Breakthrough in Robotics: Electricity-Free Circuits Enable More Advanced AI Integration

New breakthrough helps free up space for robots to 'think', say scientists

Engineers have worked out how to give robots complex instructions without electricity for the first time which could free up more space in the robotic 'brain' for them to 'think'. Mimicking how some parts of the human body work, researchers from King's College London have transmitted a series of commands to devices with a new kind of compact circuit, using variations in pressure from a fluid inside it. They say this world first opens up the possibility of a new generation of robots, whose bodies could operate independently of their built-in control centre, with this space potentially being used instead for more complex AI powered software. "Delegating tasks to different parts of the body frees up computational space for robots to 'think,' allowing future generations of robots to be more aware of their social context or even more dexterous. This opens the door for a new kind of robotics in places like social care and manufacturing," said Dr Antonio Forte, Senior Lecturer in Engineering at King's College London and senior author of the study. The findings, published in Advanced Sciencecould also enable the creation of robots able to operate in situations where electricity-powered devices cannot work, such as exploration in irradiated areas like Chernobyl which destroy circuits, and in electric sensitive environments like MRI rooms. The researchers also hope that these robots could eventually be used in low-income countries which do not have reliable access to electricity. Dr Forte said: "Put simply, robots are split into two parts: the brain and the body. An AI brain can help run the traffic system of a city, but many robots still struggle to open a door -- why is that? "Software has advanced rapidly in recent years, but hardware has not kept up. By creating a hardware system independent from the software running it, we can offload a lot of the computational load onto the hardware, in the same way your brain doesn't need to tell your heart to beat." Currently, all robots rely on electricity and computer chips to function. A robotic 'brain' of algorithms and software translates information to the body or hardware through an encoder, which then performs an action. In 'soft robotics,' a field which creates devices like robotic muscles out of soft materials, this is particularly an issue as it introduces hard electronic encoders and puts strain on the software for the material to act in a complex way, e.g. grabbing a door handle. To circumvent this, the team developed a reconfigurable circuit with an adjustable valve to be placed within a robot's hardware. This valve acts like a transistor in a normal circuit and engineers can send signals directly to hardware using pressure, mimicking binary code, allowing the robot to perform complex manoeuvres without the need for electricity or instruction from the central brain. This allows for a greater level of control than current fluid-based circuits. By offloading the work of the software onto the hardware, the new circuit frees up computational space for future robotic systems to be more adaptive, complex, and useful. As a next step, the researchers now hope to scale up their circuits from experimental hoppers and pipettes and embed them in larger robots, from crawlers used to monitor power plants to wheeled robots with entirely soft engines. Mostafa Mousa, Post-graduate Researcher at King's College London and author, said: "Ultimately, without investment in embodied intelligence robots will plateau. Soon, if we do not offload the computational load that modern day robots take on, algorithmic improvements will have little impact on their performance. Our work is just a first step on this path, but the future holds smarter robots with smarter bodies."

Electricity-free circuit helps free up space for robots to 'think,' say scientists

