CERES :: Browsing by Author "Xia, Yuanqing"

Browsing by Author "Xia, Yuanqing"

Now showing 1 - 20 of 24

Open Access
Attitude tracking control for reentry vehicles using centralised robust model predictive control
(Elsevier, 2022-09-02) Chai, Runqi; Tsourdos, Antonios; Gao, Huijun; Chai, Senchun; Xia, Yuanqing
In this work, a centralised robust model predictive control (CRMPC) algorithm is proposed for reentry vehicles to track reference attitude trajectories subject to state/input constraints and uncertainties. In contrast to most designs that apply a cascade control structure for the two-timescale attitude dynamical systems, the proposed control scheme utilises a centralised structure to avoid additional controller development and parameter turning. By designing a nonlinear feedback law and tightening the system constraints, robust constraint satisfaction can be ensured for all admissible uncertainties. In addition, to guarantee the recursive feasibility and closed-loop stability of the proposed CRMPC, a terminal controller, along with a terminal region, is introduced. The validity of using the proposed approach to solve the considered problem is confirmed by executing several experimental studies, which were compared against two other established methods.
Open Access
Deep learning-based trajectory planning and control for autonomous ground vehicle parking maneuver
(IEEE, 2022-06-23) Chai, Runqi; Liu, Derong; Liu, Tianhao; Tsourdos, Antonios; Xia, Yuanqing; Chai, Senchun
In this paper, a novel integrated real-time trajectory planning and tracking control framework capable of dealing with autonomous ground vehicle (AGV) parking maneuver problems is presented. In the motion planning component, a newly-proposed idea of utilizing deep neural networks (DNNs) for approximating optimal parking trajectories is further extended by taking advantages of a recurrent network structure. The main aim is to fully exploit the inherent relationships between different vehicle states in the training process. Furthermore, two transfer learning strategies are applied such that the developed motion planner can be adapted to suit various AGVs. In order to follow the planned maneuver trajectory, an adaptive learning tracking control algorithm is designed and served as the motion controller. By adapting the network parameters, the stability of the proposed control scheme, along with the convergence of tracking errors, can be theoretically guaranteed. In order to validate the effectiveness and emphasize key features of our proposal, a number of experimental studies and comparative analysis were executed. The obtained results reveal that the proposed strategy can enable the AGV to fulfill the parking mission with enhanced motion planning and control performance. Note to Practitioners—This article was motivated by the problem of optimal automatic parking planning and tracking control for autonomous ground vehicles (AGVs) maneuvering in a restricted environment (e.g., constrained parking regions). A number of challenges may arise when dealing with this problem (e.g., the model uncertainties involved in the vehicle dynamics, system variable limits, and the presence of external disturbances). Existing approaches to address such a problem usually exploit the merit of optimization-based planning/control techniques such as model predictive control and dynamic programming in order for an optimal solution. However, two practical issues may require further considerations: 1). The nonlinear (re)optimization process tends to consume a large amount of computing power and it might not be affordable in real-time; 2). Existing motion planning and control algorithms might not be easily adapted to suit various types of AGVs. To overcome the aforementioned issues, we present an idea of utilizing the recurrent deep neural network (RDNN) for planning optimal parking maneuver trajectories and an adaptive learning NN-based (ALNN) control scheme for robust trajectory tracking. In addition, by introducing two transfer learning strategies, the proposed RDNN motion planner can be adapted to suit different AGVs. In our follow-up research, we will explore the possibility of extending the developed methodology for large-scale AGV parking systems collaboratively operating in a more complex cluttered environment.
