Recent developments in philosophy, linguistics, developmental psychology and artifcial intelligence make it possible to envision a developmental path for an artifcial agent, grounded in activity-based sensorimotor representations. This paper describes how Neo, an artifcial agent, learns concepts by interacting with its simulated environment. Relatively little prior structure is required to learn fairly accurate representations of objects, activities, locations and other aspects of Neo's experience. We show how classes (categories) can be abstracted from these representations, and discuss how our representation might be extended to express physical schemas, general, domain-independent activities that could be the building blocks of concept formation.