BRC FY17 Topic 3: Context and Task-aware Active Perception for Multiagent Systems

Abstract

Proposal develops algorithms that exploit sensors mounted on multi-agent teams subject to limited connectivity to infer environment representations suitable to complete the mission. Since agents will have access to large volumes of streaming data, our work will address the challenge of how to effectively process it to model intents, interactions, and their uncertainties. Work will resolve technical issues with developing compact distributed representations of streaming data; representing and learning context models; and planning effectively for perception- based systems.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 04, 2017
Source ID
N000141712072

Entities

People

  • Jonathan How

Organizations

  • Massachusetts Institute of Technology
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems