Artificial Intelligence: Singapore Researchers Develop Robots That Feel Pain And Heal Themselves Using AI
Scientists at Nanyang Technological University (NTU), Singapore, developed “mini-brains” for this robotic experiment.
The NTU scientists innovated memtransistors, which are “brain-like” electronic devices that can process information and are capable of memory functions. They embedded these memtransistors, which function as artificial pain receptors and synapses, into AI-enabled sensor nodes in the robot. These nodes can process and respond to “pain” caused by impact from a physical force. In case of a minor injury, the robot can also repair its damage without human assistance. (ScienceDaily)
The approach by the NTU scientists is very different from current robotic technology. Most robots these days are heavily wired and have multiple sensors including cameras, microphones, and touch sensors. The data picked up by these sensors cannot be processed by the robot itself. Instead, it must be sent across to a central processing computer which houses the AI algorithms to crunch the data.
The process is slow, unwieldy, and prone to damage. In case of an accident, it can be very time-consuming and expensive to bring the robot back to functioning.
The NTU approach is to have the AI do its job inside the robot itself.
NTU embedded AI into the network of sensor nodes, connected to multiple small, less-powerful, processing units, that act like ‘mini-brains’ distributed on the robotic skin.
“This means learning happens locally and the wiring requirements and response time for the robot are reduced five to ten times compared to conventional robots,” say the NTU scientists.
Going a step further, the scientists equipped the system with a type of self-healing ion gel material. The robot, if not seriously damaged, can therefore make itself mechanically whole again without human assistance.
The scientists showed that when injured with a cut from a sharp object, the robot loses its mechanical abilities. However, the molecules in the self-healing ion gel start to interact and help the robot to “stitch” its wound together and bounce back to normalcy.
Robots’ interaction with humans
Co-lead author of the study, Associate Professor Arindam Basu from the NTU School of Electrical & Electronic Engineering said, “For robots to work together with humans one day, one concern is how to ensure they will interact safely with us. For that reason, scientists around the world have been finding ways to bring a sense of awareness to robots, such as being able to ‘feel’ pain, to react to it, and to withstand harsh operating conditions. However, the complexity of putting together the multitude of sensors required and the resultant fragility of such a system is a major barrier for widespread adoption.”
Minimal wiring and circuits
Assoc Prof Basu, who is a neuromorphic computing expert added, “Our work has demonstrated the feasibility of a robotic system that is capable of processing information efficiently with minimal wiring and circuits. By reducing the number of electronic components required, our system should become affordable and scalable. This will help accelerate the adoption of a new generation of robots in the marketplace.”
Related Story: A Robotic Scientist That Works 21.5/7
Latest Alternative Investment News
The Brunel Pension Partnership has picked Ownership Capital, RBC Global Asset Management, and Nordea Asset Management to manage its new Sustainable Equities Fund of around £1.2 billion ($1.55 billion). Brunel…
CrowdProperty, a leading crowdfunder/lender to the U.K. SME property sector, has lent over £100 million to development professionals. The funding had a beneficial impact on the UK economy because it…
Ripple Labs, the San Francisco-based technology company that facilitates cross-border payments through the use of its blockchain solutions via RippleNet, will invest an undisclosed amount in Money Tap. Money Tap…
Earlier this year, Apple (NASDAQ: AAPL) acquired Vilynx, a Barcelona-based startup that uses AI and computer vision technology to analyze a video’s visual, audio, and text elements. Reportedly, the iPhone…