2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)最新文献_第4页

Three-Dimensional Path Tracking Control of the Underactuated AUV Based on Backstepping Sliding Mode 基于反步滑模的欠驱动水下航行器三维路径跟踪控制

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8935968

Yu-shan Sun, Chenming Zhang, Hao Xu, Guo-cheng Zhang, Yuanqing Wang

{"title":"Three-Dimensional Path Tracking Control of the Underactuated AUV Based on Backstepping Sliding Mode","authors":"Yu-shan Sun, Chenming Zhang, Hao Xu, Guo-cheng Zhang, Yuanqing Wang","doi":"10.1109/ACIRS.2019.8935968","DOIUrl":"https://doi.org/10.1109/ACIRS.2019.8935968","url":null,"abstract":"Based on the improved backstepping method and sliding mode control principle, this paper studies the path tracking control problem of underactuated AUV considering the environmental position interference. The Serret-Frenet curve coordinate system is introduced, and the approach angle is designed, which decreases the path-following steady-state error. The integration of tracking error is used in the controller design to increase the robustness of the controller. In order to reduce the shaking, avoid differential explosion and optimize the tracking effect, a filter-based backstepping sliding mode controller is designed. A low-pass filter is used to approximate the virtual control signal to reduce chattering, and a second-order filter is used to avoid differential explosion. Finally, the numerical simulation results are shown to verify the control effect of the filtered backstepping sliding mode controller. Compared with the traditional backstepping sliding mode controller effect, the chattering of the controller output is significantly reduced. The AUV path tracking curve converges faster, the time taken to achieve stable tracking state is shorter, and the stability is improved.","PeriodicalId":338050,"journal":{"name":"2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114995462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Low Cost DFS-based Approach for Detection Speedup 基于dfs的低成本检测加速方法

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936043

Guan-Rong Shih, Pei-Hsuan Tsai

引用次数: 0

Categorizing License Plates Using Convolutional Neural Network with Residual Learning 基于残差学习的卷积神经网络车牌分类

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8935997

John Anthony C. Jose, Jose Martin Z. Maningo, Jayson P. Rogelio, A. Bandala, R. R. Vicerra, E. Sybingco, Phoebe Mae L. Ching, E. Dadios

{"title":"Categorizing License Plates Using Convolutional Neural Network with Residual Learning","authors":"John Anthony C. Jose, Jose Martin Z. Maningo, Jayson P. Rogelio, A. Bandala, R. R. Vicerra, E. Sybingco, Phoebe Mae L. Ching, E. Dadios","doi":"10.1109/ACIRS.2019.8935997","DOIUrl":"https://doi.org/10.1109/ACIRS.2019.8935997","url":null,"abstract":"ike other countries, the Philippines uses various license plate standards wherein some purely text while some are hybrid graphic-text plates. And to harness its generalizability, this study developed a classification algorithm utilized as a pre-processing scheme for the multi-standard license plate. With an input image captured at a different perspective, it was feed into the neural network and classify as Rizal monument series (2001 base and 2003 base), 2014 series and conduction sticker for new vehicles. In total, there are 303 different images captured for this study. Around 100 conduction sticker images, 103 Rizal Monument images, 100 black and white images. Furthermore, this study focused on using transfer learning technique, wherein a trained network utilized, then only the last layer was reset and retrained on the new dataset. To measure the performance of the classification model and optimized it cross-entropy and stochastic gradient descent was employed respectively at a learning rate of 0.001 and reduced by 10 for every seven (7) epochs. The progression of accuracy results in increasing the epochs, and for the 25 epochs, the training completed in 4 minutes and 7 seconds with the best validation accuracy of 82.61%.","PeriodicalId":338050,"journal":{"name":"2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122970514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

A Two-Stage Adaptive Clustering Approach for 3D Point Clouds 三维点云的两阶段自适应聚类方法

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936035

Caihong Zhang, Shaoping Wang, Biao Yu, Bichun Li, Hui Zhu

引用次数: 6

Roust Vanishing Point Detection Based on the Combination of Edge and Optical Flow 基于边缘和光流结合的鲁棒消失点检测

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936016

Zhelin Yu, Lidong Zhu

引用次数: 4

Adaptive Multi-Strategy Observation of Kernelized Correlation Filter for Visual Object Tracking

