Is The Leader Robot an Adequate Sensor for Posture Estimation and Ergonomic Assessment of A Human Teleoperator?

Ergonomic assessment of human posture plays a vital role in understanding\nwork-related safety and health. Current posture estimation approaches face\nocclusion challenges in teleoperation and physical human-robot interaction. We\ninvestigate if the leader robot is an adequate sensor for posture estimation in\nteleoperation and we introduce a new probabilistic approach that relies solely\non the trajectory of the leader robot for generating observations. We model the\nhuman using a redundant, partially-observable dynamical system and we infer the\nposture using a standard particle filter. We compare our approach with postures\nfrom a commercial motion capture system and also two least-squares optimization\napproaches for human inverse kinematics. The results reveal that the proposed\napproach successfully estimates human postures and ergonomic risk scores\ncomparable to those estimates from gold-standard motion capture.\n