@article{wan_jing_dai_rea_2022, title={Fuel-Optimal Guidance for End-to-End Human-Mars Entry, Powered-Descent, and Landing Mission}, volume={58}, ISSN={["1557-9603"]}, DOI={10.1109/TAES.2022.3141325}, abstractNote={This article investigates the fuel-optimal guidance problem of the end-to-end human-Mars entry, powered-descent, and landing (EDL) mission. It applies a unified modeling scheme and develops a computationally efficient new optimization algorithm to solve the multiphase optimal guidance problem. The end-to-end EDL guidance problem is first modeled as a multiphase optimal control problem with different dynamics and constraints at each phase. Via polynomial approximation and discretization techniques, this multiphase optimal control problem is then reformulated as a polynomial programming problem. By introducing intermediate variables and quadratic equality constraints, a polynomial program is equivalently converted into a nonconvex quadratically constrained quadratic program (QCQP). Then, a novel customized alternating direction method of multipliers (ADMM) is proposed to efficiently solve the large-scale QCQP with convergence proof to a local optimum under certain conditions on the algorithmic parameters. The fuel savings under the end-to-end human-Mars EDL guidance are verified by comparing to the fuel consumption using the separate phase guidance approach. Furthermore, the computational efficiency of the customized ADMM algorithm is validated by comparing to the state-of-the-art nonlinear programming method. The robustness of the customized ADMM algorithm is verified via extensive simulation cases with random initial conditions.}, number={4}, journal={IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS}, author={Wan, Changhuang and Jing, Gangshan and Dai, Ran and Rea, Jeremy R.}, year={2022}, month={Aug}, pages={2837–2854} }
 @article{jing_bai_george_chakrabortty_sharma_2022, title={Learning Distributed Stabilizing Controllers for Multi-Agent Systems}, volume={6}, ISSN={["2475-1456"]}, DOI={10.1109/LCSYS.2021.3072007}, abstractNote={We address model-free distributed stabilization of heterogeneous continuous-time linear multi-agent systems using reinforcement learning (RL). Two algorithms are developed. The first algorithm solves a centralized linear quadratic regulator (LQR) problem without knowing any initial stabilizing gain in advance. The second algorithm builds upon the results of the first algorithm, and extends it to distributed stabilization of multi-agent systems with predefined interaction graphs. Rigorous proofs are provided to show that the proposed algorithms achieve guaranteed convergence if specific conditions hold. A simulation example is presented to demonstrate the theoretical results.}, journal={IEEE CONTROL SYSTEMS LETTERS}, author={Jing, Gangshan and Bai, He and George, Jemin and Chakrabortty, Aranya and Sharma, Piyush K.}, year={2022}, pages={301–306} }
 @article{jing_bai_george_chakrabortty_2021, title={Decomposability and Parallel Computation of Multi-Agent LQR}, ISSN={["2378-5861"]}, DOI={10.23919/ACC50511.2021.9483338}, abstractNote={Individual agents in a multi-agent system (MAS) may have decoupled open-loop dynamics, but a cooperative control objective usually results in coupled closed-loop dynamics thereby making the control design computationally expensive. The computation time becomes even higher when a learning strategy such as reinforcement learning (RL) needs to be applied to deal with the situation when the agents dynamics are not known. To resolve this problem, we propose a parallel RL scheme for a linear quadratic regulator (LQR) design in a continuous-time linear MAS. The idea is to exploit the structural properties of two graphs embedded in the $Q$ and $R$ weighting matrices in the LQR objective to define an orthogonal transformation that can convert the original LQR design to multiple decoupled smaller-sized LQR designs. We show that if the MAS is homogeneous then this decomposition retains closed-loop optimality. Conditions for decomposability, an algorithm for constructing the transformation matrix, a parallel RL algorithm, and robustness analysis when the design is applied to non-homogeneous MAS are presented. Simulations show that the proposed approach can guarantee significant speed-up in learning without any loss in the cumulative value of the LOR cost.}, journal={2021 AMERICAN CONTROL CONFERENCE (ACC)}, author={Jing, Gangshan and Bai, He and George, Jemin and Chakrabortty, Aranya}, year={2021}, pages={4527–4532} }
