Abstract. Population of simulated agents controlled by dynamical neural networks are trained by artificial evolution to access linguistic instructions and to execute them by indicating, touching or moving specific target objects. During training the agent experiences only a subset of all object/action pairs. During post-evaluation, some of the successful agents proved to be able to access and execute also linguistic instructions not experienced during training. This is owe to the development of a semantic space, grounded on the sensory motor capability of the agent and organised in a systematised way in order to facilitate linguistic compositionality and behavioural generalisation. Key words: Grounding, CTRNNs, Artificial Evolution