Multi-Target Encirclement with Collision Avoidance via Deep Reinforcement Learning using Relational Graphs
Tianle Zhang,Zhen Liu,Zhiqiang Pu,Jianqiang Yi,Tianle Zhang,Zhen Liu,Zhiqiang Pu,Jianqiang Yi
In this paper, we propose a novel decentralized method based on deep reinforcement learning using robot-level and target-level relational graphs, to solve the problem of multi-target encirclement with collision avoidance (MECA). Specifically, the robot-level relational graphs, composed of three heterogeneous relational graphs between each robot and other robots, targets and obstacles, are modeled ...
