Xuefeng Zhou

ORCID: 0000-0003-1642-2059
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Robot Manipulation and Learning
  • Robotic Mechanisms and Dynamics
  • Robotic Locomotion and Control
  • Soft Robotics and Applications
  • Robotic Path Planning Algorithms
  • Modular Robots and Swarm Intelligence
  • Adaptive Control of Nonlinear Systems
  • Manufacturing Process and Optimization
  • Robotics and Sensor-Based Localization
  • Iterative Learning Control Systems
  • Advanced Surface Polishing Techniques
  • Advanced machining processes and optimization
  • Prosthetics and Rehabilitation Robotics
  • Fault Detection and Control Systems
  • Anomaly Detection Techniques and Applications
  • Teleoperation and Haptic Systems
  • Control and Dynamics of Mobile Robots
  • Adaptive Dynamic Programming Control
  • Advanced Control Systems Optimization
  • Advanced Numerical Analysis Techniques
  • Industrial Vision Systems and Defect Detection
  • Reinforcement Learning in Robotics
  • Muscle activation and electromyography studies
  • Advanced Image and Video Retrieval Techniques
  • Advanced Memory and Neural Computing

Guangdong Institute of Intelligent Manufacturing
2016-2025

Guangdong Academy of Sciences
2014-2025

Tongji University
2024

Wuhu Hit Robot Technology Research Institute
2019-2021

Key Laboratory of Guangdong Province
2021

Shanxi Datong University
2020

South China University of Technology
2009-2017

Xi'an Technological University
2011

High-rise tasks such as cleaning, painting, inspection, and maintenance on walls of large buildings or other structures require robots with climbing manipulating skills. Motivated by these potential applications inspired the motion inchworms, we have developed a biped wall-climbing robot-W-Climbot. Built modular approach, robot consists five joint modules connected in series two suction mounted at ends. With this configuration mode, W-Climbot not only has superior mobility smooth walls, but...

10.1109/tmech.2012.2213303 article EN IEEE/ASME Transactions on Mechatronics 2012-09-05

Accurate position-force control is a core and challenging problem in robotics, especially for manipulators with redundant degrees of freedom (DOFs). For example, trajectory tracking-based usually fails grinding robots due to intolerable impact forces imposed onto the end effectors. The main difficulties lie coupling motion contact force, redundancy resolution, physical constraints, etc. In this article, we propose novel motion-force strategy framework projection recurrent neural networks...

10.1109/tie.2020.2970635 article EN IEEE Transactions on Industrial Electronics 2020-02-05

Industrial robot provides a promising alternative in freeform surface milling. However, due to its low stiffness, it is difficult guarantee the machining quality. While existing research considers mainly influence of posture on workpiece setup's equally important. In this article, ensure overall workpiece's stiffness meets requirement threshold robotic milling, method for simultaneously optimizing and setup proposed. First, evaluate during machining, article presents new index...

10.1109/tmech.2021.3068599 article EN IEEE/ASME Transactions on Mechatronics 2021-03-24

In this brief, we presented a framework for the trajectory optimization of 5-link Biped Robot using Beetle Antennae Search (BAS) algorithm. The biped robot is highly non-linear and has complex dynamical modeling. It challenging to obtain closed-form solution Robot. modeling two stages, i.e., optimal generation robust control robot. conventional methodologies treat both problems separately are computationally expensive. This brief an problem that combines We employed problem’s...

10.1109/tcsii.2021.3062639 article EN IEEE Transactions on Circuits & Systems II Express Briefs 2021-03-01

Abstract Biped wall-climbing robots (BWCRs) serve as viable alternatives to human workers for inspection and maintenance tasks within three-dimensional (3D) curtain wall environments. However, autonomous climbing in such environments presents significant challenges, particularly related localization navigation. This paper a pioneering navigation framework tailored BWCRs navigate through 3D The comprises three essential stages: Building Information Model (BIM)-based map extraction, path...

10.1017/s0263574724002170 article EN Robotica 2025-01-03

For the safe operation of redundant manipulators, physical constraints such as joint angle, velocity, and acceleration limits should be taken into account when designing redundancy resolution schemes. Velocity-level schemes are widely adopted in kinematic control manipulators due to existence well-tuned inner loop regarding velocity control. However, it is difficult deal with for velocity-level methods. In this paper, a recurrent-neural-network-based method proposed problem, theoretical...

10.1109/tie.2018.2851960 article EN IEEE Transactions on Industrial Electronics 2018-07-09

Agriculture, forestry, and building industry would be prospective fields of robotic applications. High-rise tasks in these require robots with climbing skills. Motivated by potential applications inspired animal motion, we have developed a biped robot—Climbot. Built modular approach, the robot consists five joint modules connected series two special grippers mounted at ends, scalability changing degrees-of-freedom (DoFs). With this configuration, Climbot not only has superior mobility on...

