This work reports a master-slave separate parallel intelligent mobile robot for the fully autonomous transportation of pallets in the smart factory logistics. This separate parallel intelligent mobile robot consists of two independent sub robots, one master robot and one slave robot. It is similar to two forks of the forklift, but the slave robot does not have any physical or mechanical connection with the master robot. A compact driving unit was designed and used to ensure access to the narrow free entry under the pallets. It was also possible for the mobile robot to perform a synchronous pallet lifting action. In order to ensure the consistency and synchronization of the motions of the two sub robots, high-gain observer was used to synchronize the moving speed, the lifting speed and the relative position. Compared with the traditional forklift AGV (Automated Guided Vehicle), the mobile robot has the advantages of more compact structure, higher expandability and safety. It can move flexibly and take zero-radius turn. Therefore, the intelligent mobile robot is quite suitable for the standardized logistics factory with small working space.

This paper describes an improved brain-inspired simultaneous localization and mapping (RatSLAM) that extracts visual features from saliency maps using a frequency-tuned (FT) model. In the traditional RatSLAM algorithm, the visual template feature is organized as a one-dimensional vector whose values only depend on pixel intensity; therefore, this feature is susceptible to changes in illumination intensity. In contrast to this approach, which directly generates visual templates from raw RGB images, we propose an FT model that converts RGB images into saliency maps to obtain visual templates. The visual templates extracted from the saliency maps contain more of the feature information contained within the original images. Our experimental results demonstrate that the accuracy of loop closure detection was improved, as measured by the number of loop closures detected by our method compared with the traditional RatSLAM system. We additionally verified that the proposed FT model-based visual templates improve the robustness of familiar visual scene identification by RatSLAM.

Inspired by rodents’ free navigation through a specific space, RatSLAM mimics the function of the rat hippocampus to establish an environmental model within which the agent localizes itself. However, RatSLAM suffers from the deficiencies of erroneous loop-closure detection, low reliability on the experience map, and weak adaptability to environmental changes, such as lighting variation. To enhance environmental adaptability, this paper proposes an improved algorithm based on the HSI (hue, saturation, intensity) color space, which is superior in handling the characteristics of image brightness and saturation from the perspective of a biological visual model. The proposed algorithm first converts the raw image data from the RGB (red, green, blue) space into the HSI color space using a geometry derivation method. Then, a homomorphic filter is adopted to act on the I (intensity) channel and weaken the influence of the light intensity. Finally, guided filtering is used to process the S (saturation) channel and improve the significance of image details. The experimental results reveal that the improved RatSLAM model is superior to the original method in terms of the accuracy of visual template matching and robustness.

In robotic radiosurgery, motion tracking is crucial for accurate treatment planning of tumor inside the thoracic or abdominal cavity. Currently, motion characterization for respiration tracking mainly focuses on markers that are placed on the surface of human chest. Nevertheless, limited markers are not capable of expressing the comprehensive motion feature of the human chest and abdomen. In this paper, we proposed a method of respiratory motion characterization based on the voxel modeling of the thoracoabdominal torso. Point cloud data from depth cameras were used to achieve three-dimensional modeling of the chest and abdomen surface during respiration, and a dimensionality reduction algorithm was proposed to extract respiratory features from the established voxel model. Finally, experimental results including the accuracy of voxel model and correlation coefficient were compared to validate the feasibility of the proposed method, which provides enhanced accuracy of target motion correlation than traditional methods that utilized external markers.

Traditional methods of respiration tracking used in radiosurgical robotics employ external optical markers to estimate the tumor position, which requires extracting the respiratory motion characteristics of the chest and establishing correlation models manually. The estimation is easily affected by the placement and number of markers. In order to solve the above problem, an estimation method of tumor location during respiratory motion is proposed using point clouds of the chest and abdominal skin surface. Based on the correlations with the tumor’s location, the essential area of the surface is selected as a data set and processed. Then, a hierarchical network is built to extract the feature of the skin and map those features to the location of tumors. In order to improve the estimation accuracy, a correlation smooth strategy is used to avoid the miss correlations between the skin surface and tumor locations. Investigations are conducted to find the optimal combinations of primary factors. Five typical respiratory data are collected in the experiments. Results show that combining the essential area of the skin surface and the classification network leads to better performance. Further results also show that the error of the proposed method is smaller than that of the traditional optical marker estimation method. Using the proposed method, manually extracting features and establishing correlation models are unnecessary, and the estimation accuracy is increased.