2010 Poster Sessions : Human Motion Analysis via Whole-Body Marker Tracking Control

Student Name : Emel Demircan
Advisor : Oussama Khatib
Research Areas: Artificial Intelligence
Abstract:
The synthesis of human motion is a complex procedure that involves accurate modeling and simulation of musculoskeletal kinematics, dynamics and actuation, and characterization of reliable performance criteria. Motivated by the previous robotics research applied to these problems, the present work aims to leverage the task-based approaches to synthesize human motion and provide physiologically accurate performance predictions. This work introduces (i) a robotics-based method for the real-time reconstruction of human motion trajectories using direct marker tracking, (ii) a task-driven muscular e ort minimization criterion and (iii) human performance metrics for dynamic characterization of athletic skills. Dynamic motion reconstruction is achieved through the operational space-control of a simulated human model to track the captured marker trajectories in real-time. A muscular e ort minimization criterion is introduced to analyze human static postures. Finally, task-driven human performance metrics, including the e ort expenditure and the feasible set of operational space accelerations are developed to characterize an athletic skill based on the musculoskeletal physiology. The methodology followed incorporates extensive motion capture experiments, musculoskeletal modeling, real-time simulations and task-oriented control techniques. The future work encloses the extension of that task-based control and simulation framework for providing a feedback mechanism applicable in supporting motion training and rehabilitation.

Bio:
Emel Demircan is a Mechanical Engineering PhD student in Professor Oussama Khatib's robotics group within Arti cal Intelligence Laboratory. Her research focuses on the application of dynamics and control theory for the simulation and analysis of biomechanical and robotic systems. She is broadly interested in human motion analysis to investigate high performance skills for athletic training and performance improvement and rehabilitation of patients with impaired sensory-motor function. Emel received her MS in Mechanical Engineering from Stanford Unversity and BS in Mechanical Engineering and Industrial Engineering from Bogazici University.