Following work on joint object-action representations, the functional\nobject-oriented network (FOON) was introduced as a knowledge graph\nrepresentation for robots. Taking the form of a bipartite graph, a FOON\ncontains symbolic or high-level information that would be pertinent to a\nrobot's understanding of its environment and tasks in a way that mirrors human\nunderstanding of actions. In this work, we outline a road-map for future\ndevelopment of FOON and its application in robotic systems for task planning as\nwell as knowledge acquisition from demonstration. We propose preliminary ideas\nto show how a FOON can be created in a real-world scenario with a robot and\nhuman teacher in a way that can jointly augment existing knowledge in a FOON\nand teach a robot the skills it needs to replicate the demonstrated actions and\nsolve a given manipulation problem.\n