A5066206169- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and LiDAR Applications
- Robotic Path Planning Algorithms
- 3D Surveying and Cultural Heritage
- Autonomous Vehicle Technology and Safety
- Indoor and Outdoor Localization Technologies
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Robot Manipulation and Learning
- Modular Robots and Swarm Intelligence
- Traffic Prediction and Management Techniques
- Data Management and Algorithms
- Iron and Steelmaking Processes
- Advanced Nanomaterials in Catalysis
- Reinforcement Learning in Robotics
- Robotics and Automated Systems
- Soft Robotics and Applications
- Environmental remediation with nanomaterials
- Traffic control and management
- Radar Systems and Signal Processing
- Infrared Target Detection Methodologies
- Advanced oxidation water treatment
- Simulation Techniques and Applications
- Forensic and Genetic Research
Southeast University
2023-2025
University of Science and Technology of China
2018-2024
North China University of Science and Technology
2024
Shandong University
2024
State Key Laboratory of Digital Medical Engineering
2023
Harvard University
2023
Taiyuan Institute of Technology
2023
Tianjin Medical University
2023
Second Hospital of Tianjin Medical University
2023
Yunnan University
2022
Abstract Speciation leads to adaptive changes in organ cellular physiology and creates challenges for studying rare cell-type functions that diverge between humans mice. Rare cystic fibrosis transmembrane conductance regulator (CFTR)-rich pulmonary ionocytes exist throughout the cartilaginous airways of 1,2 , but limited presence divergent biology proximal trachea mice has prevented use traditional transgenic models elucidate ionocyte airway. Here we describe creation conditional genetic...
The blood flow, when restored clinically following a myocardial infarction (MI), disrupts the physiological and metabolic equilibrium of ischemic area, resulting in secondary damage termed ischemia-reperfusion injury (MIRI). Reactive oxygen species (ROS) generation inflammatory reactions stand as primary culprits behind MIRI. Current strategies focusing on ROS-scavenging anti-inflammatory actions have limited remission Prussian blue nanozyme (PBNz) exhibits multiple enzyme-like activities...
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic scenes. These methods typically require expensive LiDAR sensors pre-annotated datasets objects. To address these challenges, we propose OG-Gaussian, a novel approach that replaces point clouds with Occupancy Grids (OGs) generated from surround-view camera...
Simultaneous localization and mapping (SLAM) based on laser sensors has been widely adopted by mobile robots autonomous vehicles. These SLAM systems are required to support accurate with limited computational resources. In particular, point cloud registration, i.e., the process of matching aligning multiple LiDAR scans collected at locations in a global coordinate framework, deemed as bottleneck step SLAM. this paper, we propose feature filtering algorithm, PFilter, that can filter out...
Far-range perception through roadside sensors is crucial to the effectiveness of intelligent transportation systems. The main challenge far-range due difficulty performing accurate object detection and tracking under far distances <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(e.g., > 150m)</i> at a low cost. To cope with such challenges, deploying both millimeter wave Radars high-definition (HD) cameras, fusing their data for joint has...
Place recognition is crucial for tasks like loop-closure detection and re-localization. Single-chip millimeter wave radar (single-chip in short) emerges as a low-cost sensor option place recognition, with the advantage of insensitivity to degraded visual environments. However, it encounters two challenges. Firstly, sparse point cloud from single-chip leads poor performance when using current methods, which assume much denser data. Secondly, its significantly declines scenarios involving...
Double-stranded helical crystals with high axial ratio are prepared from a cholic acid ester. Two processes involved in the formation of micrometer-scale self-assembled crystals: 1) self-assembly ester to form hydrogel (the gel fibers); 2) winding fibers (laser confocal scanning micrographs show, top: left-handed; bottom: right-handed). Supporting information for this article is available on WWW under http://www.wiley-vch.de/contents/jc_2089/2008/c1296_s.pdf or author. Please note: The...
