Human Robot Collaborative Assembly Planning: An Answer Set Programming\n Approach

Abstract

For planning an assembly of a product from a given set of parts, robots\nnecessitate certain cognitive skills: high-level planning is needed to decide\nthe order of actuation actions, while geometric reasoning is needed to check\nthe feasibility of these actions. For collaborative assembly tasks with humans,\nrobots require further cognitive capabilities, such as commonsense reasoning,\nsensing, and communication skills, not only to cope with the uncertainty caused\nby incomplete knowledge about the humans' behaviors but also to ensure safer\ncollaborations. We propose a novel method for collaborative assembly planning\nunder uncertainty, that utilizes hybrid conditional planning extended with\ncommonsense reasoning and a rich set of communication actions for collaborative\ntasks. Our method is based on answer set programming. We show the applicability\nof our approach in a real-world assembly domain, where a bi-manual Baxter robot\ncollaborates with a human teammate to assemble furniture. This manuscript is\nunder consideration for acceptance in TPLP.\n