Accession Number:

AD1190037

Title:

Implicit Communication in Human-Machine Collaboration

Descriptive Note:

[Technical Report, Final Report]

Corporate Author:

REGENTS OF THE UNIVERSITY OF CALIFORNIA

Personal Author(s):

• Dragan, Anca

Report Date:

2022-11-10

Pagination or Media Count:

8

Abstract:

The goal of this project was to advance human-machine collaboration, specifically focusing on the machines ability to understand and partake in implicit communication. We focused much of the work on inferring underlying human objectives and preferences, from learning from different types of input physical corrections, feature traces, even one single state, to introducing better models of human behavior that lead to better inference, to preventing wrongharmful inference.We also made a number of contributions on enabling robots to communicate themselves implicitly objectives, capabilityincapability, their future task plans, and even emotional state. We have published numerous conference and journal papers, and received 4 best paper nominations three times at HRI, the premier conference in human-robot interaction, and once at TRO.

Descriptors:

• human-robot interaction
• human-machine interfaces
• human-machine systems
• air force
• air force research laboratories
• information systems
• human behavior
• information processing
• reinforcement learning
• scientific research
• computer science
• models
• probabilistic models
• robotics
• robots
• algorithms
• california

Subject Categories:

Distribution Statement:

[A, Approved For Public Release]