Skip to main content

Scientists Discover Way to Send Information into Black Holes Without Using Energy

3 comments

New AI Breakthrough Helps Soft Robots Learn and Adapt Like Humans

Imagine a robot arm that can gently hold fragile objects, adapt instantly when something changes, and keep working even if part of it fails—all without being retrained. Thanks to a new artificial intelligence (AI) control system, this vision is now much closer to reality.

Researchers from the Singapore–MIT Alliance for Research and Technology (SMART), National University of Singapore (NUS), Massachusetts Institute of Technology (MIT), and Nanyang Technological University (NTU Singapore) have developed a groundbreaking controller that allows soft robotic arms to learn many skills once and then adjust automatically to new situations. This innovation brings soft robotics closer to human-like adaptability and opens the door to safer, smarter robots in healthcare, industry, and everyday life.

What Makes Soft Robots Special?

Traditional robots are built with rigid metal parts, motors, and joints. They are powerful and precise, but they can also be dangerous around people and struggle in unpredictable environments.

Soft robots are different. They are made from flexible materials like soft rubber and move using special actuators—devices that work like artificial muscles. Because they bend and stretch, soft robots are naturally safer and better suited for delicate tasks such as assisting patients, handling fragile items, or working closely with humans.

However, this flexibility also creates a major problem: control.

Unlike rigid robots, soft robots constantly change shape. Even small disturbances—like a shift in weight, airflow, or minor hardware issues—can significantly affect how they move. This makes it extremely difficult to program them to behave reliably in the real world.

Why Smarter Control Is Needed

Until now, most soft robotic systems could only achieve one or two of these three essential abilities:

  1. Transfer learning – using skills learned in one task to perform another.

  2. Fast adaptation – adjusting quickly when conditions change.

  3. Guaranteed stability and safety – staying controlled while adapting.

Rarely could a single system do all three at once. This limitation has slowed the adoption of soft robots in real-world applications such as healthcare, manufacturing, and wearable devices.

The new research changes that.

In a study published in Science Advances, titled “A general soft robotic controller inspired by neuronal structural and plastic synapses that adapts to diverse arms, tasks, and perturbations,” the team introduces an AI control system that successfully combines all three capabilities in one unified framework.

Inspired by the Human Brain

The researchers took inspiration from how the human brain learns and adapts.

Our brains rely on two types of connections between neurons, called synapses:

  • Some provide stable, long-term knowledge.

  • Others change quickly, helping us adapt to new situations.

The AI controller uses the same idea.

Structural Synapses: Built-In Skills

The first part of the system, called structural synapses, is trained offline before the robot is deployed. During this phase, the robot learns basic movements such as bending, stretching, and smooth arm motion.

These structural synapses act like built-in skills. They give the robot a strong and stable foundation, similar to how humans learn fundamental motor abilities early in life.

Plastic Synapses: Real-Time Adaptation

The second part, known as plastic synapses, updates continuously while the robot is operating. These connections adjust in real time, allowing the robot to respond instantly to changes such as added weight, airflow, or damaged components.

To ensure safety, the system includes a stability mechanism that works like a safeguard. Even while adapting on the fly, the robot’s movements remain smooth and controlled.

According to Associate Professor Zhiqiang Tang, first author of the study, this is one of the first general soft-robot controllers that can transfer learning, adapt instantly, and remain stable—all at the same time.

Tested in the Real World

The team tested the system on two different soft robotic arms:

  • A cable-driven soft arm

  • A shape-memory-alloy–actuated soft arm

Despite their different designs, the same controller worked on both platforms, showing strong cross-platform flexibility.

The results were impressive:

  • 44–55% reduction in tracking errors during heavy disturbances

  • Over 92% shape accuracy even with payload changes, airflow, and actuator failures

  • Stable performance even when up to half of the actuators stopped working

The robots could perform multiple tasks—including following trajectories, placing objects, and controlling their overall shape—using a single control framework.

Professor Daniela Rus from MIT explained that combining structural learning with real-time adaptation allows robots to handle the unpredictable nature of soft materials. This brings us closer to a future where soft robots can work safely alongside people in clinics, factories, and homes.

A Major Step Toward Intelligent Soft Machines

Professor Cecilia Laschi from NUS described the work as a shift from task-specific robots to truly general, intelligent systems.

