Whole Body Motion Planning

Humanoid robots become increasingly sophisticated, both in terms of their movement as well as their sensorial capabilities. This allows to target for more complicated problems, eventually leading to robotic systems that can perform useful tasks in every days environment. In this paper, we will give an overview on some elements we consider to be important for a movement control and planning architecture. We will first explain the whole body control concept which is the underlying basis for the subsequent elements. We then present a prediction and action selection scheme that evaluates a set of behavioral instances within a parallel prediction architecture. This architecture allows the robot to quickly react to changing environments. We then review a more global movement planning approach which casts the overall robot movement into an integral optimization problem, and leads to smooth and collision-free movements within interaction time.