Gangshan Jing
multi-agent systems, formation control, reinforcement learning, network localization
Works (6)
Updated: October 14th, 2024 09:58
2022 journal article
Fuel-Optimal Guidance for End-to-End Human-Mars Entry, Powered-Descent, and Landing Mission
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 58(4), 2837–2854.
author keywords: Convex functions; Optimal control; Convergence; Computational modeling; Aerodynamics; Programming; Mars; Alternating direction method of multipliers (ADMM); human-Mars entry; powered-descent; and landing (EDL); trajectory optimization
UN Sustainable Development Goal Categories
7. Affordable and Clean Energy
(OpenAlex)
11. Sustainable Cities and Communities
(Web of Science)
Sources: Web Of Science, NC State University Libraries
Added: October 24, 2022
2021 article
Decomposability and Parallel Computation of Multi-Agent LQR
2021 AMERICAN CONTROL CONFERENCE (ACC), pp. 4527–4532.
author keywords: Reinforcement learning; linear quadratic regulator; multi-agent systems; decomposition
TL;DR:
This work proposes a parallel RL scheme for a linear quadratic regulator (LQR) design in a continuous-time linear MAS and shows that if the MAS is homogeneous then this decomposition retains closed-loop optimality.
(via Semantic Scholar)
open access via arxiv.org (repository)
Sources: Web Of Science, NC State University Libraries
Added: November 1, 2021
2021 journal article
Learning Distributed Stabilizing Controllers for Multi-Agent Systems
IEEE CONTROL SYSTEMS LETTERS, 6, 301–306.
author keywords: Heuristic algorithms; Multi-agent systems; Power system dynamics; Approximation algorithms; Damping; System dynamics; Regulators; Reinforcement learning; linear quadratic regulator; optimal distributed control; multi-agent systems
TL;DR:
This work addresses model-free distributed stabilization of heterogeneous continuous-time linear multi-agent systems using reinforcement learning (RL) and builds upon the results of the first algorithm, and extends it to distributed stabilized systems with predefined interaction graphs.
(via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries
Added: July 19, 2021
2021 article
Local Shape-Preserving Formation Maneuver Control of Multi-agent Systems: From 2D to 3D
2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), pp. 6251–6257.
author keywords: Formation control; rigidity theory; multi-agent systems
TL;DR:
This paper proposes a formation maneuver control strategy to steer a triangulated formation from two dimensional space to three dimensional space, while maintaining the shape of each triangle during the transition, using a weak rigidity function containing both distance and angle constraints.
(via Semantic Scholar)
UN Sustainable Development Goal Categories
11. Sustainable Cities and Communities
(Web of Science)
Sources: Web Of Science, NC State University Libraries
Added: May 31, 2022
2021 journal article
Model-Free Optimal Control of Linear Multiagent Systems via Decomposition and Hierarchical Approximation
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 8(3), 1069–1081.
author keywords: Decomposition; hierarchical control; large-scale networks; linear quadratic regulator (LQR); model-free reinforcement learning (RL)
TL;DR:
A hierarchical controller is proposed that adheres to a particular structure as specified by the inter-agent coupling in the objective function and by the decomposition strategy, and mathematical formulations are established to find a decomposition that minimizes required communication links or reduces the optimality gap.
(via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries
Added: October 4, 2021
2020 journal article
Model-Free Reinforcement Learning of Minimal-Cost Variance Control
IEEE CONTROL SYSTEMS LETTERS, 4(4), 916–921.
author keywords: Mathematical model; Heuristic algorithms; Stochastic processes; Iterative methods; Riccati equations; Computational complexity; Optimal control; Reinforcement learning; stochastic dynamic systems; variance control; coupled Riccati equations
TL;DR:
Two reinforcement learning algorithms for solving a class of coupled algebraic Riccati equations for linear stochastic dynamic systems with unknown state and input matrices where the input matrix can be estimated at the very first iteration are proposed.
(via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries
Added: July 13, 2020
Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.
Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.