Octopus Tentacle-Inspired In-Sensor Adaptive Integral for Edge-Intelligent Touch Intention Recognition

Area of Science:

• Materials Science
• Robotics
• Electronics Engineering

Background:

• Current touch electronics face limitations in adaptability, deformation stability, and data processing.
• The need for adaptive devices is crucial for evolving interactive contexts and technological innovation.

Purpose of the Study:

• To propose a novel reconfigurable and adaptive intelligent (RAI) touch sensor.
• To enhance multitouch interaction capabilities and device adaptability.
• To address limitations in current touch sensing technologies.

Main Methods:

• Inspired by octopus tentacle behavior, a geometric progression structure was employed for sensing elements.
• Integrated-in-sensing mechanisms and programmable logic were utilized to compress sensing data dimensionality.
• Hard-soft bonding and interface modulation of functional materials were leveraged for enhanced adaptability.

Main Results:

• The RAI touch sensor demonstrated remarkable deformability with a 200% strain range and 180° twist tolerance.
• Exceptional deformation stability was achieved, exceeding 10,000 cycles.
• Dynamic intention recognition accuracy surpassed 99% across diverse configurations.

Conclusions:

• The proposed RAI touch sensor overcomes limitations of conventional devices, offering superior adaptability and stability.
• Its integrated-in-sensing and edge data compression capabilities advance Internet of Things (IoT) and edge computing.
• This innovation paves the way for next-generation adaptive and intelligent electronic systems.