Machine Learning Team Lead at White Hat, Founder/Director at Farset Labs
What is this work about?
Collaborative target tracking behaviours
What are the main findings of this work?
No surprise; two AUVs with a comms link are better at tracking, and that tracking is easier when the targets are stupid/random.
What gap in our understanding does this work fill?
Highlights MLO tracking operations, and provides insight into globally aware control systems
What research tradition/approach/method is used?
Stocastic analysis, utilising Artificial Potential Fields (for Motor Schema control) to factor in multiple behaviours (i.e. target tracking + obstacle avoidance.
Uses simple map maximisation to collaborate between nodes
How is this work connected to the wider research
Stojanovic (2008), Akyildiz/Pompolo (2006) regarding comms environment; Zorzi regarding routing considerations; Freitag (2005), and Deng (2008) regarding collabirative path planning for AUVs
How is this work relevant to your assignment?
More than I was expecting, as it presents the compromise between control and comms planes. Will be used as the basis of my simulation generation.
What are the limitations of this work?
Does not at all factor in trust into the collaborative generation of the global map, or have any kind of temporal backoff from the results of the global map.
Assumes a maximum energy use comms model that is unrealistic and wasteful.
It’s all good.