Wearable Human Body

Engineers at Georgia Tech’s College of Engineering have developed a wireless system that allows wearable devices and tiny medical implants to communicate directly through the body’s tissues. Called SWANS (Smart Wireless Autonomous Networking System), the technology takes inspiration from the nervous system and uses the body’s natural ionic conductivity to transmit small electrical signals. Unlike conventional Bluetooth or NFC connections, which struggle to penetrate tissue and require relatively large antennas and substantial power, SWANS enables sensors and therapeutic devices located in different parts of the body to coordinate without being physically connected or positioned close together.

The researchers demonstrated the approach by creating a network of sensors and neural interfaces that coordinated limb movement in an animal model. Because the system requires very little power, implants can be made smaller than 3 millimeters, potentially allowing them to be inserted using a syringe rather than surgery. Sensors could eventually detect biological changes and automatically instruct another device to deliver medication, stimulate a nerve, or perform another therapeutic action at the appropriate location. Researchers vision SWANS as a step toward personalized bioelectronic medicine in which distributed sensors, wearables, and implants work together to monitor health and deliver treatments when needed.

More information:

https://coe.gatech.edu/news/2026/09/engineers-connect-health-wearables-and-implants-using-body-network

Smart Contact Lens Measures Stress Through Tears

Researchers have developed a lab on a contact lens capable of detecting serotonin in tears, potentially enabling continuous, noninvasive monitoring of stress and other physiological changes. The soft, reusable hydrogel lens incorporates flexible graphene and silver electrodes, with ferrocene helping it selectively detect extremely low serotonin concentrations. Laboratory tests showed sensitivity well below typical serotonin levels found in human tears, while experiments involving 10 volunteers found that tear serotonin decreased after stressful public-speaking and mathematics tasks. Testing on an anesthetized pig also demonstrated serotonin detection without signs of short-term irritation or infection.

The technology could eventually shift wearable health monitoring beyond physical measurements such as heart rate and temperature toward continuous biochemical sensing. Researchers have already produced a proof-of-concept wireless version using NFC for battery-free sensing and smartphone data transmission. However, substantial validation and safety testing remain necessary, particularly to understand how tear serotonin varies among individuals and relates to blood biomarkers and clinical assessments. Future versions could simultaneously measure serotonin, cortisol, and other molecules, potentially turning contact lenses into wearable platforms that provide a richer picture of stress and physiological health throughout everyday life.

More information:

https://spectrum.ieee.org/serotonin-stress-smart-contact-lens

Brain Waves May Underpin Cognition and Consciousness

A new theory from MIT proposes that cognition and consciousness emerge partly through analog computations performed by traveling electrical brain waves, rather than solely through fixed neural circuits and synaptic connections. While synapses provide the underlying infrastructure for storing memories, goals, and knowledge, researchers argue that they are too slow to explain the brain’s ability to rapidly reorganize information. Instead, rhythmic waves coordinate large populations of neurons in real time. Slower alpha and beta waves may regulate faster gamma activity associated with sensory information, dynamically determining which neural ensembles become active at places and moments. The interaction and interference of these waves could therefore enable parallel, analog forms of spatiotemporal computing.

The researchers extend this framework to consciousness, proposing that conscious experience emerges when brain-wave patterns organize activity across the cortex into a coherent, globally integrated state. Evidence from anesthesia studies supports this possibility: different anesthetic drugs can produce unconsciousness while disrupting large-scale wave dynamics despite acting through different molecular mechanisms. However, the authors emphasize that this remains a theory, and direct experimental evidence that brain waves perform the proposed analog computations is still needed. If confirmed, the framework could reshape models of cognition and potentially inspire treatments that target brain-wave dynamics, which can sometimes be influenced non-invasively.

More information:

https://www.technology.org/2026/09/19/cognition-and-consciousness-arise-from-analog-computations-says-new-theory/

AI Takes Root in Farming

Farmers are adopting artificial intelligence more readily than many other emerging technologies. Agriculture is particularly suited to AI because farms generate large amounts of data from machinery, sensors, satellites, weather services and field observations. AI can turn this information into practical recommendations, helping farmers predict yields, identify pests and diseases, optimise irrigation and fertiliser use, and make better operational decisions. Generative AI is also emerging as a kind of virtual agronomist, allowing farmers to obtain advice through natural-language queries and potentially making sophisticated agricultural knowledge easier to access.

Targeted applications of AI could generate around $100 billion in additional on-farm value globally. The appeal is largely driven by measurable benefits, higher productivity, reduced input and labour costs, improved resource efficiency and greater resilience to increasingly unpredictable environmental conditions. However, adoption is not uniform. Connectivity, data quality, affordability and concerns over control of farm data remain significant obstacles, particularly for smaller farms and farmers in regions with limited digital infrastructure. The broader message is that AI is gaining traction in agriculture because it can address concrete, everyday farming problems.