10.1115/1.4028683 article EN Journal of Mechanisms and Robotics 2016-01-27

Motion planning is a core issuein the field of robotic control, which directly affects programming efficiency robots. In this article, we study motion problem manipulators for simultaneous obstacle avoidance and target tracking, propose novel real-time method in complex workspace. One important feature proposed that robot can avoid colliding with obstacles by easily defining “virtual fences,” are described group level set functions. Thus, feasible space be abstracted as inequality...

10.1109/tie.2021.3073305 article EN IEEE Transactions on Industrial Electronics 2021-04-21

Vacuum adsorption is a simple but effective attaching method widely used in many fields including robotic wall climbing. It required that the sucker aligned well with target surface to form airtight chamber for vacuum generation. For applications biped wall-climbing robots, automatically aligning beneficial and important enhance efficiency effectiveness of adsorption. Especially, such function essential autonomous intelligent To this end, we propose novel low-cost approach perform alignment...

10.1109/tmech.2014.2317190 article EN IEEE/ASME Transactions on Mechatronics 2014-06-04

Biped truss climbing robots (BTCRs) are employed to perform high-rise tasks within environments, benefiting from their superior transition capabilities and flexible mobility. However, the intricate geometry of these structures poses challenges for robot navigation operation. To tackle this issue, paper proposes a novel BTCRs path planning framework based on progressive multi-layer architecture. The robot’s regions between adjacent members determined efficiently by unfolding three-dimensional...

10.1177/01423312241309411 article EN Transactions of the Institute of Measurement and Control 2025-03-22

Collision avoidance plays a major part in the control of wheeled mobile robot (WMR). Most existing collision-avoidance methods mainly focus on single WMR and environmental obstacles. There are few products that cast light between multiple WMRs (MWMRs). In this article, problem simultaneous target tracking is investigated for MWMRs working shared environment from perspective optimization. The strategy formulated as an inequality constraint, which has proven to be collision free MWMRs....

10.1109/tcyb.2021.3070385 article EN IEEE Transactions on Cybernetics 2021-05-07

Global localization is a well-known problem of estimating the pose robot in learned map without any prior knowledge its initial pose. It difficult to achieve global with lidar when only limited number scans are available, especially environments simple and repetitive local geometric features. Camera has advantage rich information but suffers from lack reliable efficient algorithms relative high computation burden. In this paper, we propose fast approach capability addressing kidnapped...

10.1109/robio.2017.8324775 article EN 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO) 2017-12-01

In this study, we investigate the problem of cooperative kinematic control for multiple redundant manipulators under partially known information using recurrent neural network (RNN). The communication among is modeled as a graph topology with exchange that only occurs at neighbouring robot nodes. Under information, four objectives are simultaneously achieved, i.e, global cooperation and synchronization manipulators, joint physical limits compliance, neighbor-to-neighbor robots, optimality...

10.1109/access.2020.2974248 article EN cc-by IEEE Access 2020-01-01

High-rise tasks in agriculture, forestry and building industry requires robots possessing climbing function. Motivated by these potential applications inspired the motion of animals such as inchworms, we have developed a novel biped robot - Climbot. Built with modular approach, consists five 1-DoF joint modules connected series two special grippers mounted at ends. With this configuration, Climbot is able not only to climb variety media, but also grasp manipulate objects, hence ¿mobile¿...

10.1109/iros.2011.6094406 article EN 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems 2011-09-01

Obstacle avoidance is an important subject in the control of robot manipulators, but remains challenging for robots with redundant degrees freedom, especially when there exist complex physical constraints. In this paper, we propose a novel controller based on deep recurrent neural networks. By abstracting and obstacles into critical point sets respectively, distance between can be described simpler way, then obstacle strategy established form inequality constraints by general class-K...

10.3389/fnbot.2019.00047 article EN cc-by Frontiers in Neurorobotics 2019-07-04

Robotic bin-picking is a common process in modern manufacturing, logistics, and warehousing that aims to pick-up known or unknown objects with random poses out of bin by using robot-camera system. Rapid accurate object pose estimation pipelines have become an escalating issue for robot picking recent years. In this paper, fast 6-DoF (degrees freedom) pipeline proposed which the capable recognizing different types various cluttered scenarios uses adaptive threshold segment strategy accelerate...

10.1109/access.2020.2983173 article EN cc-by IEEE Access 2020-01-01

This paper studies control the robotic arm based on our hand movement and gestures. Data from a Leap Motion controller which detects gestures movement, than data are delivered through USB to SCARA arm. Motion, tracks of hands is available minute movements dynamic motions. uses an existing robot, can be controlled by using device called as Motion. We would like investigate more this implement, such that robot interfaced with for successful control.

10.1109/icrae.2017.8291351 article EN 2017-12-01
Coming Soon ...