Open Access
Design and implementation of deep neural network-based control for automatic parking maneuver process
(IEEE, 2020-12-17) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing; Chen, C. L. Philip
This article focuses on the design, test, and validation of a deep neural network (DNN)-based control scheme capable of predicting optimal motion commands for autonomous ground vehicles (AGVs) during the parking maneuver process. The proposed design utilizes a multilayer structure. In the first layer, a desensitized trajectory optimization method is iteratively performed to establish a set of time-optimal parking trajectories with the consideration of noise-perturbed initial configurations. Subsequently, by using the preplanned optimal parking trajectory data set, several DNNs are trained in order to learn the functional relationship between the system state-control actions in the second layer. To obtain further improvements regarding the DNN performances, a simple yet effective data aggregation approach is designed and applied. These trained DNNs are then utilized as the motion controllers to generate feedback actions in real time. Numerical results were executed to demonstrate the effectiveness and the real-time applicability of using the proposed control scheme to plan and steer the AGV parking maneuver. Experimental results were also provided to justify the algorithm performance in real-world implementations.
Open Access
Dual-loop tube-based robust model predictive attitude tracking control for spacecraft with system constraints and additive disturbances
(IEEE, 2021-05-05) Chai, Runqi; Tsourdos, Antonios; Gao, Huijun; Xia, Yuanqing; Chai, Senchun
In this paper, the problem of optimal time-varying attitude tracking control for rigid spacecraft with system constraints and unknown additive disturbances is considered. Through the design of a new non-linear tube-based robust model predictive control (TRMPC) algorithm, a dual-loop cascaded tracking control framework is established. The proposed TRMPC algorithm explicitly considers the effect of disturbances and applies tightened system constraints to predict the motion of the nominal system. The obtained optimal control action is then combined with a non-linear feedback law such that the actual system trajectories can always be steered within a tube region centred around the nominal solution. To facilitate the recursive feasibility of the optimization process and guarantee the input-to-state stability of the tracking control process, the terminal controller and the corresponding terminal invariant set are also constructed. The effectiveness of using the proposed dual-loop TRMPC control scheme to track reference attitude trajectories is validated by experimental studies. A number of comparative studies were carried out, and the obtained results reveal that the proposed design is able to achieve more promising constraint handling and attitude tracking performance than that of the other newly developed methods investigated in this research.
Open Access
Efficient and near-optimal global path planning for AGVs: a DNN-based double closed-loop approach with guarantee mechanism
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Zhang, Runda; Chai, Runqi; Chen, Kaiyuan; Zhang, Jinning; Chai, Senchun; Xia, Yuanqing; Tsourdos, Antonios
In this article, a novel global path planning approach with rapid convergence properties for autonomous ground vehicles (AGVs) named neural sampling rapidly exploring random tree (NS-RRT*) is proposed. This approach has a three-layer structure to obtain a feasible and near-optimal path. The first layer is the data collection stage. Utilizing the target area adaptive rapidly exploring random tree (TAA-RRT*) algorithm to establish a collection of paths considering the initial noise disturbance. To enhance network generalization, an optimal path backward generation (OPBG) strategy is introduced to augment the dataset size. In the second layer, the deep neural network (DNN) is trained to learn the relationships between the states and the sampling strategies. In the third layer, the trained model is used to guide RRT* sampling, and an efficient guarantee mechanism is also designed to ensure the feasibility of the planning task. The proposed algorithm can assist the RRT* algorithm in efficiently obtaining optimal or near-optimal strategies, significantly enhancing search efficiency. Numerical results and experiments are executed to demonstrate the feasibility and efficiency of the proposed method.
Open Access
Fast generation of chance-constrained flight trajectory for unmanned vehicles
(IEEE, 2020-11-16) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Wang, Shuo; Xia, Yuanqing; Chai, Senchun
In this work, a fast chance-constrained trajectory generation strategy incorporating convex optimization and convex approximation of chance constraints is designed so as to solve the unmanned vehicle path planning problem. A pathlength- optimal unmanned vehicle trajectory optimization model is constructed with the consideration of the pitch angle constraint, the curvature radius constraint, the probabilistic control actuation constraint, and the probabilistic collision avoidance constraint. Subsequently, convexification technique is introduced to convert the nonlinear problem formulation into a convex form. To deal with the probabilistic constraints in the optimization model, convex approximation techniques are introduced such that the probabilistic constraints are replaced by deterministic ones, while simultaneously preserving the convexity of the optimization model. Numerical results, obtained from a number of case studies, validate the effectiveness and reliability of the proposed approach. A number of comparative studies were also performed. The results confirm that the proposed design is able to produce more optimal flight paths and achieve enhanced computational performance than other chance-constrained optimization approaches investigated in this paper.
