Search results

Human assembly process recognition in human–robot collaboration (HRC) has been studied recently. However, most research works do not cover high-precision and long-timespan sub-assembly recognition. Hence this paper aims to deal with this problem.

To deal with the above-mentioned problem, the authors propose a 3D long-term recurrent convolutional networks (LRCN) by combining 3D convolutional neural networks (CNN) with long short-term memory (LSTM). 3D CNN behaves well in human action recognition. But when it comes to human sub-assembly recognition, the accuracy of 3D CNN is very low and the number of model parameters is huge, which limits its application in human sub-assembly recognition. Meanwhile, LSTM has the incomparable superiority of long-time memory and time dimensionality compression ability. Hence, by combining 3D CNN with LSTM, the new approach can greatly improve the recognition accuracy and reduce the number of model parameters.

Experiments were performed to validate the proposed method and preferable results have been obtained, where the recognition accuracy increases from 82% to 99%, recall ratio increases from 95% to 100% and the number of model parameters is reduced more than 8 times.

The authors focus on a new problem of high-precision and long-timespan sub-assembly recognition in the area of human assembly process recognition. Then, the 3D LRCN method is a new method with high-precision and long-timespan recognition ability for human sub-assembly recognition compared to 3D CNN method. It is extraordinarily valuable for the robot in HRC. It can help the robot understand what the sub-assembly human cooperator has done in HRC.

High precision assembly processes using industrial robots require the process parameters to be tuned to achieve desired performance such as cycle time and first time through rate. Some researchers proposed methods such as design-of-experiments (DOE) to obtain optimal parameters. However, these methods only discuss how to find the optimal parameters if the part and/or workpiece location errors are in a certain range. In real assembly processes, the part and/or workpiece location errors could be different from batch to batch. Therefore, the existing methods have some limitations. This paper aims to improve the process parameter optimization method for complex robotic assembly process.

In this paper, the parameter optimization process based on DOE with different part and/or workpiece location errors is investigated. An online parameter optimization method is also proposed.

Experimental results demonstrate that the optimal parameters for different initial conditions are different and larger initial part and/or workpiece location errors will cause longer cycle time. Therefore, to improve the assembly process performance, the initial part and/or workpiece location errors should be compensated first, and the optimal parameters in production should be changed once the initial tool position is compensated. Experimental results show that the proposed method is very promising in reducing the cycle time in assembly processes.

The proposed method is practical without any limitation.

The proposed technique is implemented and tested using a real industrial application, a valve body assembly process. Hence, the developed method can be directly implemented in production.

This paper provides a technique to improve the assembly efficiency by compensating the initial part location errors. An online parameter optimization method is also proposed to automatically perform the parameter optimization process without human intervention. Compared with the results using other methods, the proposed technology can greatly reduce the assembly cycle time.

Paint path planning for industrial robots is critical for uniform paint distribution, process cycle time and material waste, etc. However, paint path planning is still a costly and time‐consuming process. Currently paint path planning has always caused a bottle‐neck for manufacturing automation because typical manual teaching methods are tedious, error‐prone and skill‐dependent. Hence, it is essential to develop automated tool path‐planning methods to replace manual paint path planning. The purpose of this paper is to review the existing automated tool path‐planning methods, and investigate their advantages and disadvantages.

The approach takes the form of a review of automated tool path‐planning methods, to investigate the advantages and disadvantages of the current technologies.

Paint path planning is a very complicated task considering complex parts, paint process requirements and complicated spraying tools. There are some research and development efforts in this area. Based on the review of the methods used for paint path planning and simulation, the paper concludes that: the tessellated CAD model formats have many advantages in paint path planning and paint deposition simulation. However, the tessellated CAD model formats lack edge and connection information. Hence, it may not be suitable for some applications requiring edge following, such as welding. For the spray gun model, more complicated models, such as 2D models, should be used for both path planning and paint distribution simulation. Paint path generation methods should be able to generate a paint path for complex automotive parts without assumptions, such as presupposing a part with a continuous surface.

The paper makes possible automated path generation for spray‐painting process using industrial robots such that the path‐planning time can be reduced, the product quality improved, etc.

The paper provides a useful review of current paint path‐planning methodologies based on the CAD models of parts.

The electronics industries are relying increasingly on robotics for their production. Wafer handling robots are used to transfer wafers between wafer processing stations. A pick‐measure‐place method is typically utilized to transfer wafers accurately. The measurement step is performed using an aligner, which is time‐consuming. To increase wafer transfer efficiency, it is desirable to speed up the measurement process or place it in parallel with other operations. To solve the problem, optic sensors are installed at each station to estimate the wafer eccentricity on‐the‐fly. The eccentricity values are then applied to control the robot to place the wafer directly onto another station accurately without using the aligner. However, current methods face problems to achieve high accuracy requirements to meet the electronic manufacturing needs. The purpose of this paper is to develop a technique to improve the wafer handling performance in semiconductor manufacturing.

