This article is concerned with the problem of planning optimal maneuver trajectories and guiding the mobile robot toward target positions in uncertain environments for exploration purposes. A hierarchical deep learning-based control framework is proposed which consists of an upper level motion planning layer and a lower level waypoint tracking layer. In the motion planning phase, a recurrent deep neural network (RDNN)-based algorithm is adopted to predict the optimal maneuver profiles for the mobile robot. This approach is built upon a recently proposed idea of using deep neural networks (DNNs) to approximate the optimal motion trajectories, which has been validated that a fast approximation performance can be achieved. To further enhance the network prediction performance, a recurrent network model capable of fully exploiting the inherent relationship between preoptimized system state and control pairs is advocated. In the lower level, a deep reinforcement learning (DRL)-based collision-free control algorithm is established to achieve the waypoint tracking task in an uncertain environment (e.g., the existence of unexpected obstacles). Since this approach allows the control policy to directly learn from human demonstration data, the time required by the training process can be significantly reduced. Moreover, a noisy prioritized experience replay (PER) algorithm is proposed to improve the exploring rate of control policy. The effectiveness of applying the proposed deep learning-based control is validated by executing a number of simulation and experimental case studies. The simulation result shows that the proposed DRL method outperforms the vanilla PER algorithm in terms of training speed. Experimental videos are also uploaded, and the corresponding results confirm that the proposed strategy is able to fulfill the autonomous exploration mission with improved motion planning performance, enhanced collision avoidance ability, and less training time.

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.

This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. By introducing a series of event sequences, a new multiphase constrained optimal control formulation is constructed to describe the automatic overtaking process. Although existing trajectory optimization techniques can be applied to address the constructed problem, they may suffer from poor or premature convergence issues due to the complexity of the mission formulation. Thus, to offer an effective alternative, a novel desensitized trajectory optimization method is designed and implemented to explore the optimal overtaking maneuver for the AGVs. The proposed method applies a double layer structure, where an enhanced intelligent optimization method is used in the outer layer such that the main inner optimization routine can be boosted by starting at a better reference solution. The algorithm convergence as well as the solution optimality conditions are theoretically analyzed. Numerical results are provided to illustrate the validity of the established formulation. Comparative case studies were executed to demonstrate the quality of the obtained solution and the enhanced performance of the proposed trajectory optimization method.

A two step strategy is developed for trajectory planning and guidance of a hypersonic vehicle (HV) in the reentry phase. The first step A two step strategy is developed for real-time trajectory planning of a hypersonic vehicle (HV) in the reentry phase. The first step generates the optimal trajectory for the HV using a recently-proposed fuzzy multi-objective transcription method. In the second step, the optimally generated trajectories are utilized to train a deep neural network (DNN) which is then acted as the optimal command generator in real-time. A detailed simulation study was carried out to verify the effectiveness and real-time applicability of the proposed integrated design. The DNN-driven controller is further compared against other optimization-based techniques existing in relative works. Moreover, extension works on the real-time trajectory planning of a 6DoF HV model were performed. The results confirm the feasibility and reliability of applying the proposed method for the planning of hypersonic vehicle entry flight path in real-time.