Constructing precise 3D maps is crucial for the development of future map-based systems such as self-driving and navigation. However, generating these in complex environments, multi-level parking garages or shopping malls, remains a formidable challenge. In this paper, we introduce participatory sensing approach that delegates map-building tasks to map users, thereby enabling cost-effective continuous data collection. The proposed method harnesses collective efforts facilitating expansion...
Grasping selection for a individual object has been developed many years, and there feasible proposals have presented. However, robot serving in daily life, this capacity is far from enough. Because the scene our common life usually chaotic, where objects are often mutual influences, front back occlusion, stack up down. In paper, we mainly focus on grasping plan clutter scene. The first step of work to segment input picture which going manipulate. We use Faster R-CNN model based color image...
In this paper, we present the USTC FLICAR Dataset, which is dedicated to development of simultaneous localization and mapping precise 3D reconstruction workspace for heavy-duty autonomous aerial work robots. recent years, numerous public datasets have played significant roles in advancement cars unmanned vehicles (UAVs). However, these two platforms differ from robots: UAVs are limited their payload capacity, while restricted two-dimensional movements. To fill gap, create “Giraffe” robot...
In this paper, we present a automatic robotic grasp system that is capable of grasping objects with wide range sizes and shapes firmly delicately. The two main components object are selection execution. key novel feature our proposal define three primitives which able to handle diverse objects. process, the algorithm needs determine better primitive for each position. This phase does not rely on precise model but just local length width information object. For different primitives, there...
The increased ownership of motor vehicles has brought many urban problems, such as traffic congestion, environmental pollution. Traffic signal control is recognized one effective ways to alleviate these problems. However, it still hard automatically choose appropriate timing plans for different conditions due the dynamics and uncertainty transportation systems. In this paper, we propose a latent factor model based plan recommendation method address problem. proposed method, abstract states...
In this letter, we propose MAROAM, a millimeter wave radar-based SLAM framework, which employs two-step feature selection process to build the global consistent map. Specifically, first extract points from raw data based on their local geometric properties filter out those that violate principle of millimeter-wave radar imaging. Then, further employ another round probabilistic by examining how often and recent point has been detected in proceeding frames. With such selection, establish map...
Place recognition is crucial for tasks like loop-closure detection and re-localization. Single-chip millimeter wave radar (single-chip in short) emerges as a low-cost sensor option place recognition, with the advantage of insensitivity to degraded visual environments. However, it encounters two challenges. Firstly, sparse point cloud from single-chip leads poor performance when using current methods, which assume much denser data. Secondly, its significantly declines scenarios involving...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
The integration of complementary characteristics from camera and radar data has emerged as an effective approach in 3D object detection. However, such fusion-based methods remain unexplored for place recognition, equally important task autonomous systems. Given that recognition relies on the similarity between a query scene corresponding candidate scene, stationary background is expected to play crucial role task. As such, current well-designed camera-radar fusion detection can hardly take...
Localization and mapping are critical tasks for various applications such as autonomous vehicles robotics. The challenges posed by outdoor environments present particular complexities due to their unbounded characteristics. In this work, we MM-Gaussian, a LiDAR-camera multi-modal fusion system localization in scenes. Our approach is inspired the recently developed 3D Gaussians, which demonstrate remarkable capabilities achieving high rendering quality fast speed. Specifically, our fully...
Prior point cloud provides 3D environmental context, which enhances the capabilities of monocular camera in downstream vision tasks, such as object detection, via data fusion. However, absence accurate and automated registration methods for estimating extrinsic parameters roadside scene clouds notably constrains potential applications cameras. This paper proposes a novel approach automatic between prior images from scenes. The main idea involves rendering photorealistic grayscale views taken...
Autonomous systems often employ multiple LiDARs to leverage the integrated advantages, enhancing perception and robustness. The most critical prerequisite under this setting is estimating extrinsic between each LiDAR, i.e., calibration. Despite exciting progress in multi-LiDAR calibration efforts, a universal, sensor-agnostic method remains elusive. According coarse-to-fine framework, we first design spherical descriptor TERRA for 3-DoF rotation initialization with no prior knowledge. To...