No abstract

As the restaurant industry is facing labor shortage issues, the use of meal delivery robots instead of waiters/waitresses not only allows the customers to experience the impact of robot technology but also benefits the restaurant business financially by reducing labor costs. Most existing meal delivery robots employ magnetic navigation technologies, which require magnetic strip installation and changes to the restaurant decor. Once the moving path is changed, the magnetic strips need to be re-laid. This study proposes multisource information fusion, i.e., the fusion of ultra-wide band positioning technology with an odometer and a low-cost gyroscope accelerometer, to achieve the positioning of a non-rail meal delivery robot with navigation. By using a low-cost electronic compass and gyroscope accelerometer, the delivery robot can move along a fixed orbit in a flexible and cost-effective manner with steering control. Ultra-wide band (UWB) and track estimation algorithm are combined by extended Kalman filter (EKF), and the positioning error after fusion is about 15 cm, which is accepted by restaurants. In summary, the proposed approach has some potential for commercial applications.

For the successful application of brain-computer interface (BCI) systems, accurate recognition of electroencephalography (EEG) signals is one of the core issues. To solve the differences in individual EEG signals and the problem of less EEG data in classification and recognition, an attention mechanism-based multi-scale convolution network was designed; the transfer learning data alignment algorithm was then introduced to explore the application of transfer learning for analyzing motor imagery EEG signals. The data set 2a of BCI Competition IV was used to verify the designed dual channel attention module migration alignment with convolution neural network (MS-AFM). Experimental results showed that the classification recognition rate improved with the addition of the alignment algorithm and adaptive adjustment in transfer learning; the average classification recognition rate of nine subjects was 86.03%.

Algorithm frameworks based on feature point matching are mature and widely used in simultaneous localization and mapping (SLAM). However, in the complex and changeable indoor environment, feature point matching-based SLAM currently has two major problems, namely, decreased accuracy of pose estimation due to the interference caused by dynamic objects to the SLAM system and tracking loss caused by the lack of feature points in weak texture scenes. To address these problems, herein, we present a robust and real-time RGB-D SLAM algorithm that is based on ORBSLAM3. For interference caused by indoor moving objects, we add the improved lightweight object detection network YOLOv4-tiny to detect dynamic regions, and the dynamic features in the dynamic area are then eliminated in the algorithm tracking stage. In the case of indoor weak texture scenes, while extracting point features the system extracts surface features at the same time. The framework fuses point and surface features to track camera pose. Experiments on the public TUM RGB-D data sets show that compared with the ORB-SLAM3 algorithm in highly dynamic scenes, the root mean square error (RMSE) of the absolute path error of the proposed algorithm improved by an average of 94.08%. Camera pose is tracked without loss over time. The algorithm takes an average of 34 ms to track each frame of the picture just with a CPU, which is suitably real-time and practical. The proposed algorithm is compared with other similar algorithms, and it exhibits excellent real-time performance and accuracy. We also used a Kinect camera to evaluate our algorithm in complex indoor environment, and also showed high robustness and real-time. To sum up, our algorithm can not only deal with the interference caused by dynamic objects to the system but also stably run in the open indoor weak texture scene.