Search results

Existing Simultaneous Localization and Mapping (SLAM) algorithms have been relatively well developed. However, when in complex dynamic environments, the movement of the dynamic points on the dynamic objects in the image in the mapping can have an impact on the observation of the system, and thus there will be biases and errors in the position estimation and the creation of map points. The aim of this paper is to achieve more accurate accuracy in SLAM algorithms compared to traditional methods through semantic approaches.

In this paper, the semantic segmentation of dynamic objects is realized based on U-Net semantic segmentation network, followed by motion consistency detection through motion detection method to determine whether the segmented objects are moving in the current scene or not, and combined with the motion compensation method to eliminate dynamic points and compensate for the current local image, so as to make the system robust.

Experiments comparing the effect of detecting dynamic points and removing outliers are conducted on a dynamic data set of Technische Universität München, and the results show that the absolute trajectory accuracy of this paper's method is significantly improved compared with ORB-SLAM3 and DS-SLAM.

In this paper, in the semantic segmentation network part, the segmentation mask is combined with the method of dynamic point detection, elimination and compensation, which reduces the influence of dynamic objects, thus effectively improving the accuracy of localization in dynamic environments.

In this study, an attempt has been made to collect the research that has been done on the construction and design of the H₂O₂ sensor. So far, many efforts have been made to quickly and sensitively determine H₂O₂ concentration based on different analytical principles. In this study, the importance of H₂O₂, its applications in various industries, especially the food industry, and the importance of measuring it with different techniques, especially portable sensors and on-site analysis, have been investigated and studied.

Hydrogen peroxide (H₂O₂) is a very simple molecule in nature, but due to its strong oxidizing and reducing properties, it has been widely used in the pharmaceutical, medical, environmental, mining, textile, paper, food production and chemical industries. Sensitive, rapid and continuous detection of H₂O₂ is of great importance in many systems for product quality control, health care, medical diagnostics, food safety and environmental protection.

Various methods have been developed and applied for the analysis of H₂O₂, such as fluorescence, colorimetry and electrochemistry, among them, the electrochemical technique due to its advantages in simple instrumentation, easy miniaturization, sensitivity and selectivity.

Monitoring the H₂O₂ concentration level is of practical importance for academic and industrial purposes. Edible oils are prone to oxidation during processing and storage, which may adversely affect oil quality and human health. Determination of peroxide value (PV) of edible oils is essential because PV is one of the most common quality parameters for monitoring lipid oxidation and oil quality control. The development of cheap, simple, fast, sensitive and selective H₂O₂ sensors is essential.

Electric vehicles are well known for a silent and smooth drive; however, their presence on the road is difficult to identify for road users who may be subjected to certain incidences. Although electric vehicles are free from exhaust emission gases, the wear particles coming out from disc brakes are still unresolved issues. Therefore, the purpose of the present paper is to introduce a smart eco-friendly braking system that uses signal processing and integrated technologies to eventually build a comprehensive driver assistance system.

The parameters obstacle identification, driver drowsiness, driver alcohol situation and heart rate were all taken into account. A contactless brake blending system has been designed while upgrading a rapid response. The implemented state flow rule-based decision strategy validated with the outcomes of a novel experimental setup.

The drowsiness state of drivers was successfully identified for the proposed control map and set up vindicated with the improvement in stopping time, atmospheric environment and increase in vehicle active safety regime.

The present study adopted a unique approach and obtained a brake blending system for improved braking performance as well as overall safety enhancement with rapid control of the vehicle.

The purpose of this study is to design a wearable medical device as a human care platform and to introduce the design details, key technologies and practical implementation methods of the system.

A multi-channel data acquisition scheme based on PCI-E (rapid interconnection of peripheral components) was proposed. The flexible biosensor is integrated with the flexible data acquisition card with monitoring capability, and the embedded (device that can operate independently) chip STM32F103VET6 is used to realize the simultaneous processing of multi-channel human health parameters. The human health parameters were transferred to the upper computer LabVIEW by intelligent clothing through USB or wireless Bluetooth to complete the transmission and processing of clinical data, which facilitates the analysis of medical data.

The smart clothing provides a mobile medical cloud platform for wearable medical through cloud computing, which can continuously monitor the body's wrist movement, body temperature and perspiration for 24 h. The result shows that each channel is completely accurate to the top computer display, which can meet the expected requirements, and the wearable instant care system can be applied to healthcare.

The smart clothing in this study is based on the monitoring and diagnosis of textiles, and the electronic communication devices can cooperate and interact to form a wearable textile system that provides medical monitoring and prevention services to individuals in the fastest and most accurate way. Each channel of the system is precisely matched to the display screen of the host computer and meets the expected requirements. As a real-time human health protection platform technology, continuous monitoring of human vital signs can complete the application of human motion detection, medical health monitoring and human–computer interaction. Ultimately, such an intelligent garment will become an integral part of our everyday clothing.

The current difficulties of distribution network working robots are mainly in the performance and operation mode. On the one hand, high-altitude power operation tasks require high load-carrying capacity and dexterity of the robot; on the other hand, the fully autonomous mode is uncontrollable and the teleoperation mode has a high failure rate. Therefore, this study aims to design a distribution network operation robot named Sky-Worker to solve the above two problems.

The heterogeneous arms of Sky-Worker are driven by hydraulics and electric motors to solve the contradiction between high load-carrying capacity and high flexibility. A human–robot collaborative shared control architecture is built to realize real-time human intervention during autonomous operation, and control weights are dynamically assigned based on energy optimization.

Simulations and tests show that Sky-Worker has good dexterity while having a high load capacity. Based on Sky-Worker, multiuser tests and practical application experiments show that the designed shared-control mode effectively improves the success rate and efficiency of operations compared with other current operation modes.

