improve the robot's maneuverability and its ability to operate in rough water and windy conditions, with future applications including marine ecosystem monitoring, coastal surveillance, and climate research.

More information:

https://techxplore.com/news/2026-07-birdlike-robot-underwater-flight.html

Tiny Robot Boats Assemble Floating Structures

MIT researchers have developed FloatForm, a swarm of small autonomous robotic boats that can self-organise into floating structures such as bridges, platforms, or temporary workspaces. Inspired by the way fire ants link together to form rafts, each boat communicates only with its nearby neighbours rather than relying on a central controller. This decentralised approach allows the swarm to dynamically assemble, reconfigure, or repair structures even if individual robots fail or environmental conditions change. In laboratory demonstrations, groups of up to eight boats successfully formed a range of stable geometric configurations with a high success rate.

The researchers envision FloatForm as a flexible infrastructure solution for waterfront cities and disaster-response scenarios, where temporary floating structures can be deployed quickly without permanent construction. Potential applications include emergency bridges, floating markets, event stages, environmental monitoring platforms, and mobile sensor networks. By combining swarm intelligence with modular robotics, the system demonstrates how large-scale, adaptive infrastructure can emerge from the coordinated actions of many simple robots, opening new possibilities for resilient and responsive urban environments.

More information:

https://news.mit.edu/2026/tiny-robot-boats-build-floating-structures-0709

Cyborg Cockroach Swarms Go Underwater

Researchers from Nanyang Technological University in Singapore and Waseda University have developed remote-controlled cyborg cockroaches that can now operate underwater by wearing miniature 3D-printed diving suits. The lightweight system generates oxygen through a chemical reaction and delivers it directly to the insects' breathing openings, allowing them to survive and move underwater for up to three hours without impairing their natural mobility. The technology builds on previous work that enabled researchers to steer swarms of cockroaches remotely using tiny electronic implants.

The amphibious cyborg insects are designed to support search-and-rescue missions in environments inaccessible to conventional robots, such as flooded buildings, collapsed tunnels, drains, and other confined spaces. Because the insects rely on their own muscles for movement, they require far less energy than similarly sized robots while remaining highly agile. The research team also envisions future applications in infrastructure inspection and, eventually, exploration of extreme environments, including planetary missions where lightweight, energy-efficient biohybrid systems could offer significant advantages.

More information:

https://www.newscientist.com/article/2531894-remote-controlled-cockroach-swarm-can-now-breathe-underwater/

PaperTok Fights AI Slop

Researchers at the University of Washington have developed PaperTok, an AI-powered tool that helps scientists turn academic papers into engaging 45-second videos for platforms such as TikTok, YouTube Shorts, and Instagram Reels. Designed to combat misleading AI-generated science content ("AI slop"), the system keeps researchers in control by allowing them to review and refine AI-generated scripts before publication.

The developers argue that if scientists do not actively communicate their findings on popular social media platforms, inaccurate AI-generated summaries are likely to fill the gap. Early evaluations suggest that PaperTok can make research more accessible to non-specialist audiences while preserving scientific accuracy through researcher oversight. The team hopes it will encourage wider public engagement with credible scientific research.

More information:

https://www.geekwire.com/2026/short-form-science-university-of-washington-researchers-launch-papertok-to-combat-ai-slop/

Wearable Robotic Glove Restores Hand Function

Researchers from the Medical University of Vienna, working with collaborators from ETH Zurich, the Technical University of Munich, and the University of Belgrade, have developed a wearable neurorobotic system designed to restore hand function in people with severe neurological impairments. The system combines a lightweight robotic hand exoskeleton with functional electrical stimulation (FES), which activates weakened muscles through carefully timed electrical impulses. By synchronizing robotic assistance with the user's own muscle activity, the device enables more natural and coordinated grasping and finger movements than conventional rehabilitation approaches.

The researchers evaluated the system in individuals with spinal cord injuries and stroke-related hand paralysis, demonstrating significant improvements in performing everyday tasks such as grasping and manipulating objects. Unlike existing rehabilitation devices that often rely solely on robotics or electrical stimulation, the hybrid approach leverages the strengths of both technologies, promoting functional recovery while encouraging active patient participation. The team believes the wearable system could support both clinical rehabilitation and home-based therapy, offering a practical solution for improving independence and quality of life for people with impaired hand function.

More information:

https://www.news-medical.net/news/20260619/Scientists-develop-wearable-robotic-system-to-restore-hand-function.aspx

New Tool Detects AI Vision Hallucinations

Researchers at Los Alamos National Laboratory have developed a new tool called the Prelim Attention Score (PAS) to detect hallucinations in vision-language AI models, systems that combine image analysis with large language models. These models can sometimes generate descriptions of objects or details that are not actually present in an image. PAS works by monitoring how much the AI relies on the visual input versus its own previously generated text while producing a response, helping identify when the model is beginning to make things up.

The method operates in real time and can be integrated into existing vision-language models. By analyzing internal attention patterns, PAS provides a score indicating the likelihood of hallucination, allowing developers and users to assess the reliability of AI-generated outputs. The approach achieves state-of-the-art accuracy in detecting hallucinations and could improve the safety and trustworthiness of AI systems used in applications such as autonomous vehicles, healthcare imaging, robotics, and security monitoring.

More information:

https://interestingengineering.com/ai-robotics/us-tool-hallucinations-machine-vision-model

Digital Preservation of the Endangered Vaquita

Researchers from Florida Atlantic University have created one of the most detailed digital records ever made of the vaquita (Phocoena sinus), the world’s most endangered marine mammal. Using medical CT scans, high-resolution micro-CT imaging, and digital photography, the team digitized a rare female vaquita skeleton collected in 1966, transforming it into interactive 3D models that can be explored, measured, and studied without risking damage to the fragile original specimen. The resulting datasets have been made freely available through the MorphoSource repository.

The project serves as both a scientific resource and a conservation effort for a species on the brink of extinction. Found only in Mexico’s northern Gulf of California, the vaquita has suffered a catastrophic population decline due to accidental entanglement in illegal gillnets used to catch totoaba fish. With only a handful of individuals believed to remain in the wild, the digital archive preserves invaluable anatomical information for future generations while raising awareness of the urgent need for international action to eliminate gillnet fishing and protect this critically endangered porpoise.

More information:

https://www.fau.edu/newsdesk/articles/pixels-preserve-endangered-vaquita.php

AI Brain Implant Restores Communication and Employment for ALS Patient

Researchers at the University of California, Davis have demonstrated a major advance in brain–computer interface (BCI) technology that enabled a 47-year-old patient with amyotrophic lateral sclerosis (ALS) to communicate, control a computer, and maintain full-time employment despite losing the ability to speak. The implanted system uses AI-driven decoding algorithms to translate neural activity associated with intended speech into text and synthesized speech, while also providing cursor control for independent computer use. Over more than two years of daily use, the patient generated nearly two million words and over 183,000 sentences, achieving communication speeds of about 56 words per minute with high accuracy.

The study is considered a significant milestone because the system functioned reliably outside the laboratory and without constant researcher supervision. Researchers reported that the participant accumulated more than 3,800 hours of use, creating the largest known single-neuron-resolution brain recording dataset of its kind. Beyond restoring communication, the technology allowed the user to reconnect socially, preserve aspects of his natural voice, and continue professional work, highlighting how AI-enhanced BCIs are moving from experimental demonstrations toward practical tools that can meaningfully improve quality of life for people with severe paralysis.

More information:

https://www.theregister.com/science/2026/06/16/ai-and-brain-computer-interface-allow-speechless-als-patient-to-work-a-full-time-job/5256492