Abstract:
ZRob is a drum robot designed to learn rhythmic patterns through interaction. Rhythmic patterns usually are assumed to be planned and predictable to some extent. Especially when we want to make machines or robots for performing these patterns. But, can we observe interesting patterns out of chaos? According to the theory of the dynamical systems, in chaotic systems, the behavior of the states or outputs is unpredictable. Specifically, robots can have chaotic behavior because of their nonlinear dynamics. In robot control research, an important goal is to stabilize the dynamics of the robots and avoid chaos. In ZRob however, chaos can be helpful as a source of creativity. In this talk, I will discuss the possibility of observing emergent rhythmic patterns using the chaotic dynamics of ZRob. In an experiment using ZRob, the results showed interesting drumming patterns which are pretty unique and hardly feasible for humans to play. The current study is going to be presented in the NIME conference as well.
Bio:
Mojtaba Karbasi is a PhD fellow at RITMO Centre at the University of Oslo. His research is focused on robot control and learning, reinforcement learning, cognitive robotics, and motor control theories. He is currently working on drum robots which are designed to learn drumming tasks through interaction with the environment. In this work, he is exploring reinforcement learning methods and motor control models to develop an interactive robotic system for playing the drum. Learn more about his research on the drum robot "ZRob" here.