Measuring task complexity of movement skill is an important factor to evaluate a difficulty of learning and/or imitating a task for autonomous robots. Although many complexity-measures are proposed in research areas such as neuroscience, physics, computer science, and biology, there have been little attention on the robotic tasks. To cope with measuring complexity of robotic task, we propose an information-theoretic measure for task complexity of movement skills. By modeling proprioceptive as well as exteroceptive sensor data as multivariate Gaussian distribution, movements of a task can be modeled as probabilistic model. Additionally, complexity of temporal variations is modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on the real robotic movement tasks.

• 권우영(Department of Electronics and Computer Engineering, Hanyang University) | Woo Young Kwon
• 서일홍(Department of Electronics and Computer Engineering, Hanyang University) | Il Hong Suh Corresponding author
• 이준구(Department of Electronics and Computer Engineering, Hanyang University) | Jungoo Lee
• 유범재(Korea Institute of Science and Technology) | Bum-Jae You
• 오상록(Korea Institute of Science and Technology) | Sang-Rok Oh