Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once. To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.

By moving a commercial 2D LiDAR, 3D maps of the environment can be built, based on the data of a 2D LiDAR and its movements. Compared to a commercial 3D LiDAR, a moving 2D LiDAR is more economical. A series of problems need to be solved in order for a moving 2D LiDAR to perform better, among them, improving accuracy and real-time performance. In order to solve these problems, estimating the movements of a 2D LiDAR, and identifying and removing moving objects in the environment, are issues that should be studied. More specifically, calibrating the installation error between the 2D LiDAR and the moving unit, the movement estimation of the moving unit, and identifying moving objects at low scanning frequencies, are involved. As actual applications are mostly dynamic, and in these applications, a moving 2D LiDAR moves between multiple moving objects, we believe that, for a moving 2D LiDAR, how to accurately construct 3D maps in dynamic environments will be an important future research topic. Moreover, how to deal with moving objects in a dynamic environment via a moving 2D LiDAR has not been solved by previous research.

The state-of-the-art visual simultaneous localization and mapping (V-SLAM) systems have high accuracy localization capabilities and impressive mapping effects. However, most of these systems assume that the operating environment is static, thereby limiting their application in the real dynamic world. In this paper, by fusing the information of an RGB-D camera and two encoders that are mounted on a differential-drive robot, we aim to estimate the motion of the robot and construct a static background OctoMap in both dynamic and static environments. A tightly coupled feature-based method is proposed to fuse the two types of information based on the optimization. Dynamic pixels occupied by dynamic objects are detected and culled to cope with dynamic environments. The ability to identify the dynamic pixels on both predefined and undefined dynamic objects is available, which is attributed to the combination of the CPU-based object detection method and a multiview constraint-based approach. We first construct local sub-OctoMaps by using the keyframes and then fuse the sub-OctoMaps into a full OctoMap. This submap-based approach gives the OctoMap the ability to deform, and significantly reduces the map updating time and memory costs. We evaluated the proposed system in various dynamic and static scenes. The results show that our system possesses competitive pose accuracy and high robustness, as well as the ability to construct a clean static OctoMap in dynamic scenes.

An isosceles-trapezoidal flexural pivot can be of great use for practical designs, especially in the cases that a pure rotation about a virtual pivot is required. The analysis of rotational precision for such a structure is important for the mechanical design in precise-required applications. For this purpose, a rigid isosceles-trapezoidal linkage model is first proposed to provide an accurate analytical result for its notch-type flexural counterpart. The influence of dimensional parameters on the center shift is discussed. In order to disclose the equivalence between leaf-type flexure structure and its pseudo-rigid-body model, a transitional model is introduced, from which an equivalent pseudo-rigid-body model for leaf-type isosceles-trapezoidal flexure structure is then derived. The results of both simulation and experiment verify that the equivalent rigid model is also accurate enough in the case of a larger deflection.

Bionic propulsion has advantages over traditional blade propellers, such as efficiency and noise control. Existing research on ray-inspired robot fish has mainly focused on a single type of pectoral fin as bionic propeller, which only performed well in terms of pure speed or maneuverability. Rarely has the performance of different fin types been compared on the same platform to find an optimal solution. In this paper, a modularized robot fish with high-fidelity biomimetic pectoral fins and novel multi-DOF propelling mechanism is presented. A kinematic model of the pectoral fin based on motion analysis of a cownose ray is introduced as guidance for the propelling mechanism design. A high-fidelity parametric geo-model is established and evaluated based on statistical data. The design and fabrication process of the 3D soft bionic fins, as well as the robot platform, is also elaborated. Through experiments comparing the performance of different fin types constructed with different materials and approaches, it was found that the new soft fins made of silicon rubber have better performance than traditional fins constructed with a flexible inner skeleton and a permeable outer skin as a result of better 3D profile preservation and hydrodynamic force interaction. The robot ray prototype also acquires a better combination of high speed and maneuverability compared to results of previous research.