- Designing collective behaviors is cumbersome
- Requires experts for modeling
- Evolutionary computation to generate collective behaviors
$$\frac{dR}{dt} = -aR + vnD , R(0) = R_0$$
$$\frac{dO}{dt} = aR -bO +cE, O(0) = O_0$$
$$\frac{dE}{dt} = q(D)bO - cE, E(0) = E_0$$
$$\frac{dA}{dt} = p(D)bO - mA + wnD$$
$$\frac{dD}{dt} = mA - nD, D(0) = D_0$$
Reference: Stability of choice in the honey bee nest-site selection process
Reference: Evolution of collective behaviors for a real swarm of aquatic surface robots
Merits
Demerits
Reference: GESwarm: Grammatical Evolution for the Automatic Synthesis of Collective Behaviors in Swarm Robotics
Advantages
Disadvantages
Reference: Behavior Trees for Evolutionary Robotics
Reference: odNEAT: An algorithm for distributed online, onboard evolution of robot behaviours
- A multi-agent Grammatical Evolution with BT
Hello! Neighbour!
How are you doing with the phenotype in this environment?
Hello!
I collected 35 oz of water with the phenotype.
Take my genome and perform magic using genetic operators !
This work has been funded by ONR grant number N000141613025.