 @article{wan_jing_dai_zhao_2021, title={Local Shape-Preserving Formation Maneuver Control of Multi-agent Systems: From 2D to 3D}, ISSN={["0743-1546"]}, DOI={10.1109/CDC45484.2021.9683637}, abstractNote={In this paper, we propose a formation maneuver control strategy to steer a triangulated formation from two dimensional (2D) space to three dimensional (3D) space, while maintaining the shape of each triangle during the transition. To describe the desired 3D formation shape, we adopt a weak rigidity function containing both distance and angle constraints, together with a sign function. The local shapes are preserved by restricting agents’ motions to the null-space of the distance rigidity function. Furthermore, we formulate this formation maneuver control as an optimal control problem to minimize the control efforts subject to system dynamics, local shape preserving constraints, initial and terminal boundary conditions, which can be solved via a nonlinear programming solver. In the end, two simulation examples are provided to show the effectiveness of our formation control strategy.}, journal={2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC)}, author={Wan, Changhuang and Jing, Gangshan and Dai, Ran and Zhao, Ruike}, year={2021}, pages={6251–6257} }
 @article{jing_bai_george_chakrabortty_2021, title={Model-Free Optimal Control of Linear Multiagent Systems via Decomposition and Hierarchical Approximation}, volume={8}, ISSN={["2372-2533"]}, DOI={10.1109/TCNS.2021.3074256}, abstractNote={Designing the optimal linear quadratic regulator (LQR) for a large-scale multiagent system is time consuming since it involves solving a large-size matrix Riccati equation. The situation is further exasperated when the design needs to be done in a model-free way using schemes such as reinforcement learning (RL). To reduce this computational complexity, we decompose the large-scale LQR design problem into multiple small-size LQR design problems. We consider the objective function to be specified over an undirected graph, and cast the decomposition as a graph clustering problem. The graph is decomposed into two parts, one consisting of independent clusters of connected components, and the other containing edges that connect different clusters. Accordingly, the resulting controller has a hierarchical structure, consisting of two components. The first component optimizes the performance of each independent cluster by solving the small-size LQR design problem in a model-free way using an RL algorithm. The second component accounts for the objective coupling different clusters, which is achieved by solving a least-squares problem in one shot. Although suboptimal, the hierarchical controller adheres to a particular structure as specified by interagent couplings in the objective function and by the decomposition strategy. Mathematical formulations are established to find a decomposition that minimizes the number of required communication links or reduces the optimality gap. Numerical simulations are provided to highlight the pros and cons of the proposed designs.}, number={3}, journal={IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS}, author={Jing, Gangshan and Bai, He and George, Jemin and Chakrabortty, Aranya}, year={2021}, month={Sep}, pages={1069–1081} }
 @article{jing_bai_george_chakrabortty_2020, title={Model-Free Reinforcement Learning of Minimal-Cost Variance Control}, volume={4}, ISSN={["2475-1456"]}, DOI={10.1109/LCSYS.2020.2995547}, abstractNote={This letter proposes two reinforcement learning (RL) algorithms for solving a class of coupled algebraic Riccati equations (CARE) for linear stochastic dynamic systems with unknown state and input matrices. The CARE are formulated for a minimal-cost variance (MCV) control problem that aims to minimize the variance of a cost function while keeping its mean at an acceptable range using a noisy infinite-horizon full-state feedback linear quadratic regulator (LQR). We propose two RL algorithms where the input matrix can be estimated at the very first iteration. This, in turn, frees up significant amount of computational complexity in the intermediate steps of the learning phase by avoiding repeated matrix inversion of a high-dimensional data matrix. The overall complexity is shown to be less than RL for both stochastic and deterministic LQR. Additionally, the disturbance noise entering the model is not required to satisfy any condition for ensuring efficiency of either RL algorithms. Simulation examples are presented to illustrate the effectiveness of the two designs.}, number={4}, journal={IEEE CONTROL SYSTEMS LETTERS}, author={Jing, Gangshan and Bai, He and George, Jemin and Chakrabortty, Aranya}, year={2020}, month={Oct}, pages={916–921} }