Mitchell Dinham

A robust algorithm for weld seam extraction based on prior knowledge of weld seam

– This paper aims to develop a method to extract the weld seam from the welding image., – The initial step is to set the window for the region of the weld seam. Filter and edge‐operator are then applied to acquire edges of images. Based on the prior knowledge about characteristics of the weld seam, a series of routines is proposed to recognize the seam edges and calculate the seam representation., – The proposed method can be used to extract seams of different deviations from noise‐polluted images efficiently. Besides, the method is low time‐consuming and quick enough for real time processing., – Weld seam extraction is the key problem in passive vision based seam tracking technology. The proposed method can extract the weld seam even when the image is noisy, and it is quick enough to be applied in seam tracking technology. The method is expected to improve seam tracking results., – A useful method is developed for weld seam extraction from the noise‐polluted image based on prior knowledge of weld seam. The method is robust and quick enough for real time processing.

Automatic Seam Detection and Path Planning in Robotic Welding

To make robotic welding systems more flexible, vision sensors are introduced as they provide large amount of information about the welding components. In this paper a method is introduced to automatically locate the weld seam between two objects in butt welding applications. The proposed method provides flexibility for robotic welding by having the ability to locate the weld seam on arbitrarily positioned work pieces. This method is also cost effective as it is developed using images captured from a low cost web-cam. Furthermore, the proposed method is able to plan a robot path along the identified seam. Simulation and experimental results show that the method can be used successfully in detecting and locating seams on variously shaped work pieces and robot paths can be successfully generated to follow the weld seams.

A low cost hand-eye calibration method for arc welding robots

Hand-eye calibration is one of the most important and fundamental tasks in performing visual guided robot control tasks. Many techniques have been proposed that use various expensive equipment ranging from a three dimensional positioning device to a laser measurement device. The work presented in this paper aims at developing a low cost robot hand/eye calibration method that is accurate and robust enough to be used in a robotic arc welding system. The proposed calibration method allows the camera and object frames to be referenced directly to the robots base co-ordinate frame. Experimental results show that the developed method can be used to achieve a calibration accuracy of 1 mm (in the directions of interest, X and Y axes) that is acceptable for robotic welding applications.

Time Optimal Path Planning for Mobile Robots in Dynamic Environments

This paper aims to develop a control method by using artificial potential field with the addition of an algorithm that implements an online time-optimal collision avoidance strategy for a robot to move through a partially known dynamic environment. In many applications, robots are required to move along a predefined path if there are no moving obstacles. When moving obstacles are encountered a collision avoidance strategy must be employed. In this paper, a control strategy is developed to address these two requirements. This is done by using the potential field to follow the predefined paths and to avoid the obstacle. The time-optimal issue is then taken into consideration, when moving obstacles are encountered, to decide if the robot is to move around obstacles or wait until obstacles moving out of the robot path. Simulation results shown that a significant time saving (around 10%) can be achieved using the proposed method.

Low cost simultaneous calibration of a stereo vision system and a welding robot

Stereo vision and hand-eye calibration is one of the most important and fundamental tasks in visually guided robotic control tasks. The work presented in this paper aims to develop an accurate camera based stereo vision and hand-eye calibration algorithm that is robust enough to be used in a robotic arc welding system. The proposed calibration method allows the object reference frame to be directly related to the robots base co-ordinate frame without the use of expensive coordinate measuring devices. Experimental results have shown that the proposed method can achieve a positional error of less than 1 mm in the Cartesian space, which is acceptable in most arc welding applications.

Simultaneous Calibration of a Stereo Vision System and a Welding Robot-an Automated Approach

For a vision guided industrial robot to be used in a production environment effectively and efficiently, it is important that such a system can be quickly and accurately calibrated. The work presented in this paper aims to develop a new method for calibrating a vision guided arc welding robot. This is achieved through automated calibration of the cameras and the optimised simultaneous calibration of a robot arm and robot mounted stereo vision system. The developed method can be implemented in practice and with minimum human intervention. The automatic calibration algorithm not only allows for a faster initial calibration, but also reduces the machine down-time for any subsequent calibrations after an accidental collision or if the camera fixture is relocated. Experimental results show that the proposed method can achieve the required accuracy for robotic arc welding applications.

The Development of a Low Cost Autonomous Robotic Arc Welding System

A significant challenge for robotic welding to be widely adopted is the time taken to program robot paths for new parts. While computer vision can be used to detect and locate weld joints, due to the large number of possible joint configurations, work piece materials and environmental impacts such as lighting conditions, autonomous weld joint detection and localisation remains a significant challenge. This paper introduces an autonomous robotic arc welding system that is capable of detecting realistic weld joints and calculating their position in the robot workspace with minimal human interaction. The proposed method is capable of detecting and localising butt and fillet weld joints regardless of base material, surface finish or imperfections. The welding results show that the proposed method is capable of producing high quality weld paths suitable for industrial applications.