CoordiNet: Constrained Dynamics Learning for State Coordination Over Graph
- 24 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal and Information Processing over Networks
- Vol. 9, 242-257
Abstract
A neural architecture to efficiently coordinate the transitions of state variables (states) over a graph is proposed. We consider the coordination of the time evolution of the state variables associated with the nodes on a graph. The states are associated with physical attributes of agents, e.g., the speed and/or location of vehicles. Efficient coordination then corresponds to the optimization of dynamics (how fast do vehicles travel) that may be subject to constraints (travel must be collision-free). The aim of this paper is (i) the formulation of learnable constrained dynamics which governs the transition of states under constraints over a graph and (ii) to show its industrial application. Firstly, we formulate continuous ordinary differential equations (ODEs), namely forward propagation of state transitions over a graph and backward propagation to optimize model parameters for the learnable constrained dynamics. Discretization of these continuous ODEs results in the neural architecture CoordiNet . Secondly, as an application of CoordiNet, we address a traffic coordination problem by learning constrained dynamics such that vehicles can travel as fast as possible without collisions. Simulation experiments of traffic coordination confirm that our method maximizes the vehicles' speed states while avoiding collisions.Keywords
Funding Information
- IEEE Publication Technology Group
This publication has 12 references indexed in Scilit:
- Continuous-time finite-horizon ADP for automated vehicle controller design with high efficiency2020
- Neural ODEs as the deep limit of ResNets with constant weightsAnalysis and Applications, 2020
- Cooperative Multi-Vehicle Behavior Coordination for Autonomous Driving2019
- Parallel Optimal Control for Cooperative Automation of Large-scale Connected Vehicles via ADMM2018
- Densely Connected Convolutional Networks2017
- A Survey on the Coordination of Connected and Automated Vehicles at Intersections and Merging at Highway On-RampsIEEE Transactions on Intelligent Transportation Systems, 2016
- Convex Analysis and Monotone Operator Theory in Hilbert Spaces2011
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- A dual algorithm for the solution of nonlinear variational problems via finite element approximationComputers & Mathematics with Applications, 1976
- The Numerical Solution of Parabolic and Elliptic Differential EquationsJournal of the Society for Industrial and Applied Mathematics, 1955