Wei Guo

The sampling-based motion planner is the mainstream method to solve the motion planning problem in high-dimensional space. In the process of exploring robot configuration space, this type of algorithm needs to perform collision query on a large number of samples, which greatly limits their planning efficiency. Therefore, this paper uses machine learning methods to establish a probabilistic model of the obstacle region in configuration space by learning a large number of labeled samples. Based on this, the high-dimensional samples’ rapid collision query is realized. The influence of number of Gaussian components on the fitting accuracy is analyzed in detail, and a self-adaptive model training method based on Greedy expectation-maximization algorithm is proposed. At the same time, this method has the capability of online updating and can eliminate model fitting errors due to environmental changes. Finally, the model is combined with a variety of sampling-based motion planners and is validated in multiple sets of simulations and real world experiments. The results show that, compared with traditional methods, the proposed method has significantly improved the planning efficiency.

In "Literary Variation of Indian Buddhist Stories in Chinese 志怪 Novels," Wei Guo discusses Buddhist Sutra scriptures which have been a reservoir of inspiration for Zhiguai novels since their first introduction in Chinese literature. Buddhist texts were less relevant for the "documentary" tradition of Chinese literature owing to their rough structure, vague context, and lack of a sense of history and reality, since they were originally intended as texts of didacticism. Hence, in order to integrate these exotic literary materials with local aesthetic concepts, Chinese writers explored creative adaptations including the addition of adding detail, linguistic embellishments, and the endowment of each story with specific narrative scenes in terms of character, place, and time. Guo argues that Indian Buddhist stories have been remolded in Zhiguai novels and transformed from imaginary religious literature into figurative and documentary literature whereby the convergence of the source texts with the target texts shows the processes of formation of world literature.

Self-contribution may be an influential factor in fairness consideration and consequent behavioral decisions. Few studies have investigated simultaneous effects of task difficulty and self-contribution on fairness consideration outcomes and associated neurophysiological responses. To elucidate modulation effects of task difficulty and self-contribution on fairness consideration, 30 recruited participants played a modified ultimatum game while undergoing event-related potential measurements. A 2 × 3 × 2 within-subject design was adopted. A significant interaction between fairness type and contribution was observed in the behavioral data, with unfair offers being more acceptable in the other-contribution condition than in the self-contribution or both-contribution conditions. In the early processing time window, feedback-related negative magnitudes were greater in the hard condition than in the easy condition. P300 responses were more pronounced when participants contributed equally to the proposer than in the self- and other-contribution conditions. These results demonstrated that individuals’ decisions are influenced by their own effort contributions relative to those of others in cooperative contexts.

The making of infrared templates is of great significance for improving the accuracy and precision of infrared imaging guidance. However, collecting infrared images from fields is difficult, of high cost, and time-consuming. In order to address this problem, an infrared image generation method, infrared generative adversarial networks, based on conditional generative adversarial networks architecture is proposed. In I-GANs, visible images instead of random noise are used as the inputs, and the D-LinkNet network is also utilized to build the generative model, enabling improved learning of rich image textures and identification of dependencies between images. Moreover, the PatchGAN architecture is employed to build a discriminant model to process the high-frequency components of the images effectively and reduce the amount of calculation required. In addition, batch normalization is used to optimize the training process, and thereby, the instability and mode collapse of the generated adversarial network training can be alleviated. Finally, experimental verification is conducted on the produced infrared/visible light dataset. The experimental results reveal that high-quality and reliable infrared data are generated by the proposed I-GANs.

This study explores how and when ethical leadership predicts three forms of team-level creativity, namely team creativity, average of member creativity, and dispersion of member creativity. The results, based on 230 members of 44 knowledge work teams from Chinese organizations, showed that ethical leadership was positively related to team creativity and average of member creativity but was negatively related to dispersion of member creativity. Consistent with the predictions of uncertainty reduction theory, psychological safety climate mediated the relationship between ethical leadership and the three forms of team-level creativity. Furthermore, supervisor support for creativity positively moderated the effect of ethical leadership on psychological safety climate and the indirect effects of ethical leadership on the three forms of team-level creativity through psychological safety climate. The analysis offers significant theoretical and practical implications on ethical leadership and creativity in organizations.