A new study has introduced a biomimetic smart insole system designed to address the increasing need for accurate gait monitoring, especially as lower limb dysfunction and abnormal gait become more common due to aging populations and chronic diseases. Current clinical methods for gait assessment rely on laboratory equipment such as optical motion capture systems and force platforms, which are expensive, limited by space, and unable to monitor natural movement in everyday life.
Wearable pressure-sensing insoles have emerged as an alternative for continuous gait monitoring. However, existing technologies face challenges including inadequate sensor performance across the full range of foot pressures, reliance on batteries with short lifespans, and difficulties processing large amounts of data in real time. The newly developed smart insole aims to overcome these limitations by integrating advanced sensing technology, an autonomous power supply, and artificial intelligence-based diagnostic tools.
The research team drew inspiration from the structure of mantis legs to design a dual-microstructure capacitive pressure sensor using microstructured PDMS combined with compressible elastic foam. This design achieves a detection limit as low as 0.10 Pa and a maximum detection range of 1.4 MPa. The sensors maintained mechanical stability over 12,000 loading cycles, exceeding the performance of current flexible pressure sensors.
For energy management, the smart insole incorporates a perovskite solar cell paired with a lithium-sulfur nanobattery to form an adaptive closed-loop power system. This allows stable operation under different lighting conditions, with light charging efficiency reaching 11.21% and energy storage efficiency at 72.15%. These features support long-term continuous use without frequent recharging.
Data collected by the insole’s 16-channel wireless module is processed using embedded artificial intelligence algorithms. According to the researchers: "Based on a random forest model, the system can achieve 96.0% accuracy in identifying arch abnormalities; based on a one-dimensional convolutional neural network (1D-CNN), it can classify 12 pathological gait patterns with an accuracy of 97.6%." The mobile application displays dynamic force field distributions via color maps to assist clinicians and rehabilitation professionals with decision-making.
The study demonstrates that combining high-precision biomimetic sensing with sustainable energy solutions and intelligent diagnostics results in a wearable platform suitable for clinical validation. Researchers say this approach offers new opportunities for early screening of lower limb diseases, personalized rehabilitation training, and remote medical monitoring: "By deeply integrating biomimetic high-precision sensing, sustainable energy interfaces, and intelligent mechanical diagnostics, this research has constructed a clinically validated closed-loop wearable platform, providing a novel technological pathway for early screening of lower limb diseases, personalized rehabilitation training, and remote medical monitoring."
