Search

Large-scale 3-D lidar maps are widely used in mobile robot localization because they can provide excellent constraints. However, the enormous number of point clouds imposes constraints on communication, storage, and computation, which brings a massive demand for localization-oriented point cloud map compression. This article proposes an efficient localization-oriented 3-D lidar map compression algorithm. First, we construct a multipose lidar sampling model based on feasible regions so that the compressed map includes observation data on multiple trajectories. Then, a localization error sensitivity analysis is introduced to score the map points, and their localization contribution is calculated according to the 6-DOF scores and observability of the map points. Finally, according to the localization contribution of map points, multiresolution map compression units and a specific line-to-plane ratio are used to compress the map. We have conducted multiple sets of comparative experiments with our self-recorded multitrajectory dataset to demonstrate the effectiveness and efficiency of our algorithm. Compared with different map compression algorithms, the final results show that when the compression ratio drops to 0.1%, although other algorithms fail, our algorithm can still provide high localization accuracy, which reaches map compression for efficient localization.

Neural network models of machine learning have shown promising prospects for visual tasks, such as facial emotion recognition (FER). However, the generalization of the model trained from a dataset with a few samples is limited. Unlike the machine, the human brain can effectively realize the required information from a few samples to complete the visual tasks. To learn the generalization ability of the brain, in this article, we propose a novel brain-machine coupled learning method for facial emotion recognition to let the neural network learn the visual knowledge of the machine and cognitive knowledge of the brain simultaneously. The proposed method utilizes visual images and electroencephalogram (EEG) signals to couple training the models in the visual and cognitive domains. Each domain model consists of two types of interactive channels, common and private. Since the EEG signals can reflect brain activity, the cognitive process of the brain is decoded by a model following reverse engineering. Decoding the EEG signals induced by the facial emotion images, the common channel in the visual domain can approach the cognitive process in the cognitive domain. Moreover, the knowledge specific to each domain is found in each private channel using an adversarial strategy. After learning, without the participation of the EEG signals, only the concatenation of both channels in the visual domain is used to classify facial emotion images based on the visual knowledge of the machine and the cognitive knowledge learned from the brain. Experiments demonstrate that the proposed method can produce excellent performance on several public datasets. Further experiments show that the proposed method trained from the EEG signals has good generalization ability on new datasets and can be applied to other network models, illustrating the potential for practical applications.