Open Access
High-fidelity trajectory optimization for aeroassisted vehicles using variable order pseudospectral method
(Elsevier, 2020-08-15) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing
In this study, the problem of time-optimal reconnaissance trajectory design for the aeroassisted vehicle is considered. Different from most works reported previously, we explore the feasibility of applying a high-order aeroassisted vehicle dynamic model to plan the optimal flight trajectory such that the gap between the simulated model and the real system can be narrowed. A highly-constrained optimal control model containing six-degree-of-freedom vehicle dynamics is established. To solve the formulated high-order trajectory planning model, a pipelined optimization strategy is illustrated. This approach is based on the variable order Radau pseudospectral method, indicating that the mesh grid used for discretizing the continuous system experiences several adaption iterations. Utilization of such a strategy can potentially smooth the flight trajectory and improve the algorithm convergence ability. Numerical simulations are reported to demonstrate some key features of the optimized flight trajectory. A number of comparative studies are also provided to verify the effectiveness of the applied method as well as the high-order trajectory planning model.
Open Access
Improved gradient-based algorithm for solving aeroassisted vehicle trajectory optimization problems
(American Institute of Aeronautics and Astronautics, 2017-05-04) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing
Space maneuver vehicles (SMVs) [1,2] will play an increasingly important role in the future exploration of space because their on-orbit maneuverability can greatly increase the operational flexibility, and they are more difficult as a target to be tracked and intercepted. Therefore, a well-designed trajectory, particularly in the skip entry phase, is a key for stable flight and for improved guidance control of the vehicle [3,4]. Trajectory design for space vehicles can be treated as an optimal control problem. Because of the highly nonlinear characteristics and strict path constraints of the problem, direct methods are usually applied to calculate the optimal trajectories, such as the direct multiple shooting method [5], direct collocation method [5,6], or hp hp -adaptive pseudospectral method [7,8].
Open Access
An interactive fuzzy physical programming for solving multiobjective skip entry problem
(IEEE, 2017-04-24) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Xia, Yuanqing
The multi-criteria trajectory planning for Space Manoeuvre Vehicle (SMV) is recognised as a challenging problem. Because of the nonlinearity and uncertainty in the dynamic model and even the objectives, it is hard for decision makers to balance all of the preference indices without violating strict path and box constraints. In this paper, to provide the designer an effective method and solve the trajectory hopping problem, an Interactive Fuzzy Physical Programming (IFPP) algorithm is introduced. A new multi-objective SMV optimal control problem is formulated and parameterized using an adaptive technique. By using the density function, the oscillations of the trajectory can be captured effectively. In addition, an interactive decision-making strategy is applied to modify the current designer’s preferences during optimization process. Two realistic decision-making scenarios are conducted by using the proposed algorithm; Simulation results indicated that without driving objective functions out of the tolerable region, the proposed approach can have better performance in terms of the satisfactory degree compared with other approaches like traditional weighted-sum method, Goal Programming (GP) and fuzzy goal programming (FGP). Also, the results can satisfy the current preferences given by the decision makers. Therefore, The method is potentially feasible for solving multi-criteria SMV trajectory planning problems.
Open Access
Multi-objective optimal parking maneuver planning of autonomous wheeled vehicles
(IEEE, 2020-01-01) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing; Philip Chen, C. L.
This paper proposes a computational trajectory optimization framework for solving the problem of multi-objective automatic parking motion planning. Constrained automatic parking maneuver problem is usually difficult to solve because of some practical limitations and requirements. This problem becomes more challenging when multiple objectives are required to be optimized simultaneously. The designed approach employs a swarm intelligent algorithm to produce the trade-off front along the objective space. In order to enhance the local search ability of the algorithm, a gradient operation is utilized to update the solution. In addition, since the evolutionary process tends to be sensitive with respect to the flight control parameters, a novel adaptive parameter controller is designed and incorporated in the algorithm framework such that the proposed method can dynamically balance the exploitation and exploration. The performance of using the designed multi-objective strategy is validated and analyzed by performing a number of simulation and experimental studies. The results indicate that the present approach can provide reliable solutions and it can outperform other existing approaches investigated in this paper.
