Struggling to understand research papers? Don’t panic! Get simple explanations to your questions. Learn more

scispace - formally typeset
SciSpace - Your AI assistant to discover and understand research papers | Product Hunt

Conference

International Conference Control and Robots 

About: International Conference Control and Robots is an academic conference. The conference publishes majorly in the area(s): Robot & Robot kinematics. Over the lifetime, 47 publication(s) have been published by the conference receiving 38 citation(s).
Papers
More filters

Proceedings ArticleDOI
01 Sep 2018
TL;DR: A deep learning method is presented for the detection of car license plate by Train a region proposal network and use the output of the RPN to train the R-CNN, shortened to a controllable range.
Abstract: Vehicle license plate, also known as a number plate, represents a legal license to participate in the public traffic. It plays an important role in detecting stolen vehicles, controlling traffic volume, ticketing speeding vehicles, and so on. In this paper, we presented a deep learning method for the detection of car license plate. We train a region proposal network and use the output of the RPN to train the R-CNN. The training time for complex large images is shortened to a controllable range. The detection time of the target area is shortened to quasi real time, and the accuracy is also considerable.

6 citations


Proceedings ArticleDOI
01 Sep 2018
TL;DR: A new method is proposed to solve the inverse kinematics model for 7-DoF manipulators by focusing on how to derive equations for the feasible space of the endpoint of each joint and correspondingly the feasibleSpace of each arm-angle when the end position of the robot arm is given, which lays the foundation for the robotic arm to complete obstacle avoidance and optimal path planning tasks.
Abstract: The 7-DoF Manipulator has a high degree of flexibility and can perform many complex tasks for humans, therefore widely used in many fields. This paper proposes a new method to solve the inverse kinematics model for 7-DoF manipulators. Specifically, it focuses on how to derive equations for the feasible space of the endpoint of each joint and correspondingly the feasible space of each arm-angle when the endpoint of the robot arm is given, which lays the foundation for the robotic arm to complete obstacle avoidance and optimal path planning tasks. First, the influence of the first three joints and the last three joints on the end position of the robotic arm is decoupled. Based on this decoupling, the relationship between the last three joint angles and the end position of the robotic arm is solved through the space vector. Furthermore, the relationship between the end position of the robotic arm and the first three joint angles is obtained through coordinate rotation. Finally, this paper validates the results by simulations.

5 citations


Proceedings ArticleDOI
26 Dec 2020
Abstract: In this paper we have designed an intelligent wearable device and developed the corresponding algorithm, for COVID-19 positive patients that is capable of predicting and notifying the increase in severity of the virus. The device uses ESP 32: Node MCU, MAX 30102: Pulse Oximeter and Heart rate sensor, LM35: Temperature sensor and a vibration sensor. This device will monitor the patient's body condition such as heart pulse rate, oxygen saturation level, body temperature, hand movements due to restlessness and process this information simultaneously. Consequently, when the virus is predicted to advance to its next stage, an alert will be sent to the person taking care of the patient. Hence, this device will inform when the patient is advancing from mild to the moderate or serve condition of COVID-19. The paper gives a deep understanding on the use of this device.

4 citations


Proceedings ArticleDOI
01 Sep 2018
TL;DR: This paper has tested the four convolutional neural networks (ConvNet) and four weight update methods and found the ResNet-50 and AdaDelta combination showed the best performance in the insect dataset.
Abstract: Research on the artificial intelligence is increasing with the improvement of computing power and the development of algorithm theory. In particular, the deep neural network, which is a field of machine learning, is widely used in artificial intelligence because it can process data that cannot be solved by conventional shallow neural networks more effectively. Implementation of a deep neural network is generally based on popularized neural networks with excellent generalization performance, which saves time and effort. However, it is difficult to guess which deep neural networks and optimization methods can achieve the best performance in their dataset. In this paper, we have tested the four convolutional neural networks (ConvNet) and four weight update methods. Experiments were conducted using a 5-fold cross-validation based on insect image dataset. As a result, the ResNet-50 and AdaDelta combination showed the best performance (89.98 ± 1.40)% in the insect dataset.

3 citations


Proceedings ArticleDOI
01 Sep 2018
TL;DR: Experimental results show that the proposed PSO based PID and LQR techniques provide relatively fast response and small steady-state error in the system under load variation.
Abstract: In this work, we use PSO to adaptively adjust gains of PID and LQR controllers to regulate speed and position of a DC motor with load variation. The proposed framework is implemented on programmable logic controller (PLC) with encoder sensors and Ethernet port to monitor the feedback via SCADA application. Experimental results show that the proposed PSO based PID and LQR techniques provide relatively fast response and small steady-state error in the system under load variation.

3 citations


Network Information
Related Conferences (5)
Society of Instrument and Control Engineers of Japan

7.2K papers, 27.7K citations

65% related
International Conference on Intelligent Computing

10.1K papers, 37.1K citations

64% related
International Conference on Control and Automation

6.5K papers, 27.3K citations

64% related
Robotics and Biomimetics

6.2K papers, 37.6K citations

62% related
Performance
Metrics
No. of papers from the Conference in previous years
YearPapers
202031
201816