Quantifying Natural and Artificial Intelligence in Robots and Natural Systems with an Algorithmic Behavioural Test
This addresses the challenge of defining and measuring intelligence and life-like properties for researchers in robotics, AI, and artificial life, but it appears incremental as it surveys an existing metric rather than introducing a new one.
The paper tackles the problem of evaluating artificial systems' capabilities by proposing a concrete metric to measure abstract properties like environmental reactivity and behavioral control in both natural and artificial systems, without providing specific numerical results.
One of the most important aims of the fields of robotics, artificial intelligence and artificial life is the design and construction of systems and machines as versatile and as reliable as living organisms at performing high level human-like tasks. But how are we to evaluate artificial systems if we are not certain how to measure these capacities in living systems, let alone how to define life or intelligence? Here I survey a concrete metric towards measuring abstract properties of natural and artificial systems, such as the ability to react to the environment and to control one's own behaviour.