Alternative essences of intelligence

We present a novel methodology for building human-like artificially intelligent systems. We take as a model the only existing systems which are universally ac-cepted as intelligent: humans. We emphasize building intelligent systems which are not masters of a single do-main, but, like humans, are adept at performing a vari-ety of complex tasks in the real world. Using evidence from cognitive science and neuroscience, we suggest four alternative essences of intelligence to those held by classical AI. These are the parallel themes of devel-opment, social interaction, embodiment, and integra-tion. Following a methodology based on these themes, we have built a physical humanoid robot. In this paper we present our methodology and the insights it affords for facilitating learning, simplifying the computation underlying rich behavior, and building systems that can scale to more complex tasks in more challenging environments