Mechatronics, Intelligent Mechanical Engineering Course, Department of Mechanical Engineering, Faculty of Engineering, Gifu University
/ Intelligent Production Technology Research & Development Center for Aerospace (IPTeCA)

It is essential to generate a target trajectory that suppresses residual vibration and torque in order to achieve high-speed and high-precision positioning in a multi-inertia system such as a table system where resonance occurs. However, in the trajectory generation method by final-state control (FSC), which is one of the target trajectory generation methods, there is a possibility that the calculation time will increase significantly as the travel time in the generated trajectory increases.

Therefore, we are conducting research on trajectory design using deep learning (DL). We are developing an optimal trajectory generation filter to generate trajectories equivalent to ones generated by FSC.

In recent years, there has been a growing need for robot automation in the deburring process. However, because relatively inexpensive small robots have low rigidity, it is difficult to achieve high-precision deburring in units of few micrometres.

We have developed a deburring robot using a VCM stage to precisely control the pressing force of the rotating polishing brush. By estimating the pressing force (reaction force) of the rotating brush with a reaction force estimation observer (RFOB), it is possible to control the force in a wider band than when using a force sensor. This makes it possible to achieve high followability for the contour of the object to be polished.

The CMC tactile sensor, invented by Professor Kawamura at this university, is a sensor that utilizes its character of changing electrical characteristics depending on pressure. In order to implement this sensor in a robot, we are further analyzing the characteristics of the CMC tactile sensor.

Even if the robot learns to reproduce the motion of the operator applying the coating, it may not be able to reproduce the same force as the operator due to differences in the relative position of the object to be coated and the hardness of the brushes. That results in unevenness in the coating.

We are developing a robot system that repeatedly learns until it can apply the same force as the operator. The unevenness is suppressed by correcting the teaching data.

Robots are expected to be more in demand in the future. In order to introduce them to many areas, one of the critical issues is their miniaturization.

We are developing a 2-DOF motor that can operate as both a linear motor and a rotary motor. The developed motor can also generate high torque with high energy efficiency due to its magnetic screw structure. It enables not only the downsizing of the robot but also energy saving.

In order to reduce time and labor, there is a growing need to automate not only simple but also complex tasks in the production process. When performing complex tasks, humans subconsciously adapt their actions in response to an ever-changing work environment. However, this behavior is difficult for machines and robots, which excel at performing simple repetitive actions and taught tasks.

One of the complex tasks performed by humans is the wiring process, in which bolts are connected and secured to each other by wires. In cooperation with Kato Laboratory, we are developing an automatic wiring system.

We aim to automate the wiring process by using the following methods;

1: Imitation learning, whereby a person using a teleoperated robot and a real-time workspace image serves as the basis for the robot operation information. The robot then learns to automate the task based on both the camera image and the robot operation information.

2: Speeding up robot control based on mechatronics.

Nonwoven fabrics used for automobile interiors and artificial leathers are inspected for contamination during production to ensure product quality and safety. Currently, while this inspection is carried out visually by workers, the long-time work of workers and the ambiguous standards of judgment by each worker are addressed.

Therefore, we are aiming to automate the inspection process by using an image processing system. In particular, this research focuses on the search for optimal parameters necessary for image processing and is conducting research and development of automatic parameter search using genetic algorithms. In addition, we are using experimental equipment that simulates a line process to verify an automatic inspection method with the practical application in mind. Furthermore, we are researching contamination detection methods using image recognition (deep learning) as well as image processing technology, with the aim of establishing optimal inspection methods.