Open Access
Multiobjective overtaking maneuver planning of autonomous ground vehicles
(IEEE, 2020-03-05) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing; Chen, C. L. Philip
This paper proposes a computational trajectory optimization framework for solving the problem of multi-objective automatic parking motion planning. Constrained automatic parking maneuver problem is usually difficult to solve because of some practical limitations and requirements. This problem becomes more challenging when multiple objectives are required to be optimized simultaneously. The designed approach employs a swarm intelligent algorithm to produce the trade-off front along the objective space. In order to enhance the local search ability of the algorithm, a gradient operation is utilized to update the solution. In addition, since the evolutionary process tends to be sensitive with respect to the flight control parameters, a novel adaptive parameter controller is designed and incorporated in the algorithm framework such that the proposed method can dynamically balance the exploitation and exploration. The performance of using the designed multi-objective strategy is validated and analyzed by performing a number of simulation and experimental studies. The results indicate that the present approach can provide reliable solutions and it can outperform other existing approaches investigated in this paper.
Open Access
Optimal fuel consumption finite-thrust orbital hopping of aeroassisted spacecraft
(Elsevier, 2018-02-03) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing
In the paper, the problem of minimum-fuel aeroassisted spacecraft regional reconnaissance (orbital hopping) is considered. A new nonlinear constrained optimal control formulation is designed and constructed so as to describe this mission scenario. This formulation contains multiple exo-atmospheric and atmospheric flight phases and correspondingly, two sets of flight dynamics. The constructed continuous-time optimal control system is then discretized via a multi-phase global collocation technique. The resulting discrete-time system is optimized using a newly proposed gradient-based optimization algorithm. Several comparative simulations are carried out and the obtained optimal results indicate that it is effective and feasible to use the proposed multi-phase optimal control design for achieving the aeroassisted vehicle orbital hopping mission.
Open Access
Optimal tracking guidance for aeroassisted spacecraft reconnaissance mission based on receding horizon control
(IEEE, 2018-01-25) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing
This paper focuses on the application of model predictive control (MPC) for the spacecraft trajectory tracking problems. The motivation of the use of MPC, also known as receding horizon control, relies on its ability in dealing with control, state and path constraints that naturally arise in practical trajectory planning problems. Two different MPC schemes are constructed to solve the reconnaissance trajectory tracking problem. Since the MPC solves the online optimal control problems at each sampling instant, the computational cost associated with it can be high. In order to decrease the computational demand due to the optimization process, a newly proposed two-nested gradient method is used and embedded in the two MPC schemes. Simulation results are provided to illustrate the effectiveness and feasibility of the two MPC tracking algorithms combined with the improved optimization technique.
Open Access
Review of advanced guidance and control algorithms for space/aerospace vehicles
(Elsevier, 2021-03-01) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing; Chen, C.L. Philip
The design of advanced guidance and control (G&C) systems for space/aerospace vehicles has received a large amount of attention worldwide during the last few decades and will continue to be a main focus of the aerospace industry. Not surprisingly, due to the existence of various model uncertainties and environmental disturbances, robust and stochastic control-based methods have played a key role in G&C system design, and numerous effective algorithms have been successfully constructed to guide and steer the motion of space/aerospace vehicles. Apart from these stability theory-oriented techniques, in recent years, we have witnessed a growing trend of designing optimisation theory-based and artificial intelligence (AI)-based controllers for space/aerospace vehicles to meet the growing demand for better system performance. Related studies have shown that these newly developed strategies can bring many benefits from an application point of view, and they may be considered to drive the onboard decision-making system. In this paper, we provide a systematic survey of state-of-the-art algorithms that are capable of generating reliable guidance and control commands for space/aerospace vehicles. The paper first provides a brief overview of space/aerospace vehicle guidance and control problems. Following that, a broad collection of academic works concerning stability theory-based G&C methods is discussed. Some potential issues and challenges inherent in these methods are reviewed and discussed. Then, an overview is given of various recently developed optimisation theory-based methods that have the ability to produce optimal guidance and control commands, including dynamic programming-based methods, model predictive control-based methods, and other enhanced versions. The key aspects of applying these approaches, such as their main advantages and inherent challenges, are also discussed. Subsequently, a particular focus is given to recent attempts to explore the possible uses of AI techniques in connection with the optimal control of the vehicle systems. The highlights of the discussion illustrate how space/aerospace vehicle control problems may benefit from these AI models. Finally, some practical implementation considerations, together with a number of future research topics, are summarised.
