Distributed AI helps robots recognise pain and self-repair
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 of the system.
When ‘injured’ with a cut from a sharp object, the robot quickly loses mechanical function. But the molecules in the self-healing ion gel begin to interact, causing the robot to ‘stitch’ its ‘wound’ together and to restore its function while maintaining high responsiveness.
“The self-healing properties of these novel devices help the robotic system to repeatedly stitch itself together when ‘injured’ with a cut or scratch, even at room temperature. This mimics how our biological system works, much like the way human skin heals on its own after a cut,” said Rohit Abraham John, who is also a Research Fellow at the School of Materials Science & Engineering at NTU.
“In our tests, our robot can ‘survive’ and respond to unintentional mechanical damage arising from minor injuries such as scratches and bumps, while continuing to work effectively. If such a system were used with robots in real world settings, it could contribute to savings in maintenance.”
“Conventional robots carry out tasks in a structured programmable manner, but ours can perceive their environment, learning and adapting behaviour accordingly. Most researchers focus on making more and more sensitive sensors, but do not focus on the challenges of how they can make decisions effectively. Such research is necessary for the next generation of robots to interact effectively with humans,” said Associate Professor Nripan Mathews, who is co-lead author and from the School of Materials Science & Engineering at NTU.
“In this work, our team has taken an approach that is off-the-beaten path, by applying new learning materials, devices and fabrication methods for robots to mimic the human neuro-biological functions. While still at a prototype stage, our findings have laid down important frameworks for the field, pointing the way forward for researchers to tackle these challenges.”
The team is now looking to collaborate with industry partners and government research labs to enhance their system for larger scale application.
Self healable neuromorphic memtransistor elements for decentralized sensory signal processing in robotics was published in Nature Communications
Related articles
- STRETCHABLE SUPERCAPACITOR COULD BE USED FOR WEARABLES
- KIT PROVIDES ALGORITHMS FOR NEUROMORPHIC IMAGE SENSOR
- ‘COMMITTEE PROCESSING’ IMPROVES IN-MEMORY NEURAL NETWORKS
Other articles on eeNews Europe
- RISC-V boom from edge AI says Facebook’s chief AI scientist
- Multicore GPU aims at 3nm for data centre designs
- Xilinx teams for cloud-based open source Covid-19 X-ray classification
- Connected graphene sensor performs three types of Covid-19 test
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
