A Testbed for Provably Correct Mixed Initiative Human-Robot Decision Making

Abstract

We propose to instrument a testbed to support multi-disciplinary research on provably correctmixed initiative human-robot decision making. In an existing ONR MURI program, our team hasdeveloped new theories and systems to answer some of the main challenges in the deployment ofunmanned aerial and ground vehicle platforms identified by the DoD as the coordinationbetween groups of unmanned vehicles and teams of human operators. Built on the past results, inthis project, we will extend our investigation in three new frontiers: 1. In human-robotcollaboration, we will study how to infer optimal system control policies when the humankinematic and dynamic models can be individualized, and their inference can be also adaptive onthe fly. 2. In small unmanned aircraft systems, we will develop multivehicle coordination andcontrol schemes to guarantee correct operation, and we will also design the interface of suchschemes with human operators in the loop. 3. We will continue enhance the capabilities ofsemiautonomous driver assistance systems in multi-mode driver assistance scenarios, inparticular for more difficult off-road terrain scenarios. The abstract is publicly releasable.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 12, 2016
Source ID
N000141612661

Entities

People

  • S. Shankar Sastry

Organizations

  • Office of Naval Research
  • United States Navy
  • University of California Regents

Tags

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Unmanned Aerial System (UAS) Autonomous Capabilities and Mission Reconnaissance.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • Autonomy
  • Autonomy - Autonomous System Control
  • Autonomy - Human-Robot Interaction