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936042

Rif'at Ahdi Ramadhani, G. Jati, W. Jatmiko, Ario Yudo Husodo

{"title":"Adaptive Multi-Strategy Observation of Kernelized Correlation Filter for Visual Object Tracking","authors":"Rif'at Ahdi Ramadhani, G. Jati, W. Jatmiko, Ario Yudo Husodo","doi":"10.1109/ACIRS.2019.8936042","DOIUrl":"https://doi.org/10.1109/ACIRS.2019.8936042","url":null,"abstract":"Visual object tracking leads a vital role in multiple fields such as intelligent surveillance system, intelligent transportation system, human-computer interaction, behavior analysis, and intelligent driving assistance. In recent years, research of object tracking tends to focus on improving accuracy. Kernelized Correlation Filter (KCF) is considered as a baseline algorithm for real-time object tracking in term of high computation speed and accuracy by using correlation efficiently in the Frequency domain. However, correlation filter-based tracker is still prone to model drift due to incorrect predictions. This condition caused by varied appearance model especially in fast motion and motion blur. We proposed a new concept of KCF based tracker by adding confidence score scheme to detect tracker loss. Our tracker also introduces observation model with adaptive multi-strategy to find the lost target. We test the proposed method using OTB100 data that has strong characteristics in fast motion and motion blur. The result demonstrates that the proposed method was capable of recovering the lost target. The proposed tracker achieves better performance compared to the existing tracker in term of 0.887 in accuracy and 0.895 success rate.","PeriodicalId":338050,"journal":{"name":"2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"27 14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130143661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Kinematic Characteristics Analysis of Cooperative Welding Robot with Multiple Manipulators 多机械手协作焊接机器人的运动特性分析

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8935973

Qingfei Zeng, Xuemei Liu, Chengrong Qiu, Aiping Li

引用次数: 4

Robot Path Planning with Low Learning Cost Using a Novel K-means-based Pointer Networks 基于k均值的指针网络的低学习成本机器人路径规划

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936004

Wei Cheng Wang, R. Chen

引用次数: 0

3D Edge Convolution in Deep Neural Network Implementation for Land Cover Semantic Segmentation of Airborne LiDAR Data 基于深度神经网络的三维边缘卷积在机载激光雷达数据地表覆盖语义分割中的实现

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8935980

Nur Hamid, A. Wibisono, M. A. Ma'sum, Ahmad Gamal, Roni Ardhianto, A. M. Arymurthy, W. Jatmiko

引用次数: 0

Dynamic Motion Planning for Conducting Obstacle Avoidance Maneuver of Fixed Wing Autonomous Aerial Vehicle 固定翼自主飞行器避障机动的动态运动规划

2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS) Pub Date : 2019-07-01 DOI: 10.1109/ACIRS.2019.8936024

Ario Yudo Husodo, H. Wisesa, W. Jatmiko

{"title":"Dynamic Motion Planning for Conducting Obstacle Avoidance Maneuver of Fixed Wing Autonomous Aerial Vehicle","authors":"Ario Yudo Husodo, H. Wisesa, W. Jatmiko","doi":"10.1109/ACIRS.2019.8936024","DOIUrl":"https://doi.org/10.1109/ACIRS.2019.8936024","url":null,"abstract":"Fixed Wing Autonomous Aerial Vehicles (FW-AAV) face several challenges when surveying an area. One of the most crucial challenges that the vehicle face is to plan and adjust its path according to the obstacles that exist in the area. Although FW-AAV has good capability in conducting forward movement, its maneuverability is limited. It can’t pause its movement in a location and it doesn’t flexible enough to change its direction significantly when facing obstacles. In a real-world environment, the obstacles could also shift according to the unpredictable situation. In this paper, we propose a dynamic motion planning for an FW-AAV using Greedy Principle. This method tries to direct the FW-AAV path planning movement when facing obstacles considering its maneuver limitation. The proposed method introduces a concept of 4 directional rotatable Distance Sensor. The Greedy Principle is applied by choosing the nearest possible vacant path obtained by the directional sensor. The method is tested in a 3-Dimensional environment, which includes several realworld obstacles that the vehicle faces and a moving target which is the vehicle needs to reach. Using the Greedy principle, the FW-AAV could successfully reach the moving target safely.","PeriodicalId":338050,"journal":{"name":"2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120843298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2