Unmanned Maritime Operations Pedro Patron Collaborative - - PowerPoint PPT Presentation
Unmanned Maritime Operations Pedro Patron Collaborative - - PowerPoint PPT Presentation
Human-Machine Teaming for Unmanned Maritime Operations Pedro Patron Collaborative Technologies Maritime Autonomy & Technology Showcase 15 th November 2018 Identify what collaborators know so the effort of your actions can stretch to get
Human-Machine Teaming for Unmanned Maritime Operations
Pedro Patron
Collaborative Technologies
Maritime Autonomy & Technology Showcase 15thNovember 2018
Trust Teaming
“The willingness of a party to be vulnerable to the actions of another party based on the expectation that the other will perform a particular action important to the trustor, irrespective of the ability to monitor or control that other party”* “Identify what collaborators know so the effort of your actions can stretch to get things done more effectively together while having the ability to see another’s perspective”*
*own interpretation from definitions from Harvard Business Review, and Mayer et al., 1995, p. 712
TTCP Dstl UW’16
Joint points (the hip)
AUV Operator (Tablet) ROV Operator (Console) Diver (Handheld) Boat/USV Pilot (Dashboard)
Trust by exchanging of mental model
DATA ORIGINAL MODEL
Trust by clear communication
Start the mission! On my way How long until mission completion? 55 minutes Starting survey OpArea0. All previous objectives completed. OK. Proceed Abort objective. Vehicle SN224 taking over. I am not receiving any updates from side-scan sonar
Trust by transparency
10 bytes 20 bytes 5 bytes
1 packet
Sharing the mental model
Original
25 bytes 50 bytes 70 bytes
3 packets
Reconstruction
8192 bytes
Transmission
100 bytes
10 packets
200 bytes 4096 bytes
(JPG compression) (semantic compression)
200 packets 20 bytes / packet
Interacting in natural language
(click image for video)
- Prof. H. Hastie, Dr D. Robb, J. Chiyah
Participating in the mission
Location Vehicle information Vehicle Compass – heading Map Field of view Objectives Vehicle path to objective
(click image for video)
Summary
Current manned–unmanned teaming is limited, reducing operators to ‘autonomy observers’ Control can be replaced by Trust when interactions are transparent at sharing mental model Tasking becomes dynamic and fluid with all teammates participating AR and Natural Language are valid mechanisms for enhancing human-machine interactions