Navigating Robot Swarms Using Collective Intelligence Learned from Golden Shiner Fish
Navigating networked robot swarms often requires knowing where to go, sensing the environment, and path-planning based on the destination and barriers in the environment. Such a process is computationally intensive. Moreover, as the network scales up, the computational load increases quadratically, or even exponentially. Unlike these man-made systems, most biological systems scale linearly in complexity. Furthermore, the scale of a biological swarm can even enable collective intelligence. One example comes from observations of golden shiner fish. Golden shiners naturally prefer darkness and school together. Each individual golden shiner does not know where the darkness is. Neither does it sense the light gradients in the environment. However, by moving together as a school, they always end up in the shady area. We apply such collective intelligence learned from golden shiner fish to navigating robot swarms. Each individual robot's dynamic is based on the gold shiners' movement strategy---a random walk with its speed modulated by the light intensity and its direction affected by its neighbors. The theoretical analysis and simulation results show that our method 1) promises to navigate a robot swarm with little situational knowledge, 2) simplifies control and decision-making for each individual robot, 3) requires minimal or even no information exchange within the swarm, and 4) is highly distributed, adaptive, and robust.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingNavigateMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning of Coordination Policies for Robotic Swarms
Inspired by biological swarms, robotic swarms are envisioned to solve real-world problems that are difficult for individual agents. Biological swarms can achieve collective intelligence based on local interactions and si…
Emotional Metaheuristics For in-situ Foraging Using Sensor Constrained Robot Swarms
We present a new social animal inspired emotional swarm intelligence technique. This technique is used to solve a variant of the popular collective robots problem called foraging. We show with a simulation study how simp…
Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms
Robot swarms often exhibit emergent behaviors that are fascinating to observe; however, it is often difficult to predict what swarm behaviors can emerge under a given set of agent capabilities. We seek to efficiently lev…
Self-Supervised LearningA Unified Stochastic Mechanism Underlying Collective Behavior in Ants, Physical Systems, and Robotic Swarms
Biological swarms, such as ant colonies, achieve collective goals through decentralized and stochastic individual behaviors. Similarly, physical systems composed of gases, liquids, and solids exhibit random particle moti…
Asymmetric physics enables efficient learning in quadrupedal robot swarms
Animal collectives navigate cluttered environments through local coordination, yet robot swarms still struggle to reproduce this capability in the physical world. End-to-end learning offers a route to such coordination, …
Reinforcement Learning