ATK Holding Group (China)

Multimodal motion capability is an emerging topic in the robotics field, and this paper presents a hybrid robot system maneuvering in both terrestrial and aerial environments. Firstly, a micro quadruped–quadrotor robot with onboard sensing and computing is developed. This robot incorporates both the high mobility of unmanned aerial vehicles and the long endurance of mobile robots on the ground. A coordinated motion control scheme is then exploited for adaptive terrestrial–aerial motion transition. In this scheme, a bio-inspired terrestrial locomotion controller is proposed to generate various quadruped locomotions, and a model-based aerial locomotion controller is proposed to generate various quadrotor configurations. Then, an unified motion controller for the two subsystems which dynamically adjusts crawling and flying motion in a complicated environment is presented. Consequently, several practical trials are conducted to demonstrate the adaptability and the robustness of the proposed system.

We report on the detailed steps of a method to estimate the biomass of invasive plants based on UAV remote sensing and computer vision. To collect samples from the study area, we prepared a sample square assembly to randomize the sampling points. An unmanned aerial camera system was constructed using a drone and camera to acquire continuous RGB images of the study area through automated navigation. After completing the shooting, the aboveground biomass in the sample frame was collected, and all correspondences were labeled and packaged. The sample data was processed, and the aerial images were segmented into small images of 280 x 280 pixels to create an image dataset. A deep convolutional neural network was used to map the distribution of Mikania micrantha in the study area, and its vegetation index was obtained. The organisms collected were dried, and the dry weight was recorded as the ground truth biomass. The invasive plant biomass regression model was constructed using the K-nearest neighbor regression (KNNR)by extracting the vegetation index from the sample images as an independent variable and integrating it with the ground truth biomass as a dependent variable. The results showed that it was possible to predict the biomass of invasive plants accurately. An accurate spatial distribution map of invasive plant biomass was generated by image traversal, allowing precise identification of high-risk areas affected by invasive plants. In summary, this study demonstrates the potential of combining unmanned aerial vehicle remote sensing withmachine learning techniques to estimate invasive plant biomass. It contributes significantly to the research of new technologies and methods for real-time monitoring of invasive plants and provides technical support for intelligent monitoring and hazard assessment at the regional scale.

With the acceleration of the pace of modern life.many people are suffering from chronic disease[1]. Because of its physiological effects such as improving microcirculation and strengthening metabolism, far infrared fabric is widely used in the weaving of intimate clothing to alleviate diseases related to auxiliary treatment. Therefore, it is very important to explore the wearing comfort performance of far infrared fabric. In this paper, by designing two kinds of knitted fabric structure, six kinds of far-infrared Chinlon fiber yarns were selected to compared with ordinary Chinlon yarns. According to the experimental method of the whole test, 14 samples of knitted fabric are woven on the seamless knitting machine, and the warmth preservation, moisture absorption, moisture permeability and air permeability of the fabric are explored by the method of comparative evaluation. The results showed that the veil of different yarn composition effect for seamless knitted fabric to keep warm, breathable, moisture absorption, moisture permeability, the main factors of fabric structure, when the veil components in coffee polyamide or bamboo charcoal fiber, carbon for jersey seamless knitted fabric structure, has good moisture absorption, when the veil components in metal germanium polyamide, for jersey seamless knitted fabric structure, It has good moisture permeability. When the veil is composed of graphene Chinlon and the structure is 1 +3 false rib seamless knitted fabric, it has good heat retention and air permeability.

In order to combine the lightweight object detection model with small embedded devices and improve the detection accuracy of automobile rim weld, this paper proposes YOLOv4-mini based on improved YOLOv4-tiny. Firstly, the lightweight network YOLOv4-tiny is adopted as the main architecture. Secondly, the M-SPP structure is added to obtain the main features of the target and utilize the Mosaic method to enhance the dataset. The K-means + + clustering method is utilized to reset the anchor data belonging to the rim weld target. Finally, the parameters of the pre-trained model are fine-tuned to complete the training of the model. Compared with the original algorithm, in the detection task at 50% and 75% threshold of 4240 rim weld datasets, the mAP index can reach 100% and 55.15%, with the detection speed of 173.5FPS, respectively. Therefore, the improved algorithm gains higher accuracy and efficiency for the edge weld detection task.

In order to explore the comfortability of far-infrared seamless knitted fabric, this study chose coffee carbon polyamide fiber and graphene polyamide fiber as the face yarn materials to design this experiment. Both face yarn ratio and stitch were experimental factors. According to comprehensive factorials, we weaved 12 samples and tested the warmth, hygroscopicity, moisture vapor transmission and permeability of the fabric. The properties: warmth, hygroscopicity, moisture vapor transmission and permeability were influenced by face yarn ratio and stitch, and the relationship among them was studied by the fuzzy comprehensive evaluation method. The research showed that: factor A, the face yarn ratio has the greatest effect on hygroscopicity. When the face yarn ratio of the fabric is 25:75 with plain plating stitch, fabric hygroscopicity is predominant. And factor B has the greatest influence on moisture vapor transmission and permeability of the fabric. When the face yarn ratio is 25:75, and the stitch is 1+1 false rib, moisture vapor transmission is excellent. When the face yarn ratio is 25:75, and the stitch is 1+3 rib, fabric has the warmest and the most permeable properties.

Hover often occurs during flight. It is easy to distinguish whether the aircraft has a hovering phenomenon by observing trajectory curve by naked eyes, but it is extremely challenging if we want to recognize hover phenomenon automatically and accurately through algorithms. This paper presents a method to identify whether an aircraft hovers and hovering circles based on ADS-B data. It can not only accurately identify whether an aircraft has a hovering phenomenon but also calculate the number of hovering circles around a certain point and support hovering time and hovering location, including longitude and latitude. We use millions of flights data of ADS-B to evaluate our algorithm offline, deploy the solution on Umetrip application, as well as the Air China Control system, which is a collaborative product between Umetrip and Air China. Extensive evaluation shows that the algorithm we propose is significantly better than algorithm before and is ahead of the solutions for aircraft hovering recognition provided in the industry as well.