Brain-like chip breakthrough: A vision for robotics' future
Scientists from Australia's RMIT University have created a chip that functions like a brain and sees like an eye, potentially revolutionizing robotics and autonomous vehicles.
Australian engineers at RMIT University have developed a tiny, brain-like device capable of detecting hand movements, storing visual memories, and processing information without relying on an external computer. Their innovative chip mimics the functioning of the human brain and eye.
The heart of the device is a metal compound
"Neuromorphic vision systems are designed to use similar analogue processing to our brains, which can greatly reduce the amount of energy needed to perform complex visual tasks compared with digital technologies used today," stated Professor Sumeet Walia, the lead researcher of the project and director of the RMIT Centre for Advanced Materials and Sensor Research, in a university release.
The small chip contains molybdenum disulfide, or MoS2 — a metal compound only a few atoms thick. It is used for detecting light and processing visual information in real time. "This proof-of-concept device mimics the human eye’s ability to capture light and the brain’s ability to process that visual information, enabling it to sense a change in the environment instantly and make memories without the need for using huge amounts of data and energy," the lead author of the project stated.
What are the potential applications of this technology?
The new technology could significantly improve the reaction time of autonomous vehicles and advanced robotic systems, which is crucial in dangerous and unpredictable environments. "Neuromorphic vision in these applications, which is still many years away, could detect changes in a scene almost instantly, without the need to process lots of data, enabling a much faster response that could save lives," explained Prof. Sumeet Walia.
During experiments, the device detected changes in the movement of a waving hand without needing to record events frame by frame, significantly reducing the demand for data processing and energy. The team plans to scale this proof of concept to a larger array of MoS2-based pixels.
Australian scientists await patent
RMIT has filed for a provisional patent for this technology, and the research has been published in the journal "Advanced Materials Technologies". The team is also integrating this technology with conventional digital systems, which could benefit visual processing, where energy efficiency and real-time operations are crucial.
