Accurate measurement of human posture and movement plays an essential role in rehabilitation training and sports performance improvement. Current rehabilitation practices frequently utilize sensor-based methodologies (e.g., inertial measurement units, accelerometers, gyroscopes) to directly assess patient posture and track movement patterns. While these sensor-based systems offer significant advantages in providing real-time measurements, their performance often suffers from unavoidable measurement outliers, sensor drift, and external environmental disturbances, creating uncertainty and inaccuracies within posture estimation processes. Such inaccuracies could lead to incorrect clinical interpretations, inefficient training interventions, extended recovery periods, or inadequate patient-specific protocols.

Consequently, the sports rehabilitation community acknowledges the growing necessity of developing robust technical and engineering solutions aimed at effectively eliminating or mitigating these measurement inaccuracies. Current research highlights several promising strategies such as advanced filtering approaches, sensor fusion methodologies, statistical and computational modeling techniques, as well as artificial intelligence and machine learning-driven systems. However, these innovations typically remain experimental and thus require extensive validation and refinement, particularly within real-world rehabilitation contexts.

The primary objective of the current Research Topic is to gather empirical and methodological contributions focusing on engineering innovations and technological developments dedicated explicitly to enhancing rehabilitation training accuracy and effectiveness. This Research Topic aims to bridge the gap between theoretical engineering methods and practical rehabilitation implementations, encouraging interdisciplinary collaboration among sport scientists, biomechanists, rehabilitation specialists, and engineers.

We specifically invite contributions (original research, systematic reviews, methodological developments, and case studies) under themes including, but not limited to, the following areas:

o Advanced filtering and estimation algorithms addressing sensor inaccuracies and outliers in posture and movement measurements.

o Robust human movement and posture modeling and analytical techniques designed for precise rehabilitation applications.

o Validation and application of novel sensor fusion and data integration approaches in human rehabilitation training contexts.

o Innovative rehabilitation training schemes incorporating engineering methodologies and digital technologies.

o Machine learning and artificial intelligence methods assisting precise individual rehabilitation training control, estimation, and monitoring.

This comprehensive collection of research contributions aims to foster discussion, promote innovative solutions, and set future research agendas in sports technology and rehabilitation engineering fields, ultimately enhancing human movement assessments' practicality, reliability, and accuracy.

Are you interested in contributing a manuscript to this Research Topic?

Engineering Innovations for Improved Rehabilitation Training and Human Movement