• Corpus ID: 239050267

Receding Horizon Control in Deep Structured Teams: A Provably Tractable Large-Scale Approach with Application to Swarm Robotics

@article{Arabneydi2021RecedingHC,
  title={Receding Horizon Control in Deep Structured Teams: A Provably Tractable Large-Scale Approach with Application to Swarm Robotics},
  author={Jalal Arabneydi and Amir G. Aghdam},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.10554}
}
In this paper, a deep structured tracking problem is introduced for a large number of decision-makers. The problem is formulated as a linear quadratic deep structured team, where the decision-makers wish to track a global target cooperatively while considering their local targets. For the unconstrained setup, the gauge transformation technique is used to decompose the resultant optimization problem in order to obtain a low-dimensional optimal control strategy in terms of the local and global… 

Figures and Tables from this paper

Deep Structured Teams in Arbitrary-Size Linear Networks: Decentralized Estimation, Optimal Control and Separation Principle
TLDR
It is proved that the optimal strategy is linear in the local state estimate as well as the deep state estimate and can be efficiently computed by two scale-free Riccati equations and Kalman filters.

References

SHOWING 1-10 OF 28 REFERENCES
Deep Structured Teams in Arbitrary-Size Linear Networks: Decentralized Estimation, Optimal Control and Separation Principle
TLDR
It is proved that the optimal strategy is linear in the local state estimate as well as the deep state estimate and can be efficiently computed by two scale-free Riccati equations and Kalman filters.
Reinforcement Learning in Linear Quadratic Deep Structured Teams: Global Convergence of Policy Gradient Methods
TLDR
It is proved that model-based policy gradient methods globally converge to the optimal solution and model-free policy gradient and natural policy gradient algorithms for the special case of risk-neutral cost function are developed.
Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features
TLDR
This article considers a homogeneous linear regression for Markov chain models and a few orthonormal linear regressions for linear quadratic models and the convergence of two model-free (reinforcement learning) algorithms is established, which are then applied to a smart grid.
Team-optimal solution of finite number of mean-field coupled LQG subsystems
TLDR
A decentralized control system with linear dynamics, quadratic cost, and Gaussian disturbances is considered and it is shown that the optimal control law is unique, linear, and identical across all subsystems.
Fast Model Predictive Control Using Online Optimization
TLDR
A collection of methods for improving the speed of MPC, using online optimization, which can compute the control action on the order of 100 times faster than a method that uses a generic optimizer.
Reinforcement Learning in Nonzero-sum Linear Quadratic Deep Structured Games: Global Convergence of Policy Optimization
TLDR
It is proved that the proposed model-based and model-free policy gradient descent and natural policy gradient ascent algorithms globally converge to the sub-game perfect Nash equilibrium, the first result that provides a global convergence proof of policy optimization in a nonzero-sum LQ game.
Linear Quadratic Mean Field Teams: Optimal and Approximately Optimal Decentralized Solutions
We consider team optimal control of decentralized systems with linear dynamics, quadratic costs, and arbitrary disturbance that consist of multiple sub-populations with exchangeable agents (i.e.,
Optimal Distributed Control for Leader-Follower Networks: A Scalable Design
TLDR
The focus of this paper is directed towards optimal control of multi-agent systems consisting of one leader and a number of followers in the presence of noise, where the optimal distributed strategy is shown to be stationary.
Near-Optimal Control Strategy in Leader-Follower Networks: A Case Study for Linear Quadratic Mean-Field Teams
TLDR
A near-optimal control strategy is proposed that converges to the optimal solution as the number of followers increases and provides a design scheme, where the convergence rate as well as the collective behavior of the followers can be designed by choosing appropriate cost functions.
A Survey on Aerial Swarm Robotics
TLDR
The main sections of this paper focus on major results covering trajectory generation, task allocation, adversarial control, distributed sensing, monitoring, and mapping, and dynamic modeling and conditions for stability and controllability that are essential in order to achieve cooperative flight and distributed sensing.
...
1
2
3
...