Browsing by Author "Chen, C. L. Philip"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen 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.
  • Thumbnail Image
    ItemOpen 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.
  • Thumbnail Image
    ItemOpen 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.