New tech helps free up more space for robots to ‘think’

Researchers at King’s College London have achieved a groundbreaking feat in robotics. They have developed a method to convey complex instructions to robots without relying on electricity for the first time ever, which could free up more space in the robotic ‘brain’ for them to ‘think.’ By harnessing variations in pressure from a fluid, a new compact circuit enables robots to receive and execute commands, mimicking how certain functions in the human body operate.

This pioneering technology paves the way for a new era of robots that can function independently of their central control system. This development promises to free up valuable space in the robot’s ‘brain,’ potentially allowing for the integration of more advanced AI-powered software. The implications of this breakthrough are enormous, opening the door to a new generation of robots with enhanced capabilities and autonomy.

“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 have the potential to revolutionize the field of robotics. This discovery opens the door to the development of robots capable of functioning in environments where traditional electricity-powered devices fail, such as radioactive areas like Chornobyl, which can damage circuits and electric-sensitive spaces like MRI rooms. The researchers also envision these robots being deployed in low-income countries with limited access to reliable electricity.The controller valve and soft robotics hopper which can move without electricity. Credit: King’s College London

“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?” Dr Forte said. “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.”

In the world of robotics, the reliance on electricity and computer chips has been a long-standing limitation. The traditional setup involves a robotic ‘brain’ of algorithms and software, which then communicates with the hardware through an encoder to execute tasks. However, this setup presents challenges, especially in the field of ‘soft robotics,’ where the use of soft materials for robotic muscles introduces complexities in achieving complex actions.

To address this issue, a team of innovators has developed a reconfigurable circuit with an adjustable valve designed to be integrated into a robot’s hardware. This remarkable valve, functioning like a transistor in a typical circuit, enables engineers to transmit signals directly to the hardware using pressure, effectively mimicking binary code.

This breakthrough allows robots to execute intricate maneuvers without relying on electricity or instructions from the central brain. It represents a leap forward in control, surpassing the capabilities of current fluid-based circuits.

By shifting the burden of software tasks to the hardware, this pioneering circuit liberates computational space, paving the way for the creation of future robotic systems that are more adaptable, sophisticated, and ultimately more impactful.

The researchers are now aiming to take their circuits to the next level by integrating them into larger robots, from crawlers used to monitor power plants to wheeled robots with entirely soft engines. This move promises to revolutionize the field of robotics and bring about transformative changes in various industries.

“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,” said Mostafa Mousa, Post-graduate Researcher at King’s College London.

Journal reference:

  1. Mostafa Mousa, Ashkan Rezanejad, Benjamin Gorissen, Antonio E. Forte. Frequency-Controlled Fluidic Oscillators for Soft Robots. Advanced Science, 2024; DOI: 10.1002/advs.202408879

Leave a Reply

Your email address will not be published. Required fields are marked *