Modeling Social Common Sense for Seamless Human-Machine Teaming: Inverting the "Intuitive Game Engine" with Probabilistic Programming"

Abstract

Developing a model that can infer the intention of a single agent and predict its future actions. Modeling human reasoning about beliefs and desires. Optimal control for dexterous manipulation with learned local models. Developing models of coordinated action for teaming.

Document Details

Document Type
DoD Grant Award
Publication Date
Dec 04, 2018
Source ID
W911NF1510639

Entities

People

  • Joshua B. Tenenbaum

Organizations

  • Army Contracting Command
  • Massachusetts Institute of Technology
  • Office of the Secretary of Defense

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML