This chapter introduces the implementations of artificial agents in robotics. The first section looks at the early development of robotics in GOFAI (Good Old-Fashioned AI). SHAKEY is a representative example designed to operate and perform simple tasks in the real world, which illustrates the physical symbol system hypothesis. The second section introduces alternative ideas from situated cognition theorists. The ideas are inspired by studies on simple cognitive systems such as those of insects, to pursue simple architecture robotics that can solve complex problems. The third section reviews how these theoretical ideas have been translated into particular robotic architectures, focusing on subsumption architectures and some examples of behavior-based robotics.

Traditionally, to test whether the hypothesised organisation of behaviour generates the behavioural markers selected for measurement has required experiments or comparisons across species, sex and age. In the last couple of decades, important strides have been made in developing ways to create virtual animals, either on a computer screen or as freely moving robots, that can be programmed to produce the behaviour of interest. If the programmed rules are sufficient to produce the behaviour of real animals, then that adds independent evidence for the proposed organisation. Novel testing methods is one direction for the future. Another is to identify additional organisational principles. For example, some level of randomness seems essential for the production of effective functional behaviour. A challenge for the future is to understand how random processes are integrated with the causal processes described in the preceding chapters.

Traditionally, to test whether the hypothesised organisation of behaviour generates the behavioural markers selected for measurement has required experiments or comparisons across species, sex and age. In the last couple of decades, important strides have been made in developing ways to create virtual animals, either on a computer screen or as freely moving robots, that can be programmed to produce the behaviour of interest. If the programmed rules are sufficient to produce the behaviour of real animals, then that adds independent evidence for the proposed organisation. Novel testing methods is one direction for the future. Another is to identify additional organisational principles. For example, some level of randomness seems essential for the production of effective functional behaviour. A challenge for the future is to understand how random processes are integrated with the causal processes described in the preceding chapters.