ONRG-CSP: RSS Workshop on behavioral inference of remotely sensed multi-agent systems

Abstract

Unsupervised learning of interaction dynamics and behavior from multi-agentobservations has broad applications in physics, computer vision and robotics.Examples of multi-agent dynamic scenarios of interest in robotics includeautonomous driving, livestock monitorin g or competitive team games, such as therobocup. In all these problems, we can identify multiple agents (vehicles, animals,players, etc.) that dynamically interact with each other in complex ways that may bedifficult to sense and analyze. Accurate modeling of thei r intended behavior andactions can improve not only a robot s capacity to perceive the world, as inSimultaneous Localization And Map ping (SLAM), but also its capacity to makeinformed decisions and act accordingly.A successful approach to these issues requires the use of advanced inferencealgorithms that utilize state-of-the-art machine learning, data analysis, and dynamicalsystem modeling. In addition, specialized sensors, such as Electro-Optical/Infra-Redor event-based cameras, may play an important role in the perception process byproviding alternative modalities with contrasting and complementary capabilities thathelp discriminate characteristic act ions. More importantly, the interplay betweeninference algorithms and sensors can prove critical in the development of successfulrob otic systems that are able to properly discern and identify multi-agent behaviors.This workshop seeks to bring together experts in t he areas of Mathematics, MachineLearning, Perception, Communications, Sensors, Robotics and Control into onecommon forum for discuss ion regarding state-of-the-art methods for detection,classification, and behavioral inference of remotely-sensed, multi-agent dynami calsystems and their application in robotics.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 20, 2021
Source ID
N629092112046

Entities

People

  • Eduardo Montijano

Organizations

  • Office of Naval Research
  • United States Navy
  • University of Zaragoza

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Distributed Systems and Data Platform Development
  • Materials Science.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Autonomy - Autonomous System Control