Fei Chen

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.

Much of early western research has focused on identity. A primed identity can inhibit the priming of other alternative identities, and also negatively affect the intention to purchase products related to those alternative identities. In western culture, individuals operate within a cultural framework that makes them more likely to prioritize their own goals and less likely to rely on environmental factors when evaluating others. Individuals are more likely to choose products that fit their primed identity. In this study, we suggest that in collectivist Chinese culture, individuals may give priority to group-level goals and attach more importance to situational factors when evaluating others. Therefore, a primed identity may not necessarily inhibit the priming of alternative identities. In this research, we examine the association between a focal identity and alternative identities, with particular emphasis on the accessibility, discrepancies, and effects on purchase intention of alternative identities. We also examine the intent to purchase products related to the alternative identity vs. the focal identity, developing a model with which to explore this construct. We test four hypotheses through experiments using an online questionnaire and analyzing the resulting data using statistical product service solutions 22.0 and the PROCESS macro modeling tool. The results are as follows: First, the association between a focal identity and alternative identity has a positive impact on the accessibility of the alternative identity. The clearer the alternative identity is, the greater the impact of the association between the focal identity and alternative identity on the latter’s accessibility. Second, the accessibility of the alternative identity has a positive impact on the intent to purchase alternative identity vs. focal identity-related products. The greater the discrepancy between the focal identity and the alternative identity, the greater the impact on the intent to purchase alternative identity vs. focal identity-related products. The results of this study confirmed the interaction between identity association and the clarity of the alternative identity, as well as the influence of the accessibility of the alternative identity on the intent to purchase alternative identity vs. focal identity-related products. We contribute to the development of a theory on intention to purchase identity-related products.

In tone languages, some case studies showed that the word-level tonal representation was closely related to the underlying metrical pattern. Based on different tonal patterns in prosodic units, the metrical structures could generally be divided into the left- and right-dominant types in Chinese dialects. Yet the cross-dialectal phonetic realizations (e.g., duration and pitch) between or within these two metrical structures were still unrevealed. The current study investigated the duration and pitch realizations of disyllabic prosodic words in Changsha and Chengdu dialects (the left-dominant structure), and in Fuzhou and Xiamen dialects (the right-dominant structure). Results showed that not all the duration patterns across four Chinese dialects were sensitive to different metrical structures, indicating that the duration might not be the universal cue for metrical prominence in Chinese dialects. In terms of pitch realization across all the four Chinese dialects, level tones (sometimes falling tones) generally appeared in the metrically weak unit, while underlying pitch forms appeared in the metrically strong unit. Compared with duration, pitch might be more robust for prosodic realizations of metrical structures in Chinese dialects. Furthermore, there was an interaction between duration and pitch patterns in Chinese dialects, which could shed new light on the phenomenon of “metrical tone sandhi”. Meanwhile, this study also provides some references for the judgment of the metrical stress and prosodic realizations in other Chinese dialects.

Part-of-speech tagging for English composition is the basis for automatic correction of English composition. The performance of the part-of-speech tagging system directly affects the performance of the marking and analysis of the correction system. Therefore, this paper proposes an automatic scoring model for English composition based on article part-of-speech tagging. First, use the convolutional neural network to extract the word information from the character level and use this part of the information in the coarse-grained learning layer. Secondly, the word-level vector is introduced, and the residual network is used to establish an information path to integrate the coarse-grained annotation and word vector information. Then, the model relies on the recurrent neural network to extract the overall information of the sequence data to obtain accurate annotation results. Then, the features of the text content are extracted, and the automatic scoring model of English composition is constructed by means of model fusion. Finally, this paper uses the English composition scoring competition data set on the international data mining competition platform Kaggle to verify the effect of the model.