We asked 100 people: How would you train our robot?

Abstract

While robotic proficiency excels in constrained environments, the demand for vast amounts of world knowledge to cover unforeseen circumstances, constellations and tasks prevents sufficiently robust real-world application. Human computation has shown to provide successful advances to close this reasoning gap and accumulate knowledge, yet being greatly reliant on the quality of the provided data. In this paper, we introduce the game with a purpose Tool Feud that collects popularity rankings of object choices for robotic everyday activity tasks and evaluate an approach for classifying malicious responses automatically.