The kinematics model of the wafer handling robot is developed. Two sensor location calibration algorithms are proposed. Method I is based on the wafer handling path. Method II uses the offset paths from the wafer handling path. The results from these two methods are compared. To compute the wafer eccentricity on‐the‐fly, a wafer eccentricity estimation technique is developed.

The developed methods are implemented using a wafer handling robotic system in semiconductor manufacturing. The wafer eccentricity estimation errors are greatly reduced using the developed methods. The experimental results demonstrate that Method II achieves better results and can be used to improve the wafer handling accuracy and efficiency.

The proposed technique is implemented and tested many times on a wafer handing robotic system. The notch alignment in the wafer handling needs further research.

The developed method is validated using a system in semiconductor manufacturing. Hence the developed method can be directly implemented in production if the notch of a wafer can be identified.

This paper provides techniques to improve the wafer handling accuracy in semiconductor manufacturing. Compared with the results using other methods, Method II greatly increases the wafer handling accuracy to satisfy the semiconductor manufacturing needs.

Automatic trajectory generation for spray painting is highly desirable for today’s automotive manufacturing. Generating paint gun trajectories for free‐form surfaces to satisfy paint thickness requirements is still highly challenging due to the complex geometry of free‐form surfaces. In this paper, a CAD‐guided paint gun trajectory generation system for free‐form surfaces has been developed. The system utilizes the CAD information of a free‐form surface to be painted and a paint gun model to generate a paint gun trajectory to satisfy the paint thickness requirements. A paint thickness verification method is also provided to verify the generated trajectories. The simulation results have shown that the trajectory generation system achieves satisfactory performance. This trajectory generation system can also be applied to generate trajectories for many other CAD‐guided robot trajectory planning applications.

This paper aims to develop a strategy for high‐precision assembly in a semi‐structured environment based on vision and force control.

The position and orientation of a part are identified using the vision system. The force/torque control algorithm is then applied to perform a tight‐tolerance assembly that is a high‐precision assembly.

The tight tolerance assembly in a semi‐structured environment is successfully implemented using vision guidance and force/torque‐control strategy.

The developed methodology can be applied to tight tolerance assembly, such as forward‐clutch assembly, torque‐converter assembly, etc.

An industrial assembly methodology has been developed and implemented for high‐precision assembly in a semi‐structured environment. This innovation has many potential applications in automotive manufacturing.

Automated chopper gun trajectory planning (CGTP) for spray forming is highly desirable for today's automotive manufacturing. Generating chopper gun trajectories for free‐form surfaces to satisfy material distribution requirements is still highly challenging due to the complexity of the problems. In this paper, a user‐friendly software for automated CGTP has been developed. The CGTP software can take different formats of the CAD models of parts. A chopper gun trajectory is generated based on the CAD model of a part, chopper gun model, and constraints. A part is partitioned into patches to satisfy the given constraints. A trajectory integration algorithm is developed to integrate the trajectories of the patches to form a trajectory for the part. The CGTP software has been tested by Ford Motor Company and achieved satisfactory results.

Moving production lines are widely used in many manufacturing factories, such as automotive and general industries. However, industrial robots are hardly used to perform any tasks on the moving production lines. One of the main reasons is that it is difficult for conventional industrial robots to adjust to any sort of change. Therefore, the authors developed an industrial robotic system to track the random motion of the moving production lines while performing assembly processes. Before setting up a physical system to measure the system performance, it is desirable to develop a method to analyze the system performance. The purpose of this paper is to develop a performance analysis method for a robotic assembly system on a moving production line.

The developed system is based on the synergic combination of visual servoing and force control technology. Since it is difficult to model the system accurately, a second‐order system is used to approximate it. The system performance for force control and visual servoing is then analyzed. The tracking errors are calculated and compared with experimental results.

The developed method is evaluated using an experimental system and simulation. The simulation results are quite close to the experimental results. Hence, the developed method can be used to estimate the system performance.

Since only one system is set up to validate the developed method, more testing is needed to generalize it.

The developed technology is validated using the experimental results and the results are promising. Even though there is a limitation, the developed method can be used to estimate the system performance before setting up a physical system.

This paper provides a system performance analysis method for a robotic assembly on a moving production line. It is important to estimate the system performance before setting up a physical system because it will save a lot of time and resources in the manufacturing floor.