A5043461784- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
- Autonomous Vehicle Technology and Safety
- Human Pose and Action Recognition
- Control and Dynamics of Mobile Robots
- Topological Materials and Phenomena
- Indoor and Outdoor Localization Technologies
- Modular Robots and Swarm Intelligence
- Medical Imaging and Analysis
- High-Temperature Coating Behaviors
- Bacterial biofilms and quorum sensing
- Advanced Vision and Imaging
- Robotic Locomotion and Control
- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Underwater Vehicles and Communication Systems
- Advanced Image and Video Retrieval Techniques
- Graphene research and applications
- AI-based Problem Solving and Planning
- Radiomics and Machine Learning in Medical Imaging
- Sulfur Compounds in Biology
- Micro and Nano Robotics
- Industrial Technology and Control Systems
Southern University of Science and Technology
2020-2025
Tianjin University
2017-2025
University of Science and Technology Beijing
2022-2025
China Pharmaceutical University
2016-2025
Northwest Institute of Mechanical and Electrical Engineering
2024
Northwest A&F University
2024
Jiaxing University
2022-2024
Center for Life Sciences
2022-2024
Hubei University of Medicine
2020-2024
Taihe Hospital
2020-2024
Rapidly random-exploring tree (RRT) and its variants are very popular due to their ability quickly efficiently explore the state space. However, they suffer sensitivity initial solution slow convergence optimal solution, which means that consume a lot of memory time find path. It is critical short path in many applications such as autonomous vehicle with limited power/fuel. To overcome these limitations, we propose novel planning algorithm based on convolutional neural network (CNN), namely...
The rapidly exploring random tree and its variants (RRTs) have been widely adopted as the motion planning algorithms for mobile robots. However, trap space problem, such mazes S-shaped corridors, hinders their efficiency. In this article, we present a generalized Voronoi diagram (GVD)-based heuristic path algorithm to generate path, guide sampling process of RRTs, further improve efficiency RRTs. Different from other that only work in certain environments or depend on specified parameter...
Eutectic electrolytes have been widely used in low-temperature metal-ion batteries (MIBs) due to their good performance regardless of seasonal and regional changes. Durable MIBs rely on the constitution, proportion, solvation-structure construction eutectic maintain high ionic conductivity electrochemical stability. Despite rapid advances electrolytes, some key issues, including fundamental mechanisms, theoretical models, aqueous/non-aqueous controversies, challenges at sub-zero...
In a human-robot coexisting environment, it is pivotal for mobile service robot to arrive at the goal position safely and efficiently. this article, an elastic band-based rapidly exploring random tree (EB-RRT) algorithm proposed achieve real-time optimal motion planning in dynamic which can maintain homotopy trajectory based on current heuristic trajectory. Inspired by EB method, we propose hierarchical framework consisting of two planners. global planner, time-based RRT used generate...
In this article, we present a novel nonuniform sampling technique, based on the pipeline of rapidly exploring random tree (RRT), for efficiently computing high-quality collision-free paths while maintaining fast asymptotic convergence to optimal solution. Our method focuses area where path may exist so that planning process can be further accelerated. First, environment map is initialized with generalized Voronoi graph and heuristic calculated. Second, discretized construct multiple...
Biomimetics is the development of novel theories and technologies by emulating models systems nature. The transfer function from biological science into engineering promotes emerging research areas across many disparate disciplines. Recently, advances in biomimetic intelligence robotics have gained great popularity. Biomimetic are designed with characteristics functions to be applied different scenarios, such as humanoid robot home environment, quadruped field, bird-like flying sky. aims...
Mobile robot autonomous path planning is an essential factor for its wide deployment in real-world applications. Conventional sampling-based algorithms have gained tremendous success the field, but they usually take much time to find optimal solution so that quality (evaluated with cost and length) cannot be guaranteed. In this paper, based on Gaussian Mixture Regression (GMR) family of Rapidly-exploring Random Tree (RRT) schemes, we propose GMR-RRT* algorithm achieve fast mobile robots. The...
The emerging large language models (LLMs) are actively evaluated in various fields including healthcare. Most studies have focused on established benchmarks and standard parameters; however, the variation impact of prompt engineering fine-tuning strategies not been fully explored. This study GPT-3.5 Turbo, GPT-4, Llama-7B against BERT medical fellows' annotations identifying patients with metastatic cancer from discharge summaries. Results revealed that clear, concise prompts incorporating...