Open Access
A review of optimization techniques in spacecraft flight trajectory design
(Elsevier, 2019-06-04) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing
For most atmospheric or exo-atmospheric spacecraft flight scenarios, a well-designed trajectory is usually a key for stable flight and for improved guidance and control of the vehicle. Although extensive research work has been carried out on the design of spacecraft trajectories for different mission profiles and many effective tools were successfully developed for optimizing the flight path, it is only in the recent five years that there has been a growing interest in planning the flight trajectories with the consideration of multiple mission objectives and various model errors/uncertainties. It is worth noting that in many practical spacecraft guidance, navigation and control systems, multiple performance indices and different types of uncertainties must frequently be considered during the path planning phase. As a result, these requirements bring the development of multi-objective spacecraft trajectory optimization methods as well as stochastic spacecraft trajectory optimization algorithms. This paper aims to broadly review the state-of-the-art development in numerical multi-objective trajectory optimization algorithms and stochastic trajectory planning techniques for spacecraft flight operations. A brief description of the mathematical formulation of the problem is firstly introduced. Following that, various optimization methods that can be effective for solving spacecraft trajectory planning problems are reviewed, including the gradient-based methods, the convexification-based methods, and the evolutionary/metaheuristic methods. The multi-objective spacecraft trajectory optimization formulation, together with different class of multi-objective optimization algorithms, is then overviewed. The key features such as the advantages and disadvantages of these recently-developed multi-objective techniques are summarised. Moreover, attentions are given to extend the original deterministic problem to a stochastic version. Some robust optimization strategies are also outlined to deal with the stochastic trajectory planning formulation. In addition, a special focus will be given on the recent applications of the optimized trajectory. Finally, some conclusions are drawn and future research on the development of multi-objective and stochastic trajectory optimization techniques is discussed.
Open Access
Six-DOF spacecraft optimal trajectory planning and real-time attitude control: a deep neural network-based approach
(IEEE, 2019-12-12) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing; Chen, C. L. Philip
This brief presents an integrated trajectory planning and attitude control framework for six-degree-of-freedom (6-DOF) hypersonic vehicle (HV) reentry flight. The proposed framework utilizes a bilevel structure incorporating desensitized trajectory optimization and deep neural network (DNN)-based control. In the upper level, a trajectory data set containing optimal system control and state trajectories is generated, while in the lower level control system, DNNs are constructed and trained using the pregenerated trajectory ensemble in order to represent the functional relationship between the optimized system states and controls. These well-trained networks are then used to produce optimal feedback actions online. A detailed simulation analysis was performed to validate the real-time applicability and the optimality of the designed bilevel framework. Moreover, a comparative analysis was also carried out between the proposed DNN-driven controller and other optimization-based techniques existing in related works. Our results verify the reliability of using the proposed bilevel design for the control of HV reentry flight in real time.
