In the early days of artificial intelligence the focus was on abstract thinking and problem solving. These phenomena could be naturally mapped onto algorithms, which is why originally artificial intelligence was considered to be part of computer science. Over time, it turned out that this view was too limited to understand natural forms of intelligence and that embodiment must be taken into account. As a consequence the focus changed to systems that are able to autonomously interact with their environment. The major implications of embodiment, dynamical and information theoretic, are illustrated in a number of case studies. Two grand challenges, evolving grounded intelligence and exploring ecological balance, i.e. the relation between task environment, morphology, materials, and control in an artificial organism, are discussed.