Explore DDD 2019 – Denver, Sept. 16-20
This is the third in a series of talks on developing cognitive models for autonomous robots. In 2017, Jean-François presented a homebrew model, inspired by Minsky's Society of Mind, that he implemented as a hobby project for his Lego robots. He showed robots scurrying about for food and safety, all the while emoting audibly. Fun! But they couldn't learn, so he went back to the drawing board. In 2018, inspired by current neuroscience research in Predictive Processing, he rebuilt his robot's cognitive model to enable (some) learning. It worked! Jean-François got his robot to learn more effective behaviors from experience, but he had only scratched the surface.
In 2019, he expanded his Predictive Processing-inspired cognitive model so that a robot could also learn the intentions of other robots. The goal is to have them get better at competing for food, avoiding running into each other, etc. In a way, his robots are now building and evolving "models of mind" of each other while interacting (just like we do.) Robots modeling the minds of robots!
About Jean-François Cloutier
An avid programmer since the 80s, Jean-François has used and abused Prolog, LISP, Smalltalk, Java, and now Elixir.
He is a DDD, Functional Programming, and Actor Model enthusiast.
He has forever been obsessed about domain knowledge, conceptual clarity, and consistent naming.
He works in Portland, Maine as an independent consultant.
In his spare time, he trains regularly at Aikido of Maine, organizes the local Erlang/Elixir and Elm meetups, and dabbles in robotics with the Lego Robotics sets he bought "for his son".
WEBSITE: http://exploreddd.com
TWITTER: http://twitter.com/ExploreDDD