Engineers have worked out how to give robots complex instructions without electricity for the first time, which could free up more space in the robotic 'brain' for them to 'think.' Mimicking how some parts of the human body work, researchers from King's College London have transmitted a series of commands to devices with a new kind of compact circuit, using variations in pressure from a fluid inside it. They say this world first opens up the possibility of a new generation of robots, whose bodies could operate independently of their built-in control center, with this space potentially being used instead for more complex AI-powered software. "Delegating tasks to different parts of the body frees up computational space for robots to 'think,' allowing future generations of robots to be more aware of their social context or even more dexterous. This opens the door for a new kind of robotics in places like social care and manufacturing," said Dr. Antonio Forte, Senior Lecturer in Engineering at King's College London and senior author of the study. The findings, published in Advanced Science could also enable the creation of robots able to operate in situations where electricity-powered devices cannot work, such as exploration in irradiated areas like Chernobyl which destroy circuits, and in electricity sensitive environments like MRI rooms. The researchers also hope that these robots could eventually be used in low-income countries which do not have reliable access to electricity. Dr. Forte said, "Put simply, robots are split into two parts: the brain and the body. An AI brain can help run the traffic system of a city, but many robots still struggle to open a door -- why is that? "Software has advanced rapidly in recent years, but hardware has not kept up. By creating a hardware system independent from the software running it, we can offload a lot of the computational load onto the hardware, in the same way your brain doesn't need to tell your heart to beat." Currently, all robots rely on electricity and computer chips to function. A robotic 'brain' of algorithms and software translates information to the body or hardware through an encoder, which then performs an action. In 'soft robotics,' a field which creates devices like robotic muscles out of soft materials, this is particularly an issue as it introduces hard electronic encoders and puts strain on the software for the material to act in a complex way, e.g. grabbing a door handle. To circumvent this, the team developed a reconfigurable circuit with an adjustable valve to be placed within a robot's hardware. This valve acts like a transistor in a normal circuit and engineers can send signals directly to hardware using pressure, mimicking binary code, allowing the robot to perform complex maneuvers without the need for electricity or instruction from the central brain. This allows for a greater level of control than current fluid-based circuits. By offloading the work of the software onto the hardware, the new circuit frees up computational space for future robotic systems to be more adaptive, complex, and useful. As a next step, the researchers now hope to scale up their circuits from experimental hoppers and pipettes and embed them in larger robots, from crawlers used to monitor power plants to wheeled robots with entirely soft engines. Mostafa Mousa, Post-graduate Researcher at King's College London and author, said, "Ultimately, without investment in embodied intelligence, robots will plateau. Soon, if we do not offload the computational load that modern day robots take on, algorithmic improvements will have little impact on their performance. Our work is just a first step on this path, but the future holds smarter robots with smarter bodies."

