Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Hongmin Wu is active.

Publication


Featured researches published by Hongmin Wu.


conference on industrial electronics and applications | 2015

Kinect-based robotic manipulation: From human hand to end-effector

Hongmin Wu; Manjia Su; Shengjun Chen; Yisheng Guan; Hong Zhang; Guangfeng Liu

This paper presents a novel robot motion control method in real-time using the Kinect-based hand tracking. Making use of the middleware NiTE2 modules for Kinect, the 3D position of a hand center point can be captured steadily, which is applied to control the position of the robots end-effector. Meanwhile, an effective method is presented to estimate another two fingertip points in 3D space by processing hand depth images from Kinect. By utilizing these three points (a hand center and two fingertips) a coordinate system can be built up easily, which is used to specify the hand pose. In the same way, the hand pose is used to control the orientation of the end-effector. Whats more, the opening and closing actions of gripper are controlled by changing the distance between these two fingertips. This method enables an operator to control the end-effector easily with only one hand in actual real time. The effectiveness and efficiency of the presented method have been verified in the water-pouring tasks with a 5-DOFs modular manipulator.


robotics and biomimetics | 2015

A robotic off-line programming system based on SolidWorks

Hongmin Wu; Huajian Deng; Cao Yang; Yisheng Guan; Hong Zhang; Hao Li

It is well known that off-line programming (OLP) is an efficient control mode for industrial robots. However, OLP is not yet commonly and widely used in applications, since commercial OLP systems are very expensive, with prices even much higher than those of robotic systems themselves. Simple but effective OLP systems are desired, and such systems may be made based on other commonly used CAD systems. We have developed a robotic OLP system, which we called RobSim, based on SolidWorks and with Microsoft Visual Studio 2010. RobSim is developed as an add-on tool for the commonly used CAD software SolidWorks. With this OLP system, an object can be made, imported or modified in the conventional mode in SolidWorks environment, and various trajectories for a robot can be easily and conveniently defined and modified in the same environment. Trajectory interposition, kinematic computation, dynamic and graphic simulation can be conducted. Finally executable codes can be generated for the robot to perform tasks. In this paper, the development of RobSim is demonstrated. Specifically, the architecture of RobSim, the method for extracting position and orientation from a pre-defined path on an object for the robot tool, and path transformation, are presented. Simulation and experiments are also conducted to verify the effectiveness of the OLP system.


robotics and biomimetics | 2014

Coordinated motion planning with calibration and offline programming for a manipulator-positioner system

Hongmin Wu; Zhiqiang Bi; Manjia Su; Ping Zhang; Yingwu He; Yisheng Guan

A single industrial robot is sometimes not sufficient to achieve some complex tasks such as polishing or welding on complex surfaces. In this case, a positioner is usually employed as an auxiliary device, and their motion is required to be coordinated. This paper proposes a method for coordinated motion planning of a manipulator-positioner system which consists of one 6-DoF manipulator and one 2-DOF positioner. A coordinated kinematics model of the manipulator-positioner system is first established. Three-points calibration for the relative position of the positioner with respect to the manipulator is then presented. Complex paths are planned with AutoCAD and transformed into robotic language by an offline programming system. Finally, experiments in which writing letters on the moving plate of the positioner are conducted to verify the feasibility and effectiveness of the presented coordinated motion planning method and the offline programming system.


robotics and biomimetics | 2016

Sequence-modification based collision-free motion planning of multiple robots workcell

Hongmin Wu; Huajian Deng; Longxin Chen; Yisheng Guan; Hong Zhang

This work is inspired by the problem of planning multiple robots in a shared workspace. The goal is to find out a sequence order for coordinating the paths of robots so as to avoid collisions among them and deadlocks, that is, situations where each robot is waiting for the other to proceed. We assume that the workcell is known and the paths of robots can be planned in advance and all the robots move synchronously. These assumptions are good models of many tasks. The coordination is achieved by introducing improved A* heuristic algorithm for continuous state sequence planning in high dimensional space. The proposed method consist of two steps: 1) path planning for the robots, which taking into account avoidance of collision between the robots and the environment; 2) calculating all the possible colliding state and translating the coordinating problem into scheduling the path segments. Experimental cases are shown for the proposed algorithm and for their implementations. The results of the planning method can be applied to the industrial applications.


robotics and biomimetics | 2015

Base frame calibration for multi-robot coordinated systems

Huajian Deng; Hongmin Wu; Cao Yang; Yisheng Guan; Hong Zhang; Jianling Liu

It is well-known that industrial robots are not very accurate. Robot calibration, which is one of the key techniques in robot off-line programming (OLP) as well as in robotics, is very helpful to increase the accuracy of robot motion. To solve the problem of base frame calibration for coordinated multi-robot systems, this paper proposes a simple and practical method, which is improved by three points calibration. It determines the base frame relationship for multi-robot systems. With laser sensors and a buzzer, the degree of accuracy has been enhanced. In order to integrate the process and the algorithm of the calibration method, a software has been developed. Experiment results have verified the validity and effectiveness of the proposed method.


robotics and biomimetics | 2014

Offline motion planning on spherical surfaces for a manipulator

Zhiqiang Bi; Hongmin Wu; Yingwu He; Ping Zhang; Yisheng Guan; Guanfeng Liu

For many tasks such as welding and polishing on complex surfaces with manipulators, teaching-and-playback is difficult and inefficient. Motion planning with offline programming is an effective and efficient alternative control mode for these tasks. In this paper, we present a method to plan motion by offline programming for tasks on spherical workpieces and develop a corresponding planning module of the offline programming system, with practical factors including the reachable workspace and orientation constraint token into account. A calibration approach for workpiece coordinate system is first proposed, and an algorithm for orientation search is then presented. Minimal motion and energy consumption are considered as objectives in motion planning of a manipulator. A reachable workspace search method is presented, and several indexes are used to determine the optimal manipulability workspace to increase work efficiency and stability. Experiments are conducted to verify the feasibility and effectiveness of the proposed methods.


ieee ras international conference on humanoid robots | 2017

Robot introspection with Bayesian nonparametric vector autoregressive hidden Markov models

Hongmin Wu; Hongbin Lin; Yisheng Guan; Kensuke Harada; Juan Rojas


ieee ras international conference on humanoid robots | 2017

Learning human-robot collaboration insights through the integration of muscle activity in interaction motion models

Longxin Chen; Hongmin Wu; Shuangda Duan; Yisheng Guan; Juan Rojas


arXiv: Robotics | 2017

Recovering from External Disturbances in Online Manipulation through State-Dependent Revertive Recovery Policies.

Hongmin Wu; Hongbin Lin; Shuangqi Luo; Shuangda Duan; Yisheng Guan; Juan Rojas


arXiv: Robotics | 2017

Fast, Robust, and Versatile Event Detection through HMM Belief State Gradient Measures.

Shuangqi Luo; Hongmin Wu; Hongbin Lin; Shuangda Duan; Yisheng Guan; Juan Rojas

Collaboration


Dive into the Hongmin Wu's collaboration.

Top Co-Authors

Avatar

Yisheng Guan

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Shuangda Duan

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Hongbin Lin

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Juan Rojas

Sun Yat-sen University

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Huajian Deng

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Longxin Chen

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Cao Yang

Guangdong University of Technology

View shared research outputs
Top Co-Authors

Avatar

Manjia Su

Guangdong University of Technology

View shared research outputs
Researchain Logo
Decentralizing Knowledge