The global planning module of car-like robots usually plans a coarse spatial path, which may be non-smooth and kinematically infeasible for car-like robots. This study proposes an efficient spatial path smoothing approach, which is capable of optimizing a rough spatial path to be a high quality one. Two novel designs contribute to the proposed approach. One is a direct corridor construction method that provides an optimization region for path optimization. Based on a redefined path representation in the generated corridor, the second one is a core spatial path optimization method, where the optimization problem is formulated as a multi-objective quadratic programming (QP) with corridor and maximum-curvature constraints. Meanwhile, integrating a two-steps strategy into an optimization process yields a good trade-off between efficiency and quality. Experiment results validate that the proposed approach has the ability to online generate a high quality path.
Data-driven soft sensors have increasingly been applied for the quality measurement of industrial polymerization processes in recent years. However, owing to the costly assay process, the limited labeled data available still pose significant obstacles to the construction of accurate models. In this study, a novel soft sensor named the selective Wasserstein generative adversarial network, with gradient penalty-based support vector regression (SWGAN-SVR), is proposed to enhance quality prediction with limited training samples. Specifically, the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is employed to capture the distribution of the available limited labeled data and to generate virtual candidates. Subsequently, an effective data-selection strategy is developed to alleviate the problem of varied-quality samples caused by the unstable training of the WGAN-GP. The selection strategy includes two parts: the centroid metric criterion and the statistical characteristic criterion. An SVR model is constructed based on the qualified augmented training data to evaluate the prediction performance. The superiority of SWGAN-SVR is demonstrated, using a numerical example and an industrial polyethylene process.