Limb biomechanics in combat sports: insights from wearable sensor technology

Abstract

The application of wearable sensor technology in combat sports has created unprecedented opportunities for the objective, in-field analysis of limb biomechanics. This review synthesizes the current state of academic research on the use of wearable sensors for analyzing combat sports. We provide a comprehensive overview of the research landscape, identifying key sub-domains, including performance analysis, injury risk assessment, and training load monitoring. The primary sensor technologies employed are inertial measurement units (IMUs), surface electromyography (sEMG), and pressure sensors, which are increasingly used to quantify kinematic and kinetic variables of punches, kicks, and other combat-specific movements. The review details representative research findings within each sub-domain, highlighting how wearable sensors have been used to differentiate skill levels, classify techniques, estimate impact forces, and monitor fatigue. We critically examine the main challenges and controversies in the field, including the crucial issues of sensor validation against gold-standard laboratory equipment, the lack of standardized testing protocols, and the practical challenges of translating complex data into actionable insights for coaches and athletes. Finally, we offer a forward-looking perspective on the future of this interdisciplinary field, emphasizing the potential of multi-sensor fusion, advanced machine learning algorithms, and the development of smart textiles to further enhance our understanding of combat sports biomechanics. This review aims to provide a structured overview for researchers, practitioners, and technologists, while also outlining a roadmap for future investigations to overcome existing limitations and unlock the potential of wearable technology in combat sports.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.