In a human-robot coexisting environment, reaching the target place efficiently and safely is pivotal for mobile service robot. this paper, Risk-based Dual-Tree Rapidly exploring Random Tree (Risk-DTRRT) algorithm proposed robot motion planning in dynamic which provides homotopy optimal trajectory on basis of heuristic trajectory. A dual-tree framework consisting an RRT tree rewired searching. The time-based tree, considering future predictions pedestrians, utilized to generate However,...
Abstract A fundamental task in robotics is to plan collision‐free motions among a set of obstacles. Recently, learning‐based motion‐planning methods have shown significant advantages solving different planning problems high‐dimensional spaces and complex environments. This article serves as survey various that been applied robot problems, including supervised, unsupervised learning, reinforcement learning. These either rely on human‐crafted reward function for specific tasks or learn from...
Autonomous ground vehicles (AGVs) have been deployed in various working environments. Human-AGV coexisting environments introduce many challenges into the motion planning procedure. The planner should be smart enough to guide AGV move safely and smoothly. Besides, efficiency of is essential for real-time response. Risk-based algorithms consider risk collision with dynamic static obstacles deal problems human-AGV However, their performance needs further improved. bidirectional search sampling...
About 70% of water withdrawals in the Yellow River Basin (YRB) are used for irrigation, and deeply explanation effects climate change on runoff YRB provides a guarantee agricultural production. Analysis prediction were implemented according to meteorological hydrological data from 1967 2016, responses catchments six stations different combinations precipitation temperature conditions explored adopting Budyko framework, then results based scenario simulation elasticity compared. Our revealed...
Thanks to the highly-dense lighting infrastructure in public areas, visible light emerges as a promising means indoor localization and navigation. State-of-the-art techniques generally require customized hardware (sensing boards), mainly work with one single source (e.g., LEDs). This greatly limits their application scope. In this paper, we propose NaviLight, generic navigation framework based on existing any unmodified sources LED, fluorescent, incandescent lights). NaviLight simply adopts...
Sampling-based path planning is a popular methodology for robot planning. With uniform sampling strategy to explore the state space, feasible can be found without complex geometric modeling of configuration space. However, quality initial solution not guaranteed, and convergence speed optimal slow. In this paper, we present novel image-based algorithm overcome these limitations. Specifically, generative adversarial network (GAN) designed take environment map (denoted as RGB image) input...
Path planning plays an important role in autonomous robot systems. Effective understanding of the surrounding environment and efficient generation optimal collision-free path are both critical parts for solving path-planning problems. Although conventional sampling-based algorithms, such as rapidly exploring random tree (RRT) its improved version (RRT*), have been widely used problems because their ability to find a feasible even complex environments, they fail efficiently. To solve this...
The exchange bias effect, namely the horizontal shift in magnetic hysteretic loop, is known as a fundamentally and technologically important property of systems. Though effect has been widely observed normal heterostructure, it desirable to raise such pinning coupling topology-based multilayer structure. Furthermore, was theoretically proposed be able further open surface magnetization gap recently discovered intrinsic topological insulator $\mathrm{Mn}{\mathrm{Bi}}_{2}{\mathrm{Te}}_{4}$....
Sampling-based path planning is widely used in robotics, particularly high-dimensional state spaces. In the process, collision detection most time-consuming operation. Therefore, we propose a learning-based method that reduces number of checks. We develop an efficient neural network model based on graph networks. The outputs weights for each neighbor obstacle, searched path, and random geometric graph, which are to guide planner avoiding obstacles. evaluate efficiency proposed through...
Robots have become increasingly prevalent in dynamic and crowded environments such as airports shopping malls. In these scenarios, the critical challenges for robot navigation are reliability timely arrival at predetermined destinations. While existing risk-based motion planning algorithms effectively reduce collision risks with static obstacles, there is still a need significant performance improvements. Specifically, demand more rapid responses robust planning. To address this gap, we...
Abstract The task of collecting and transporting luggage trolleys in airports, characterized by its complexity within dynamic public environments, presents both an ongoing challenge a promising opportunity for automated service robots. Previous research has primarily developed on universal platforms with robot arms or focused handling single trolley, creating gap providing cost‐effective efficient solutions practical scenarios. In this paper, we propose low‐cost mobile manipulation...
One of the pivotal challenges in a multi-robot system is how to give attention accuracy and efficiency while ensuring safety. Prior arts cannot strictly guarantee collision-free for an arbitrarily large number robots or results are considerably conservative. Smoothness avoidance trajectory also needs be further optimized. This paper proposes accelerationactuated simultaneous obstacle tracking method teams robots, that provides nonconservative collision strategy gives approaches deadlock...