The system has AI-enabled sensor nodes to process and respond to ‘pain’ arising from pressure exerted by a physical force. The system also allows the robot to detect and repair its own damage with minor injuries without the need for human intervention.
Today’s sensors in factory robots typically do not process information but send it to a central processing unit in a server or the cloud where learning occurs. This can make the robots are also susceptible to damage that will require maintenance and repair, which can be long and costly, say the researchers.
The NTU approach embeds the AI machine learning into the network of sensor nodes, connected to multiple smaller processing units. 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 team. Configuring memtransistors as gated-threshold and-memristive switches, the architecture uses in-memory edge computing with minimal hardware circuitry and wiring with enhancements for fault tolerance and robustness.
Combining the system with a type of self-healing ion gel material allows the robots, when damaged, to recover their mechanical functions without human intervention.
“Our work has demonstrated the feasibility of a robotic system that is capable of processing information efficiently with minimal wiring and circuits,” said Arindam Basu, Associate Professor in the School of Electrical & Electronic Engineering at NTU. “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.”
To teach the robot how to recognise pain and learn damaging stimuli, the research team fashioned memtransistors, which are capable of memory and information processing, as artificial pain receptors and synapses.
Through lab experiments, the research team demonstrated how the robot was able to learn to respond to injury in real time. They also showed that the robot continued to respond to pressure even after damage, proving the robustness