The Machine Common Sense (MCS) program seeks to address the challenge of machine common sense by pursuing two broad strategies. Both envision machine common sense as a computational service, or as machine commonsense services. The first strategy aims to create a service that learns from experience, like a child, to construct computational models that mimic the core domains of child cognition for objects (intuitive physics), agents (intentional actors), and places (spatial navigation). The second strategy seeks to develop a service that learns from reading the Web, like a research librarian, to construct a commonsense knowledge repository capable of answering natural language and image-based questions about commonsense phenomena.
Project Overview and Background
- DARPA Machine Common Sense Page
- Concept Paper at Arxiv
- Proposer's Day YouTube Video
MCS Program Links
Examples
Violation of expectation examples using IntPhys (https://intphys.com/)