Instead of being programmed again and again for each new job, soft robots can now learn once and adapt many times. This reduces downtime, lowers costs, and makes deployment much easier.

The potential applications are wide-ranging:

Healthcare and Rehabilitation

Soft robotic devices can automatically adjust to a patient’s changing strength or posture. Rehabilitation robots can personalize therapy, while wearable soft robots can respond gently to individual needs, improving comfort and safety.

Medical Robotics

Soft robotic tools could assist in delicate procedures, adapting in real time to patient movement and anatomy.

Manufacturing and Logistics

Soft manipulators can handle fragile products, adapt to changing workloads, and continue operating even when parts fail—making factories more resilient.

Assistive Robotics

Robots designed to help elderly or disabled individuals can become more responsive, natural, and reliable.

Looking Ahead

The researchers plan to extend this technology to faster robotic systems and more complex environments. Future work will focus on industrial soft manipulators, advanced medical devices, and fully autonomous systems that can operate in real-world settings.

By giving soft robots the ability to learn broadly, adapt instantly, and stay stable, this breakthrough brings us closer to machines that behave more like living beings—flexible, intelligent, and safe.

As soft robotics continues to evolve, this brain-inspired AI controller could become a cornerstone technology, helping create a new generation of robots that truly work with humans, not just for them.

Reference: Zhiqiang Tang et al, A general soft robotic controller inspired by neuronal structural and plastic synapses that adapts to diverse arms, tasks, and perturbations, Science Advances (2026). DOI: 10.1126/sciadv.aea3712

Comments

Post a Comment

Popular

Scientists Discover Way to Send Information into Black Holes Without Using Energy

For years, scientists believed that adding even one qubit (a unit of quantum information) to a black hole needed energy. This was based on the idea that a black hole’s entropy must increase with more information, which means it must gain energy. But a new study by Jonah Kudler-Flam and Geoff Penington changes that thinking. They found that quantum information can be teleported into a black hole without adding energy or increasing entropy . This works through a process called black hole decoherence , where “soft” radiation — very low-energy signals — carry information into the black hole. In their method, the qubit enters the black hole while a new pair of entangled particles (like Hawking radiation) is created. This keeps the total information balanced, so there's no violation of the laws of physics. The energy cost only shows up when information is erased from the outside — these are called zerobits . According to Landauer’s principle, erasing information always needs energy. But ...
3 comments
Read more

Black Holes That Never Dies

Black holes are powerful objects in space with gravity so strong that nothing can escape them. In the 1970s, Stephen Hawking showed that black holes can slowly lose energy by giving off tiny particles. This process is called Hawking radiation . Over time, the black hole gets smaller and hotter, and in the end, it disappears completely. But new research by Menezes and his team shows something different. Using a theory called Loop Quantum Gravity (LQG) , they studied black holes with quantum corrections. In their model, the black hole does not vanish completely. Instead, it stops shrinking when it reaches a very small size. This leftover is called a black hole remnant . They also studied something called grey-body factors , which affect how much energy escapes from a black hole. Their findings show that the black hole cools down and stops losing mass once it reaches a minimum mass . This new model removes the idea of a “singularity” at the center of the black hole and gives us a better ...
Post a Comment
Read more

How Planetary Movements Might Explain Sunspot Cycles and Solar Phenomena

Sunspots, dark patches on the Sun's surface, follow a cycle of increasing and decreasing activity every 11 years. For years, scientists have relied on the dynamo model to explain this cycle. According to this model, the Sun's magnetic field is generated by the movement of plasma and the Sun's rotation. However, this model does not fully explain why the sunspot cycle is sometimes unpredictable. Lauri Jetsu, a researcher, has proposed a new approach. Jetsu’s analysis, using a method called the Discrete Chi-square Method (DCM), suggests that planetary movements, especially those of Earth, Jupiter, and Mercury, play a key role in driving the sunspot cycle. His theory focuses on Flux Transfer Events (FTEs), where the magnetic fields of these planets interact with the Sun’s magnetic field. These interactions could create the sunspots and explain other solar phenomena like the Sun’s magnetic polarity reversing every 11 years. The Sun, our closest star, has been a subject of scient...
Post a Comment
Read more