Weight-Mate: Adaptive Training Support for Weight Lifting

Weightlifting is easy to learn, but difficult to master. People who do weightlifting do it to improve their health, strengthen their muscles and build their physique. However, due to the complex and precise body positioning required, even experienced weightlifters require assistance in perfecting their technique. At the same time, the training requirements of the individual change over time, as they perfect and hone their craft. To help weightlifters achieve optimum personal performance, we designed Weight-Mate, a prototype wearable system for giving weightlifters of different skill levels personalized, precise and non-distracting immediate feedback on how to correct their current body positioning during deadlift training. By iterating Weight-Mate using cooperative usability testing (CUT) with weightlifters of different competencies with their coaches we designed a system that could adapt to individual physiology and training needs. The Weight-Mate sensor suit maps the lifter's body configuration against the ideal deadlift position throughout all stages of the life, as defined by their coach, and provides non-intrusive feedback to the lifter to correct their body position. Our formative evaluation with ten weightlifters shows that an adaptive approach to digital weight training offers great promise in assisting weight lifters of all levels to improve their technique, and hence improve the safety of the sport.

[1]  Anup Basu,et al.  A framework for adaptive training and games in virtual reality rehabilitation environments , 2011, VRCAI '11.

[2]  Frederic Martini,et al.  Anatomy & Physiology: E-Book , 2015 .

[3]  F. G. Evans,et al.  Anatomical Data for Analyzing Human Motion , 1983 .

[4]  B MilesMatthew,et al.  Qualitative Data Analysis , 2009, Approaches and Processes of Social Science Research.

[5]  Frederick H. Martini,et al.  Fundamentals of Anatomy & Physiology , 1989 .

[6]  Katie A. Siek,et al.  Pt Viz: towards a wearable device for visualizing knee rehabilitation exercises , 2013, CHI.

[7]  Susanne Boll,et al.  Human centered training: perceived exertion as main parameter for training adaption , 2014, NordiCHI.

[8]  Alon Eliakim,et al.  Visual feedback gait re-training in overweight children can reduce excessive tibial acceleration during walking and running: An experimental intervention study. , 2019, Gait & posture.

[9]  Joaquim A. Jorge,et al.  Physio@Home: design explorations to support movement guidance , 2014, CHI Extended Abstracts.

[10]  Masud Moshtaghi,et al.  Detecting unseen anomalies in weight training exercises , 2016, OZCHI.

[11]  Carme Torras,et al.  Adaptable Multimodal Interaction Framework for Robot-Assisted Cognitive Training , 2018, HRI.

[12]  P. Chundi,et al.  Dynamically adapting training systems based on user interactions , 2011, KDMS '11.

[13]  K. Seers Qualitative data analysis , 2011, Evidence Based Nursing.

[14]  Richard Bentley,et al.  Ethnographically-informed systems design for air traffic control , 1992, CSCW '92.

[15]  Danah Mulqueen,et al.  Using video modeling and video feedback to improve olympic weightlifting technique. , 2014 .

[16]  Hans-Werner Gellersen,et al.  MotionMA: motion modelling and analysis by demonstration , 2013, CHI.

[17]  Tovi Grossman,et al.  YouMove: enhancing movement training with an augmented reality mirror , 2013, UIST.

[18]  J Edworthy,et al.  The use of male or female voices in warnings systems: a question of acoustics. , 2003, Noise & health.

[19]  Kasper Hornbæk,et al.  Cooperative usability testing: complementing usability tests with user-supported interpretation sessions , 2005, CHI Extended Abstracts.