Assisting divers with robotic exoskeletons would increase their working efficiency and reduce the risk of accidents. Nonetheless, the synchronization of assistance with underwater movements has not been investigated and remains a complex issue.

A study published in IEEE/ASME Transactions on Mechatronics and led by WANG Xiangyang's team from Shenzhen Institute of Advanced Technology (SIAT) of the Chinese Academy of Sciences proposed an ultrarobust adaptive oscillator (URAO) method for predicting the kicking phase for the flutter kick and breaststroke kick, two main underwater motion patterns in diving activity.

The URAO method does not require prior dataset training. It can adapt to the motion characteristics of different divers, and support two representative underwater kicking modes, which demonstrates its strong adaptability and generalization capability. In particular, this method can rapidly track abrupt changes in kicking frequency.

Researchers conducted a series of experiments in an indoor still-water pool and a 70-meter outdoor pool. The results showed that the URAO method achieved stable synchronization within one kicking cycle, reduced the estimation error by 49.5% compared with existing methods, and solved the issues like slow convergence, oscillation, and prediction failure often observed in existing methods.

Based on the accurate phase information provided by URAO, the Performance-Enhancing Assistive Kicking Exosuit for Diving (PEAKED) soft diving exosuit can deliver timely assistive output when kicking direction changes underwater. For both flutter kick and breaststroke kick, the PEAKED maintained a low assistive delay and achieved smoother and more natural human-robot coordination. This study helps to improve motion efficiency and operational safety in complex underwater tasks.