VG-Swarm: A Vision-Based Gene Regulation Network for UAVs Swarm Behavior Emergence

We present VG-Swarm, a practical and effective method for aerial robots dynamic encirclement, which consists of vision-based gene regulatory network (V-GRN) visual perception module. For each flying robot deployed with the proposed method, relative spatial positions surrounding robots, targets, obstacles are first obtained by omnidirectional monocular vision. Then is used to generate concentration field within its own range according position information. The agent individually calculates selects an optimal moving direction in field, finally stays on selected encirclement pattern (a closed contour around target). As result, swarm can emerge adaptive formations entrap targets even without any communication global verify effectiveness robustness various simulations real-world experiments.