showing how a swarm of agents can escape a dead end obstacle
At the MBI workshop for collective behavior, I forged a collaboration with Helen McCreery, Varun Joshi, and Justin Werfel. We created swarms using a classical model of swarming (agents avoid, align, and get attracted to others in the swarm depending on discrete distance zones around the focal agent) which are on their way to a goal. We showed that these swarms can escape a dead-end obstacle without any additional rules besides being repelled by the obstacle. The escape probability depends mostly on the strength of alignment: The higher this parameter, the more likely it is that swarms either follow the walls or ‘bounce’ out of the obstacle. (Joshi et al., 2022)
Left: Illustration of the model, Middle: Escape of the swarm, Right: Trapped swarm.
Coordinated movement in animal groups (flocks, schools, herds, etc.) is a classic and well-studied form of collective behaviour. Most theoretical studies consider agents in unobstructed spaces; however, many animals move in often complicated environments and must navigate around and through obstacles. Here we consider simulated agents behaving according to typical flocking rules, with the addition of repulsion from obstacles, and study their collective behaviour in environments with concave obstacles (dead ends). We find that groups of such agents heading for a goal can spontaneously escape dead ends without wall-following or other specialized behaviours, in what we term ‘flocking escapes’. The mechanism arises when agents align with one another while heading away from the goal, forming a self-stable cluster that persists long enough to exit the obstacle and avoids becoming trapped again when turning back towards the goal. Solitary agents under the same conditions are never observed to escape. We show that alignment with neighbours reduces the effective turning speed of the group while letting individuals maintain high manoeuvrability when needed. The relative robustness of flocking escapes in our studies suggests that this emergent behaviour may be relevant for a variety of animal species.
