Autonomy for AGI

This paper provides a very useful and promising analysis and comparison of current architectures of autonomous intelligent systems acting in real time and specific contexts, with all their constraints. The chosen issue of Cognitive Architectures and Autonomy is really a challenge for AI current projects and future research. I appreciate and endorse not only that challenge but many specific choices and claims; in particular: (i) that “autonomy” is a key concept for general intelligent systems; (ii) that “a core issue in cognitive architecture is the integration of cognitive processes ....”; (iii) the analysis of features and capabilities missing in current architectures; (iv) that an appropriate benchmark is still lacking; (v) the stress on “real time”, on learning, on “resource management” (though goals and motivation would deserve a more central role); and especially (vi) the nice characterization of “some key features that a robot’s mind must possess” (attention, expectation, models, ...).