Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning
Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controllers are readily available, they face limitations in terms of scalability and implementation, as they do not respect the distributed information structure imposed by the network system of agents. Given the difficulties in finding optimal decentralized controllers, we propose a novel framework using graph neural networks (GNNs) to \emph{learn} these controllers. GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties. We show that GNNs learn appropriate decentralized controllers by means of imitation learning, leverage their permutation invariance properties to successfully scale to larger teams and transfer to unseen scenarios at deployment time. The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningSimilar Papers 제목 키워드 기반
Graph Neural Networks for Decentralized Controllers
Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful …
Learning Decentralized Swarms Using Rotation Equivariant Graph Neural Networks
The orchestration of agents to optimize a collective objective without centralized control is challenging yet crucial for applications such as controlling autonomous fleets, and surveillance and reconnaissance using sens…
Graph Neural NetworkMathLearning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network
Recently a line of researches has delved the use of graph neural networks (GNNs) for decentralized control in swarm robotics. However, it has been observed that relying solely on the states of immediate neighbors is insu…
Graph Neural NetworkImitation LearningVGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms
Decentralized coordination of a robot swarm requires addressing the tension between local perceptions and actions, and the accomplishment of a global objective. In this work, we propose to learn decentralized controllers…
Graph Neural NetworkScalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks
In this paper, we present a perception-action-communication loop design using Vision-based Graph Aggregation and Inference (VGAI). This multi-agent decentralized learning-to-control framework maps raw visual observations…
Graph Neural NetworkImitation Learning