We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...
Physical human-robot interaction can be significantly improved when being aware about the role each partner takes in a joint manipulation task. This holds especially in computer ...
To perform as desired in a dynamic environment a vision system must adapt to a variety of operating conditions by selecting vision modules, tuning their parameters, and controllin...
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
An interactive system is described for creating and animating deformable 3D characters. By using a hybrid layered model of kinematic and physics-based components together with an ...