A5100435445- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Advanced Steganography and Watermarking Techniques
- Digital Media Forensic Detection
- Advanced Memory and Neural Computing
- Image Processing Techniques and Applications
- Distributed Control Multi-Agent Systems
- Radiation Effects in Electronics
- Molecular Communication and Nanonetworks
- Medical Image Segmentation Techniques
- UAV Applications and Optimization
- Chaos-based Image/Signal Encryption
- Indoor and Outdoor Localization Technologies
- Modular Robots and Swarm Intelligence
- Cell Image Analysis Techniques
- Optimization and Search Problems
- Target Tracking and Data Fusion in Sensor Networks
- Adaptive Control of Nonlinear Systems
- Control and Dynamics of Mobile Robots
- CCD and CMOS Imaging Sensors
- Biometric Identification and Security
- Image and Object Detection Techniques
- Software Testing and Debugging Techniques
- Robot Manipulation and Learning
- Eating Disorders and Behaviors
Huzhou University
2023-2024
Zhejiang University
2023-2024
Zhejiang University of Technology
2023-2024
Second Hospital of Shandong University
2023
State Key Laboratory of Industrial Control Technology
2023
Northwest University
2023
Nankai University
2011-2014
Weifang University
2004
Mutual localization plays a crucial role in multi-robot cooperation. CREPES, novel system that focuses on six degrees of freedom (DOF) relative pose estimation for systems, is proposed this paper. CREPES has compact hardware design using active infrared (IR) LEDs, an IR fish-eye camera, ultra-wideband (UWB) module and inertial measurement unit (IMU). By leveraging light communication, the solves data association between visual detection UWB ranging. Ranging measurements from directional...
Neuromorphic vision sensors or event cameras have made the visual perception of extremely low reaction time possible, opening new avenues for high-dynamic robotics applications. These cameras’ output is dependent on both motion and texture. However, camera fails to capture object edges that are parallel motion. This a problem intrinsic sensor therefore challenging solve algorithmically. Human deals with perceptual fading using active mechanism small involuntary eye movements, most prominent...
Abstract Background High sedentary behavior and poor health-related quality of life (HRQoL) were common among women with polycystic ovary syndrome (PCOS). However, the association HRQoL infertile PCOS is still unknown. This study aimed to investigate them. Methods A cross-sectional was conducted 283 participants recruited from infertility outpatient clinic. self-administered, structured questionnaire including modified QoL (MPCOSQ), International Physical Activity Questionnaire short form...
Reversible watermarking algorithms make it possible that the original image can be totally restored after watermark was extracted, so is widely used in protection of medicalimages. A new reversible scheme based on Integer Discrete Cosine Transform (IntDCT) and Difference Expansion (DE) proposed this paper. The IntDCT transformation not only avoids distortion truncation error, but also leads to a faster processing speed an easily handled implementation hardware. In our scheme, firstly divided...
Abstract To prevent image forgeries, a number of forensic techniques for digital have been developed that can detect an image's origin, trace its processing history, and also locate the position tampering. Especially, statistical footprint left by JPEG compression operation be valuable source information analyst, some algorithm raised based on statistics in DCT domain. Recently, it has shown footprints removed adding suitable anti‐forensic dithering signal to domain, this results invalid...
Active learning is usually used in scenarios where few labels are available and manual labeling expensive. To improve model performance, it necessary to find the most valuable instance among all instances label maximize benefits of labeling. In practical scenarios, often more efficient query a group instead individual during each iteration. achieve this goal, we need explore similarities between ensure informativeness diversity. Many ad-hoc algorithms proposed for batch mode active learning,...
A publicly verifiable scheme for the copyright protection of digital image is proposed in this paper. Combining with some cryptographic techniques such as signature and timestamp, features an idea registering watermark information to a trusted authority (TA) rather than embedding it into host image, which overcomes many deficiencies conventional watermarking algorithm. In scheme, generalized brain-state-in-a-box neural network (gBSB) error diffusion halftoning are employed extract robust...
Mutual localization plays a crucial role in multi-robot cooperation. CREPES, novel system that focuses on six degrees of freedom (DOF) relative pose estimation for systems, is proposed this paper. CREPES has compact hardware design using active infrared (IR) LEDs, an IR fish-eye camera, ultra-wideband (UWB) module and inertial measurement unit (IMU). By leveraging light communication, the solves data association between visual detection UWB ranging. Ranging measurements from directional...
Neuromorphic vision sensors or event cameras have made the visual perception of extremely low reaction time possible, opening new avenues for high-dynamic robotics applications. These cameras' output is dependent on both motion and texture. However, camera fails to capture object edges that are parallel motion. This a problem intrinsic sensor therefore challenging solve algorithmically. Human deals with perceptual fading using active mechanism small involuntary eye movements, most prominent...
Formation flight has a vast potential for aerial robot swarms in various applications. However, existing methods lack the capability to achieve fully autonomous large-scale formation dense environments. To bridge gap, we present complete system that effectively integrates real-world constraints into navigation. This paper proposes differentiable graph-based metric quantify overall similarity error between formations. is invariant rotation, translation, and scaling, providing more freedom...
With the development of robotics, ground robots are no longer limited to planar motion. Passive height variation due complex terrain and active control provided by special structures on require a more general navigation planning framework beyond 2D. Existing methods rarely considers both simultaneously, limiting capabilities applications robots. In this paper, we proposed an optimization-based for considering passive changes z-axis. The planner first constructs penalty field chassis motion...
This paper presents a novel solution for UAV control in cooperative multi-robot systems, which can be used various scenarios such as leader-following, landing on moving base, or specific relative motion with target. Unlike classical methods that tackle the world frame, we directly target coordinate without making assumptions about In detail, formulate non-linear model predictive controller of UAV, referred to agent, within non-inertial frame (i.e., frame). The system requires states (pose...
Autonomous navigation of ground robots on uneven terrain is being considered in more and tasks. However, will bring two problems to motion planning: how assess the traversability cope with dynamics model robot associated terrain. The trajectories generated by existing methods are often too conservative or cannot be tracked well controller since second problem not solved. In this paper, we propose pose mapping describe impact robot. With mapping, can obtain SE(3) state for a given SE(2)....
Perception is necessary for autonomous navigation in an unknown area crowded with obstacles. It's challenging a robot to navigate safely without any sensors that can sense the environment, resulting $\textit{blind}$ robot, and becomes more difficult when comes group of robots. However, it could be costly equip all robots expensive perception or SLAM systems. In this paper, we propose novel system named $\textbf{ColAG}$, solve problem UGVs by introducing cooperation one UAV, which only has...
Multi-robot teams have attracted attention from industry and academia for their ability to perform collaborative tasks in unstructured environments, such as wilderness rescue transportation.In this paper, we propose a trajectory planning method non-holonomic robotic team with collaboration environments.For the adaptive state of robot catch transport targets be rescued using net, model process catching falling target net continuous differentiable form.This enables fully exploit kinematic...