Predicting Individualized Joint Kinematics over Continuous Variations of Walking, Running, and Stair Climbing

• DOI: 10.36227/techrxiv.20412171.v1
• Publication Date: 2022-08-08T05:29:57Z
• Authors: Emma Reznick; Cara Welker; Robert Gregg
• Keywords: Stair climbing

<p>GOAL: Accounting for gait individuality is important to positive outcomes with wearable robots, but tuning multi-activity models time-consuming and not viable in a clinic. Generalizations can be made predict unobserved conditions. METHODS: Kinematic individuality—how one person’s joint angles differ from the group—is quantified every subject, joint, ambulation mode (walking, running, stair ascent, descent), intramodal task (speed, incline) an open-source able-bodied dataset. Four N-way ANOVAs test how prediction methods affect fit experimental data between within modes. We whether walking carries across modes, or modal more effective against average kinematics. RESULTS: individualization improves if we consider each separately. Across all tasks, joints, improved 81% of trials, improving on by 4.3º cycle. This was statistically significant at joints half ascent/descent. CONCLUSIONS: tends improve easily predicted observing only mode.</p>