Open Access
Solving constrained trajectory planning problems using biased particle swarm optimization
(IEEE, 2021-01-11) Chai, Runqi; Tsourdos, Antonios; Savvaris, Al; Chai, Senchun; Xia, Yuanqing
Constrained trajectory optimization has been a critical component in the development of advanced guidance and control systems. An improperly planned reference trajectory can be a main cause of poor online control performance. Due to the existence of various mission-related constraints, the feasible solution space of a trajectory optimization model may be restricted to a relatively narrow corridor, thereby easily resulting in local minimum or infeasible solution detection. In this work, we are interested in making an attempt to handle the constrained trajectory design problem using a biased particle swarm optimization approach. The proposed approach reformulates the original problem to an unconstrained multi-criterion version by introducing an additional normalized objective reflecting the total amount of constraint violation. Besides, to enhance the progress during the evolutionary process, the algorithm is equipped with a local exploration operation, a novel ε-bias selection method, and an evolution restart strategy. Numerical simulation experiments, obtained from a constrained atmospheric entry trajectory optimization example, are provided to verify the effectiveness of the proposed optimization strategy. Main advantages associated with the proposed method are also highlighted by executing a number of comparative case studies.
Open Access
Solving multiobjective constrained trajectory optimization problem by an extended evolutionary algorithm
(IEEE, 2018-11-22) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Xia, Yuanqing; Chai, Senchun
Highly constrained trajectory optimization problems are usually difficult to solve. Due to some real-world requirements, a typical trajectory optimization model may need to be formulated containing several objectives. Because of the discontinuity or nonlinearity in the vehicle dynamics and mission objectives, it is challenging to generate a compromised trajectory that can satisfy constraints and optimize objectives. To address the multiobjective trajectory planning problem, this paper applies a specific multiple-shooting discretization technique with the newest NSGA-III optimization algorithm and constructs a new evolutionary optimal control solver. In addition, three constraint handling algorithms are incorporated in this evolutionary optimal control framework. The performance of using different constraint handling strategies is detailed and analyzed. The proposed approach is compared with other well-developed multiobjective techniques. Experimental studies demonstrate that the present method can outperform other evolutionary-based solvers investigated in this paper with respect to convergence ability and distribution of the Pareto-optimal solutions. Therefore, the present evolutionary optimal control solver is more attractive and can offer an alternative for optimizing multiobjective continuous-time trajectory optimization problems.
Open Access
Solving trajectory optimization problems in the presence of probabilistic constraints
(IEEE, 2019-02-07) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing; Wang, Shuo
The objective of this paper is to present an approximation-based strategy for solving the problem of nonlinear trajectory optimization with the consideration of probabilistic constraints. The proposed method defines a smooth and differentiable function to replace probabilistic constraints by the deterministic ones, thereby converting the chance-constrained trajectory optimization model into a parametric nonlinear programming model. In addition, it is proved that the approximation function and the corresponding approximation set will converge to that of the original problem. Furthermore, the optimal solution of the approximated model is ensured to converge to the optimal solution of the original problem. Numerical results, obtained from a new chance-constrained space vehicle trajectory optimization model and a 3-D unmanned vehicle trajectory smoothing problem, verify the feasibility and effectiveness of the proposed approach. Comparative studies were also carried out to show the proposed design can yield good performance and outperform other typical chance-constrained optimization techniques investigated in this paper.
Open Access
Stochastic spacecraft trajectory optimization with the consideration of chance constraints
(IEEE, 2019-04-18) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios; Chai, Senchun; Xia, Yuanqing
This brief investigates a computational framework based on optimal control for addressing the problem of stochastic trajectory optimization with the consideration of chance constraints. This design employs a discretization technique to parameterize uncertain variables and create the trajectory ensemble. Subsequently, the resulting discretized version of the problem is solved by applying standard optimal control solvers. In order to provide reliable gradient information to the optimization algorithm, a smooth and differentiable chance-constraint approximation method is proposed to replace the original probability constraints. The established methodology is implemented to explore the optimal trajectories for a spacecraft entry flight planning scenario with noise-perturbed dynamics and probabilistic constraints. Simulation results and comparative studies demonstrate that the present chance-constraint handling strategy can outperform other existing approaches analyzed in this brief, and this computational framework can produce reliable and less conservative solutions for the chance-constrained stochastic spacecraft trajectory planning problem.