Search

During the Mars ascent vehicle (MAV) launch missions, when encountering a thrust drop type of propulsion system fault problem, the general trajectory replanning methods relying on step-by-step judgments may fail to make timely decisions, potentially leading to mission failure. This paper proposes a suboptimal joint trajectory replanning (SJTR) method, which formulates the joint optimization problem of target orbit and flight trajectory after a fault within a convex optimization framework. By incorporating penalty coefficients for terminal constraints, the optimization solution adheres to the orbit redecision principle, thereby avoiding complex decision-making processes and resulting in a concise and rapid solution to the replanning problem. A learning-based warm-start scheme is proposed in conjunction with the designed SJTR method. Offline, a deep neural network (DNN) is trained using a dataset generated by the SJTR method. Online, the DNN provides initial guesses for the time optimization variables based on the current fault situation, enhancing the solving efficiency and reliability of the algorithm. Numerical simulations of the MAV flight scenario under the thrust drop faults are performed, and Monte Carlo experiments and case studies across all orbit types demonstrate the effectiveness of the proposed method.

Edge computing-based 3D perception has received attention in intelligent transportation systems (ITS) because real-time monitoring of traffic candidates potentially strengthens Vehicle-to-Everything (V2X) orchestration. Thanks to the capability of precisely measuring the depth information on surroundings from LiDAR, the increasing studies focus on lidar-based 3D detection, which significantly promotes the development of 3D perception. Few methods met the real-time requirement of edge deployment because of high computation-intensive operations. Moreover, an inconsistency problem of object detection remains uncovered in the pointcloud domain due to large sparsity. This paper thoroughly analyses this problem, comprehensively roused by recent works on determining inconsistency problems in the image specialisation. Therefore, we proposed a 3D harmonic loss function to relieve the pointcloud based inconsistent predictions. Moreover, the feasibility of 3D harmonic loss is demonstrated from a mathematical optimization perspective. The KITTI dataset and DAIR-V2X-I dataset are used for simulations, and our proposed method considerably improves the performance than benchmark models. Further, the simulative deployment on an edge device (Jetson Xavier TX) validates our proposed model's efficiency., Comment: Submitted to IEEE Transactions on Vehicular Technology