The designed heterogeneous dual-arm distribution robot aims to better serve distribution line operation tasks.

For the first time, the integration of hydraulic and motor drives into a distribution network operation robot has achieved better overall performance. A human–robot cooperative shared control framework is proposed for remote live-line working robots, which provides better operation results than other current operation modes.

Most of the linear encoders are based on optics. The accuracy and reliability of these encoders are greatly reduced in polluted and noisy environments. Moreover, these encoders have a complex structure and large sensor volume and are thus not suited to small application scenarios and do not have universality. This paper aims to present a new absolute magnetic linear encoder, which has a simple structure, small size and wide application range.

The effect of swing error is analyzed for the sensor structural arrangement. A double-threshold interval algorithm is then proposed to synthesize multiple interval electrical angles into absolute angles and convert them into actual displacement distances.

The final linear encoder measurement range is 15.57 mm, and the resolution reaches ± 2 µm. The effectiveness of the algorithm is demonstrated experimentally.

The linear encoder has good robustness, and high measurement accuracy, which is suitable for industrial production. The linear encoder has been mass-produced and used in an electric power-assisted braking system.

Breast cancer has become the largest cancer in the world today. Health problems for women with breast cancer need to be addressed urgently. This study aims to select the best method for preparing temperature-sensitive sports underwear, and to verify the feasibility of using K-type thermocouple threads in underwear fabrics.

In the experiments, two samples were designed for temperature-sensitive performance tests and the effects produced by different outer layer structures were investigated. In the second step, K-type thermocouple wires were integrated into sports underwear. The comfort and feasibility of the temperature-sensitive underwear were investigated.

It was finally verified to obtain the best comfort and temperature-sensing performance of K-type thermocouple filaments integrated into sports underwear with plain stitching.

The underwear has a certain prospect for the application of smart apparel based on breast cancer health monitoring, which is of some significance for monitoring smart apparel.

This paper aims to investigate an autonomous obstacle-surmounting method based on a hybrid gait for the problem of crossing low-height obstacles autonomously by a six wheel-legged robot. The autonomy of obstacle-surmounting is reflected in obstacle recognition based on multi-frame point cloud fusion.

In this paper, first, for the problem that the lidar on the robot cannot scan the point cloud of low-height obstacles, the lidar is driven to rotate by a 2D turntable to obtain the point cloud of low-height obstacles under the robot. Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping algorithm, fast ground segmentation algorithm and Euclidean clustering algorithm are used to recognize the point cloud of low-height obstacles and obtain low-height obstacle in-formation. Then, combined with the structural characteristics of the robot, the obstacle-surmounting action planning is carried out for two types of obstacle scenes. A segmented approach is used for action planning. Gait units are designed to describe each segment of the action. A gait matrix is used to describe the overall action. The paper also analyzes the stability and surmounting capability of the robot’s key pose and determines the robot’s surmounting capability and the value scheme of the surmounting control variables.

The experimental verification is carried out on the robot laboratory platform (BIT-6NAZA). The obstacle recognition method can accurately detect low-height obstacles. The robot can maintain a smooth posture to cross low-height obstacles, which verifies the feasibility of the adaptive obstacle-surmounting method.

The study can provide the theory and engineering foundation for the environmental perception of the unmanned platform. It provides environmental information to support follow-up work, for example, on the planning of obstacles and obstacles.

To solve the obstacle detection problem in robot autonomous obstacle negotiation, this paper aims to propose an obstacle detection system based on elevation maps for three types of obstacles: positive obstacles, negative obstacles and trench obstacles.

The system framework includes mapping, ground segmentation, obstacle clustering and obstacle recognition. The positive obstacle detection is realized by calculating its minimum rectangle bounding boxes, which includes convex hull calculation, minimum area rectangle calculation and bounding box generation. The detection of negative obstacles and trench obstacles is implemented on the basis of information absence in the map, including obstacles discovery method and type confirmation method.

The obstacle detection system has been thoroughly tested in various environments. In the outdoor experiment, with an average speed of 22.2 ms, the system successfully detected obstacles with a 95% success rate, indicating the effectiveness of the detection algorithm. Moreover, the system’s error range for obstacle detection falls between 4% and 6.6%, meeting the necessary requirements for obstacle negotiation in the next stage.

This paper studies how to solve the obstacle detection problem when the robot obstacle negotiation.

The safety management of construction machines is of primary importance. Considering that traditional construction machine safety monitoring and evaluation methods cannot adapt to the complex construction environment, and the monitoring methods based on sensor equipment cost too much. This paper aims to introduce computer vision and deep learning technologies to propose the YOLOv5-FastPose (YFP) model to realize the pose estimation of construction machines by improving the AlphaPose human pose model.

This model introduced the object detection module YOLOv5m to improve the recognition accuracy for detecting construction machines. Meanwhile, to better capture the pose characteristics, the FastPose network optimized feature extraction was introduced into the Single-Machine Pose Estimation Module (SMPE) of AlphaPose. This study used Alberta Construction Image Dataset (ACID) and Construction Equipment Poses Dataset (CEPD) to establish the dataset of object detection and pose estimation of construction machines through data augmentation technology and Labelme image annotation software for training and testing the YFP model.

The experimental results show that the improved model YFP achieves an average normalization error (NE) of 12.94 × 10^–3, an average Percentage of Correct Keypoints (PCK) of 98.48% and an average Area Under the PCK Curve (AUC) of 37.50 × 10^–3. Compared with existing methods, this model has higher accuracy in the pose estimation of the construction machine.

This study extends and optimizes the human pose estimation model AlphaPose to make it suitable for construction machines, improving the performance of pose estimation for construction machines.