Robots with space to 'think' will become more useful - Earth.com

Engineers have developed a pioneering technique that enables robots to follow complex instructions without the need for electricity. This could significantly expand the cognitive capabilities of robots by freeing up more space in their "brains" for advanced thinking. This breakthrough, led by researchers from King's College London (KCL), involves transmitting commands to robots through variations in fluid pressure instead of relying on electrical signals - a world-first approach that could revolutionize how robots are built and operate. This novel method could pave the way for a new generation of robots whose bodies can function independently from their central control systems. The space in the robotic system, traditionally dedicated to basic operations, could instead be used for more sophisticated artificial intelligence (AI) software, allowing these machines to manage more complex tasks in diverse environments. Such an advancement could lead to robots that are not only more efficient but also more socially aware and adaptable in real-world situations. Antonio Forte is a senior lecturer in engineering at KCL and the senior author of the study. "Delegating tasks to different parts of the body frees up computational space for robots to 'think,' allowing future generations of robots to be more aware of their social context or even more dexterous," said Forte. "This opens the door for a new kind of robotics in places like social care and manufacturing." The research, recently published in Advanced Science, goes beyond simply improving robotic efficiency - it also opens the possibility of using robots in situations where electricity-powered devices cannot function effectively. This could include exploration missions in irradiated zones such as Chernobyl, where high radiation levels can destroy electrical circuits, or in highly sensitive environments like MRI rooms, where electronic devices can interfere with medical equipment. Furthermore, robots built using this fluid-powered technology could become essential in low-income countries, where reliable access to electricity may be a challenge. Forte highlights the importance of this new approach in enhancing the functionality of robots. "Put simply, robots are split into two parts: the brain and the body. An AI brain can help run the traffic system of a city, but many robots still struggle to open a door - why is that? Software has advanced rapidly in recent years, but hardware has not kept up," said Forte. "By creating a hardware system independent from the software running it, we can offload a lot of the computational load onto the hardware, in the same way your brain doesn't need to tell your heart to beat." Currently, almost all robots rely on electricity and integrated computer chips to perform their tasks. A robotic "brain," which consists of algorithms and AI software, sends instructions to the robot's physical body, which carries out the action. This interaction between the software and the hardware is managed through encoders, which translate the software's commands into physical movements. However, this approach is particularly problematic for "soft robotics," a subfield that designs devices made from soft, flexible materials, like robotic muscles. The integration of rigid electronic encoders complicates the system, making it harder for the material to perform complex tasks, such as grasping a doorknob. To address this challenge, the research team developed a reconfigurable circuit featuring an adjustable valve. This valve acts like a transistor in a standard electrical circuit, but instead of using electrical signals, it uses pressure to send commands directly to the hardware. The engineers use fluid pressure to transmit binary-like signals to the robot's physical structure, allowing the robot to perform complex movements without requiring electricity or constant instructions from a central processing unit. This innovation allows for a level of control that surpasses what current fluid-based systems can offer. By offloading part of the computational work onto the robot's physical system, this new circuit design frees up the robot's "brain" to focus on more complex tasks, making the robot more adaptive and capable in a wide variety of scenarios. As a result, robots equipped with this technology could be more effective in real-world situations, including those that require nuanced physical interactions or decision-making abilities. The next step for the researchers is to scale up their circuit design. They plan to move beyond small experimental setups and integrate this technology into larger robots, such as those used for monitoring power plants or robots with entirely soft engines. These new systems could be used in environments that require advanced robotics, like industrial sites or in complex rescue operations. Mostafa Mousa, a post-graduate researcher at KCL and co-author of the study, emphasized the broader implications of this development. "Ultimately, without investment in embodied intelligence, robots will plateau. Soon, if we do not offload the computational load that modern day robots take on, algorithmic improvements will have little impact on their performance," said Mousa. "Our work is just a first step on this path, but the future holds smarter robots with smarter bodies." This breakthrough marks a significant step forward in the field of robotics, with the potential to transform the capabilities of robots across industries. By shifting part of the cognitive load from software to hardware, robots could become far more versatile and efficient in their tasks, allowing them to be more adaptive, resilient, and ultimately, more useful in a wider range of applications. -- - Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

New technology helps robots understand instructions without electricity

Serving tech enthusiasts for over 25 years. TechSpot means tech analysis and advice you can trust. What just happened? Researchers from King's College London have figured out how to give robots complex instructions without using any electricity at all, not even through batteries. The key is a new type of compact circuit that uses fluid pressure instead of electrical currents to transmit commands to robotic devices. The circuit works by mimicking how certain parts of the human body operate. The engineers were able to use it to encode a series of instructions through variations in the pressure of liquid flowing through these special circuits. The circuits themselves act like the transistors in normal electronics, except they use hydraulic pressure instead of electricity as the input signal. When outfitted with these quirky circuits, robots can still perform several complex maneuvers, as seen in the demo video below. According to the researchers, this amazing "world-first" achievement could free up tons of space normally reserved for a robot's electronic "brain," potentially allowing future bots to pack in more advanced AI software to help them better understand social cues, be more dexterous, and operate with greater autonomy. Perhaps more impressively, the research could enable robot designs with more computational load offloaded directly to the hardware. Dr Antonio Forte, the King's College senior lecturer who led the study, likens this to how the brain doesn't technically need to tell your heart to beat. Similarly, a robot's main control unit doesn't need to waste processing power on basic, routine tasks. Since the pressure-based circuits don't rely on electricity at all, the tech also enables robots to operate in situations where electronics would get fried - such as around powerful radiation or in medical facilities with large MRI machines. The researchers also note that the tech could be beneficial for squishy "soft robots" made out of flexible materials like robotic muscles. The current approach of introducing rigid electronic components to translate the brain's signals puts a strain on the software when you want those soft materials to perform complex movements, they say. The team's paper detailing their groundbreaking fluidic circuit was awarded a featured cover spot in the journal Advanced Science for its "outstanding results." Next, they hope to scale it up and integrate it into larger robots like crawlers that monitor power plants.