We present a method for the control of robot swarms using two subsets of robots: a larger group of simple, oblivious robots (which we call the workers) that is governed by simple local attraction forces, and a smaller group (the guides) with sufficient mission knowledge to create and displace a desired worker formation by operating on the local forces of the workers. The guides coordinate to shape the workers like smart particles by changing their interaction parameters. We study the approach with a large scale experiment in a physics based simulator with up to 5000 robots forming three different patterns. Our experiments reveal that the approach scales well with increasing robot numbers, and presents little pattern distortion. We evaluate the approach on a physical swarm of robots that use visual inertial odometry to compute their relative positions and obtain results that are comparable with simulation. This work lays the foundation for designing and coordinating configurable smart particles, with applications in smart materials and nanomedicine.

翻译：我们提出了一种利用两类机器人子集来控制机器人集群的方法：一个由简单、无感知机器人（称为“工人”）组成的较大群体，它们受简单局部吸引力支配；另一个由具备足够任务知识的较小群体（称为“向导”）组成，通过操控工人的局部作用力，来创建并推移期望的工人编队。向导通过改变工人的交互参数，如同操控智能粒子般协调塑造工人的形态。我们在基于物理的模拟器中进行了大规模实验，涉及多达5000个机器人形成三种不同图案。实验表明，该方法随着机器人数量增加表现出良好的可扩展性，且图案畸变较小。我们还在使用视觉惯性里程计计算相对位置的物理机器人集群上对该方法进行了评估，获得了与模拟可比较的结果。这项工作为设计和协调可配置的智能粒子奠定了基础，并在智能材料和纳米医学中具有应用前景。