Finding a feasible, collision-free path in line with social activities is an important and challenging task for robots working in dense crowds. In recent years, many studies have used deep reinforcement learning techniques to solve this problem. In particular, it is necessary to find an efficient path in a short time which often requires predicting the interaction with neighboring agents. However, as the crowd grows and the scene becomes more and more complex, researchers usually simplify the problem to a one-way human-robot interaction problem. But, in fact, we have to consider not only the interaction between humans and robots but also the influence of human-human interactions on the movement trajectory of the robot. Therefore, this article proposes a method based on deep reinforcement learning to enable the robot to avoid obstacles in the crowd and navigate smoothly from the starting point to the target point. We use a dual social attention mechanism to jointly model human-robot and human-human interaction. All sorts of experiments demonstrate that our model can make robots navigate in dense crowds more efficiently compared with other algorithms.
The emotion-cause pair extraction task is a fine-grained task in text sentiment analysis, which aims to extract all emotions and their underlying causes in a document. Recent studies have addressed the emotion-cause pair extraction task in a step-by-step manner, i.e., the two subtasks of emotion extraction and cause extraction are completed first, followed by the pairing task of emotion-cause pairs. However, this fail to deal well with the potential relationship between the two subtasks and the extraction task of emotion-cause pairs. At the same time, the grammatical information contained in the document itself is ignored. To address the above issues, we propose a deep neural network based on span association prediction for the task of emotion-cause pair extraction, exploiting general grammatical conventions to span-encode sentences. We use the span association pairing method to obtain candidate emotion-cause pairs, and establish a multi-dimensional information interaction mechanism to screen candidate emotion-cause pairs. Experimental results on a quasi-baseline corpus show that our model can accurately extract potential emotion-cause pairs and outperform existing baselines.
With the continuous development of deep learning, more and more huge deep learning models are developed by researchers, which leads to an exponential increase of the parameters of models. Therein, the convolutional recurrent network as a type of widely used deep learning method is often employed to handle spatiotemporal data, e.g., traffic data. However, because of the large number of parameters in the model, the convolutional recurrent network needs to consume a lot of computing resources and time in the training process. To reduce the consumption of resources, we propose a sparse convolutional recurrent network with a sparse gating mechanism that is able to reduce the complexity of the network by an improved gate unit while keeping the performance of the model. We evaluate the performance of our proposed network on traffic flow datasets, and the experimental results show that the parameters of the model are significantly reduced under the condition of similar prediction accuracy compared with the traditional convolutional recurrent network.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.