CADR-RAS Webinar: Robust coordinated autonomy through Dec-MCTS with communicated behavioural intent

We are developing multi-robot coordination algorithms for enabling coordinated manoeuvres that are tightly-coupled, robust, interpretable, and applicable to Defence-relevant missions such as scouting and target tracking.

This project aims to address several fundamental challenges revealed through our high-TRL Defence projects, including:

1. developing new representations for encoding "behavioural intent" to be communicated between coordinating robots,
2. exploring coordination strategies for scouting ahead to provide valuable information to high value assets, and
3. performing coordinated information gathering in cluttered and congested environments.

We have proposed a variety of algorithmic solutions to these challenges, including generalisations of our decentralised Monte Carlo tree search (Dec-MCTS) coordination algorithm and incorporating Behaviour Trees as a convenient and interpretable encoding for "behavioural intent".

This talk will also touch on our related projects at UTS involving large scale field demonstrations of coordinated autonomous systems for Defence, and how the new fundamental algorithms developed in this project could be incorporated into future system demonstrations.