More information:

https://finance.yahoo.com/technology/ai/articles/farmers-embracing-ai-more-other-110000541.html

Brain Implant Enables Speech and Gestures Through an Avatar

Researchers at the University of California developed a BCI that allows people with severe paralysis to communicate using both speech and upper-body gestures through a digital avatar. The system uses one implant containing 253 electrodes positioned on the surface of the sensorimotor cortex to capture neural activity associated with attempted speech and movements. Machine-learning algorithms decode these signals in real time, enabling an animated avatar to speak while simultaneously performing gestures such as waving or nodding. The study involved two participants with severe paralysis and demonstrated that neural signals for speech and movement can be extracted from the same cortical region and translated into coordinated communication.

The research represents a step toward BCIs that reproduce the richness of natural human communication rather than simply generating text, speech, or cursor movements. Because conversation relies heavily on non-verbal cues, combining vocal expression with gestures could make interactions more intuitive and socially expressive for people affected by conditions such as ALS or brainstem stroke. Importantly, the findings suggest that a single neural interface can support multiple functions simultaneously, potentially reducing the need for separate implants dedicated to different tasks. The researchers ultimately envision multifunctional systems capable of restoring a broader range of communication and interaction abilities for people with severe paralysis.

More information:

https://www.science.org/content/article/single-brain-implant-lets-paralyzed-people-both-talk-and-gesture-avatar

Beijing’s Robot Kindergarten

A new robot kindergarten has opened in Beijing’s Shijingshan district to explore a different approach to training robots: allowing them to learn continuously through physical interaction, touch, trial and error, rather than relying primarily on human demonstrations. The facility was jointly established by tactile-sensing company Tashan Technology and a team led by Turing Award winner and reinforcement-learning pioneer Richard Sutton. Robots repeatedly attempt movements, receive feedback from their environment and modify their behaviour based on the results, for example, learning to avoid an obstacle after colliding with it. Sutton described the facility as a controlled environment where robots can learn about their own bodies and the physical world, making mistakes an essential source of training data.

The initiative reflects a broader effort to develop robots capable of continuous, autonomous learning after deployment, rather than having their behaviour largely fixed by pre-training, simulation or teleoperation. Researchers argue that robots could eventually generate their own experience-based datasets and potentially share what individual machines learn across common models, helping them adapt to situations not covered during initial training. Significant challenges remain, particularly hardware durability and the complexity of learning sophisticated humanoid behaviours. For now, autonomous experiential learning is expected to complement rather than replace imitation learning and simulation, while potentially becoming increasingly important as robots enter factories, services and homes.

More information:

https://www.globaltimes.cn/page/202609/1369570.shtml

Brain Implant Controlled Across Continents

Researchers from KAIST and Yonsei University have demonstrated a wireless brain implant that can be controlled across continents. Their system, called RAPIDO, received commands sent from Chicago to a laboratory in Daejeon, South Korea with an average response time of about 109 milliseconds. Designed for experiments with freely moving animals, the implant combines two capabilities: precisely delivering drugs into specific brain regions and providing targeted light stimulation for optogenetic experiments. Its refillable cartridge and internet-based control could enable longer-term studies while reducing the need for researchers to physically approach or repeatedly handle experimental animals.

In experiments with rats, RAPIDO successfully delivered controlled doses of cocaine into the nucleus accumbens over several weeks, producing measurable dose-dependent behavioral effects. In a separate experiment, researchers used the implant's light stimulation to activate the RhoA signaling pathway, preventing rats from developing the same learned preference for a cocaine-associated environment. The researchers stress that this does not constitute a treatment for addiction; rather, the work demonstrates a platform for remotely manipulating specific neural processes and studying their effects on behavior. Significant challenges must be addressed before such technology could be considered for human clinical applications.

More information:

https://www.sciencealert.com/a-brain-implant-in-korea-was-just-controlled-from-the-us

LLM-Personalised Autonomous Driving

Researchers at Delft University of Technology have developed an approach that allows passengers to personalise how an autonomous vehicle drives using natural-language commands. Instead of allowing a large language model (LLM) to control the vehicle directly, the system uses the LLM to interpret requests or indications that the passenger feels dizzy. These preferences are translated into adjustments to parameters used by a conventional, safety-aware motion planner, affecting characteristics such as speed, acceleration, steering smoothness and collision avoidance. The system also keeps the passenger in the loop by explaining the proposed changes in everyday language and asking for confirmation before applying them. Tests using the nuPlan autonomous-driving simulator showed that the system could successfully adapt driving behaviour to eight different passenger prompts, producing smoother driving when comfort was prioritised and higher speeds when urgency was expressed.

The approach is significant because it combines the flexibility and natural-language understanding of LLMs with the predictability of traditional autonomous-driving controllers. Rather than relying on an LLM for real-time driving decisions—which can suffer from latency, hallucinations and a lack of performance guarantees—the researchers use GPT-4o-mini only to translate subjective passenger preferences into changes within predefined safe limits. This separation means the underlying motion planner remains responsible for vehicle control, reducing the potential consequences of incorrect LLM outputs. However, researchers note that maintaining safe operating constraints still requires substantial engineering, and the Delft approach does not yet provide mathematically provable safety. Other work is therefore exploring additional verification layers that mathematically check AI-generated driving decisions against traffic rules and predicted road-user behaviour before they are executed.

More information:

https://spectrum.ieee.org/autonomous-vehicles-motion-planner-llm