Development of visual-servo pick-and-place robot technology for manufacturing automation

点击翻译按钮获取中文摘要

Pick-and-place Robots have been widely used to automate the laborious and repetitive tasks by human operators to ensure consistent quality of products at high speed, increase productivity, lower labour costs and reduce workplace injury claims. However, a specially designed pick-and-place robot can no longer fit the current fast changing manufacturing process, where assembly lines should be flexible to be reconfigured quickly for different customer needs by programmable pick-and-place robots. The objective of the proposed research is to develop and test a visual-servo control algorithm for robots to perform pick-and-place autonomously, which can used to control industrial robots for small and medium sized auto parts manufacturers. The proposed approach will integrate the stereo computer vision and robotic technologies for visual-servo robotic control technology. The computer vision will identify the target in 3D space using imaging processing technology. A path for the end-effector of robot will then be planned subject to the constraint of space and operation requirements. The visual and path information will be feedback into the robot control system to form an outer feedback control loop. The inner control loop will move the end-effector to the target following the planned path in a controlled manner. The outcome of the proposed research provide a cost-effective way to help small and medium sized auto parts suppliers to increase productivity and quality while reduce labor costs by automating assembly lines. It will not only increase jobs to our industrial partner but also the local suppliers. The project will enhance the visual-servo robotic technology to automatically catch non-cooperative targets. In addition to the economic and technical benefits to Canada outlined above, this project will train three HQP in the related field and enhance the industrial partner's market competitiveness.