A5103202398- Odor and Emission Control Technologies
- Advanced Chemical Sensor Technologies
- Robotic Path Planning Algorithms
- Insect Pheromone Research and Control
- Traffic Prediction and Management Techniques
- Remote Sensing and LiDAR Applications
- Control and Dynamics of Mobile Robots
- Automated Road and Building Extraction
- Robotics and Automated Systems
- Food Supply Chain Traceability
- Autonomous Vehicle Technology and Safety
- Color perception and design
- Evaluation Methods in Various Fields
- Evacuation and Crowd Dynamics
- Geochemistry and Geologic Mapping
- 3D Shape Modeling and Analysis
- Human Mobility and Location-Based Analysis
- Remote-Sensing Image Classification
- Robotics and Sensor-Based Localization
- Hydrocarbon exploration and reservoir analysis
- Transportation Planning and Optimization
- Mineral Processing and Grinding
- 3D Surveying and Cultural Heritage
- Olfactory and Sensory Function Studies
- Robotic Locomotion and Control
Technology and Engineering Center for Space Utilization
2024-2025
Chinese Academy of Sciences
2024-2025
Beijing University of Chemical Technology
2023-2025
Current road extraction models from remote sensing images based on deep learning are computationally demanding and memory-intensive because of their high model complexity, making them impractical for mobile devices. This study aimed to develop a lightweight accurate model, called Road-MobileSeg, address the problem automatically extracting roads The Road-MobileFormer was designed as backbone structure Road-MobileSeg. In Road-MobileFormer, Coordinate Attention Module incorporated encode both...
Travel time estimation (TTE) is a critical function in intelligent driving systems. Current research and applications related to TTE primarily focus on urban environments. The objective of this study develop methods that are applicable wilderness areas characterized by plateau mountainous topography. We selected Transformer, which has greater robustness capturing long-distance dependencies than LSTM, Transformer-based model. model simultaneously integrates positional encoding multi-head...
In field driving activities, off-road areas usually lack existing paths that can be directly driven on by ground vehicles, but their surface environments still satisfy the planning and passage requirements of some vehicles. Additionally, path methods face limitations in complex characterized undulating terrains diverse land cover types. Therefore, this study introduces an improved A* algorithm adapted 3D model real scenes is constructed. A velocity curve fitted evaluation function to reflect...
To address the problem of ignoring unpaved roads when planning off-road emergency rescue paths, an improved A* algorithm that incorporates road factors is developed to create path model in this study. reduce number search nodes and improve efficiency searches, current node classified according angle between line connecting target point due east direction. Additionally, direction determined real time through optimization method efficiency. identify with shortest travel suitable for wilderness...
In the animal production industry, manure odors can be a potential nuisance to neighboring residents. A more suitable metric other than odor concentration and intensity is required evaluate dispersion or on-farm odor-reducing technologies. An parameter was developed better describe by integrating concentration, intensity, hedonic tone values into an index. order mathematically define index, assumption made that index equivalent geometric mean of tone. The mathematical models for...
Multisource data fusion technology integrates the strengths of various sources, addressing limitations relying on a single source. Therefore, it has been widely applied in fields such as lithological classification and mineral exploration. However, traditional deep learning algorithms fail to distinguish importance different features effectively during fusion, leading insufficient focus model. To address this issue, paper introduces ResHA network based hybrid attention mechanism fuse from...
<title>Abstract</title> Current research and applications on travel time estimation primarily concentrate urban scenarios are unable to fulfil the necessary criteria in regions characterized by plateau mountainous topography. In this study, a set of terrain-weather features, comprising attributes terrain weather, was devised reflect factors influencing such settings, catering for predicating times those environments. A Transformer-based model developed, which can improve accuracy paths with...
N-butanol is used as a reference odor to train panelists and field sniffers measure concentrations intensities, respectively. It has different characteristics from that of livestock odors. Odors headspace samples stored swine manure wastewater sludge were analyzed with GC/MS. Seventeen identified compounds selected candidate constituents an artificial (ASO). Twenty-four formulations these developed. Three trials conducted evaluate 24 based on six criteria: the formulation would be safe human...
In order to mitigate the influence of outliers in point clouds on voxel down-sampling results and accuracy cloud registration practical applications, method Point Cloud Library (PCL) has been improved. First, nearest-neighbor distance is applied search for actual that closest calculated centroid a volume. This then used as reserved replace voxel, which helps preserve local detailed features edge contour cloud. Secondly, considering voxels located at edges often contain large number these are...
To address the issues of extensive calculation and low efficiency in path planning for robotic arm a mobile exploration robot operating complex environments, local environment construction strategy is proposed. In this strategy, center base used as viewpoint at current working position, varies depending on robot's designated positions target objects. The was constructed using arm's maximum range motion. During task, its corresponding will change position changes. Path be performed rather...
Odor measurements were compared among four olfactometry laboratoriesacross North America. Odorous air samples collected from livestock facilities weredelivered to the laboratories and odor concentration of each sample wasmeasured by olfactometers at same time. A certified commercial n-butanol,air mixture 40ppm, was used as a reference odor. Relatively large variations wereobserved between laboratories. By applying normalization model data fourlaboratories, standard error decreased 36%,...