Memoirs of a Postgrad has an eye-opening analysis of the world of cognitive robotics – the science of developing ‘cognitive agents’.
When we think of ‘intelligent robots’ we tend to think of the human-think-alike androids from science-fiction, but the article argues that we should think about it more in terms of intelligence that would manifest itself it whatever way the robot interacts with the world.
Bats undoubtedly have a special sort of ‘bat intelligence’ because they interact with the world in unique ways and need to perform tasks only relevant to bats.
Similarly, a robot might be small, have wheels and only have limited sensors, and so its intelligence should be ‘embodied’ within its own ways of experiencing and interacting with the world.
However, the article argues there’s more to it than just simple interaction.
…cognition requires not only real-time interaction with the real world (thus incorporating the concept of embodiment), it also requires the ability to internally improve ones interaction with the environment without it actually being present. So, the cognitive agent must be able internally simulate in some way its interactions with the world, and be able to learn from this process…
Link to ‘What does Cognitive Robotics mean?’