간행물
로봇학회논문지 KCI 등재 The Journal of Korea Robotics Society
- 발행기관 한국로봇학회
- 자료유형 학술지
- 간기 계간
- ISSN 1975-6291 (Print)2287-3961 (Online)
- 수록기간 2006 ~ 2020
- 주제분류 공학 > 제어계측공학 공학 분류의 다른 간행물
- 십진분류KDC 559DDC 629
권호리스트/논문검색
제14권 제1호 (통권 제51호) (2019년 3월) 10건
1.
2019.03
서비스 종료(열람 제한)
Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.
2.
2019.03
서비스 종료(열람 제한)
Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.
3.
2019.03
서비스 종료(열람 제한)
In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.
4.
2019.03
서비스 종료(열람 제한)
For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot’s understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.
5.
2019.03
서비스 종료(열람 제한)
A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.
6.
2019.03
서비스 종료(열람 제한)
Reinforcement learning has been applied to various problems in robotics. However, it was still hard to train complex robotic manipulation tasks since there is a few models which can be applicable to general tasks. Such general models require a lot of training episodes. In these reasons, deep neural networks which have shown to be good function approximators have not been actively used for robot manipulation task. Recently, some of these challenges are solved by a set of methods, such as Guided Policy Search, which guide or limit search directions while training of a deep neural network based policy model. These frameworks are already applied to a humanoid robot, PR2. However, in robotics, it is not trivial to adjust existing algorithms designed for one robot to another robot. In this paper, we present our implementation of Guided Policy Search to the robotic arms of the Baxter Research Robot. To meet the goals and needs of the project, we build on an existing implementation of Baxter Agent class for the Guided Policy Search algorithm code using the built-in Python interface. This work is expected to play an important role in popularizing robot manipulation reinforcement learning methods on cost-effective robot platforms.
7.
2019.03
서비스 종료(열람 제한)
This work presents a design and control method for a flexible robot arm operated by a wire drive that follows human gestures. When moving the robot arm to a desired position, the necessary wire moving length is calculated and the motors are rotated accordingly to the length. A robotic arm is composed of a total of two module-formed mechanism similar to real human motion. Two wires are used as a closed loop in one module, and universal joints are attached to each disk to create up, down, left, and right movements. In order to control the motor, the anti-windup PID was applied to limit the sudden change usually caused by accumulated error in the integral control term. In addition, master/ slave communication protocol and operation program for linking 6 motors to MYO sensor and IMU sensor output were developed at the same time. This makes it possible to receive the image information of the camera attached to the robot arm and simultaneously send the control command to the robot at high speed.
8.
2019.03
서비스 종료(열람 제한)
The paper proposes a stiffness measurement device composed of a measurement part including six indenters and a fixing part including four fixtures. The device is able to make simultaneously measurements of the stiffness of human arm. The six indenters make use of both position and force control schemes sequentially whenever needed. In addition, the loadcells and the digital encoders are attached to the indenters and electric motors, respectively, so that the data can be provided in real time. On the end of the indenter, two-axis potentiometer is attached in order to measure the angle difference between the applied force axis and the axis normal to the skin of human arm, and to convert the force measured on the loadcell into the actual applied force to skin. For this purpose, the mapping between the voltage output and the angle of potentiometer was obtained by fitting it for each axis. Ultimately, the measurement device was able to measure the stiffnesses of six regions of human arm.
9.
2019.03
서비스 종료(열람 제한)
In this paper, we propose an algorithm that estimates the location of lunar rover using IMU and vision system instead of the dead-reckoning method using IMU and encoder, which is difficult to estimate the exact distance due to the accumulated error and slip. First, in the lunar environment, magnetic fields are not uniform, unlike the Earth, so only acceleration and gyro sensor data were used for the localization. These data were applied to extended kalman filter to estimate Roll, Pitch, Yaw Euler angles of the exploration rover. Also, the lunar module has special color which can not be seen in the lunar environment. Therefore, the lunar module were correctly recognized by applying the HSV color filter to the stereo image taken by lunar rover. Then, the distance between the exploration rover and the lunar module was estimated through SIFT feature point matching algorithm and geometry. Finally, the estimated Euler angles and distances were used to estimate the current position of the rover from the lunar module. The performance of the proposed algorithm was been compared to the conventional algorithm to show the superiority of the proposed algorithm.
10.
2019.03
서비스 종료(열람 제한)
In this paper, we develop a virtual experimental environment to investigate users’ eye gaze in human-robot social interaction, and verify it’s potential for further studies. The system consists of a 3D robot character capable of hosting simple interactions with a user, and a gaze processing module recording which body part of the robot character, such as eyes, mouth or arms, the user is looking at, regardless of whether the robot is stationary or moving. To verify that the results acquired on this virtual environment are aligned with those of physically existing robots, we performed robot-guided quiz sessions with 120 participants and compared the participants’ gaze patterns with those in previous works. The results included the followings. First, when interacting with the robot character, the user's gaze pattern showed similar statistics as the conversations between humans. Second, an animated mouth of the robot character received longer attention compared to the stationary one. Third, nonverbal interactions such as leakage cues were also effective in the interaction with the robot character, and the correct answer ratios of the cued groups were higher. Finally, gender differences in the users’ gaze were observed, especially in the frequency of the mutual gaze.
