{"title":"Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images","authors":"Zhen Chen, A. Georgiadis","doi":"10.1109/ICRAE48301.2019.9043800","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043800","url":null,"abstract":"Object detection plays a significant role in an intelligent system equipped with a fisheye camera. The fisheye image captures a wide field-of-view but deforms in the radial direction. The deformation changes the relative angle between the edge of objects and the image. Therefore, a horizontal bounding box cannot perform an accurate description of an object's location and dimension in advanced neural network training. In this paper, we build a rotation sensitive neural network targeting to realize one-stage regression on the fisheye image detection. The oriented bounding box is applied in the object's description and detection. To evaluate our proposed method, we develop a new labelled fisheye image dataset that contains two categories. The network model training takes around 3 hours and achieves 100% precious by the test set.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"194 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123656839","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}
Hui Wang, Ting Lei, Y. Rong, Pengfei Xiong, Yu Huang
{"title":"Automatic GTAW Robot Arc Length Control Based on Particle Filter","authors":"Hui Wang, Ting Lei, Y. Rong, Pengfei Xiong, Yu Huang","doi":"10.1109/ICRAE48301.2019.9043787","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043787","url":null,"abstract":"In the automatic GTAW robot welding process, workpiece-surface unevenness and tungsten-electrode loss are so common that frequently cause the fluctuation of welding arc length and the unstable welding quality. In order to solve the phenomenon, this paper collected real-time welding arc voltage, and obtained the arc length data by the relationship between arc length and arc voltage by using an arc voltage sensor, and proposed a particle-filter-based automatic GTAW robot arc length adjustment method to eliminate the nonlinear non-Gaussian noise in the welding process, which can accurately and quickly control the arc length of the welding robot. Experiment results showed that the designed method can effectively improve the stability of the welding arc length and the welding quality.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129199485","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}
Md. Sadad Mahamud, Md. Abdullah Al Rakib, T. M. Faruqi, Mainul Haque, Sharifa Akter Rukaia, Sumaiya Nazmi
{"title":"Mouchak - An IoT Basted Smart Beekeeping System Using MQTT","authors":"Md. Sadad Mahamud, Md. Abdullah Al Rakib, T. M. Faruqi, Mainul Haque, Sharifa Akter Rukaia, Sumaiya Nazmi","doi":"10.1109/ICRAE48301.2019.9043815","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043815","url":null,"abstract":"Internet of things (IoT) is playing an enormous role to automate our world. In this paper, an automated IoT based system is proposed for beekeeping, where a smart prototype bee box is designed to monitor the bee colony. Using this system farmers can easily check the quantity of honey and wax. It will also provide necessary information about real-time temperature and humidity of the beehive. Moreover, a farmer can be awarded about the bee piping by monitoring the bee noises of the hive. Through this eco-friendly and cost-effective system, farmers can monitor their beehives characteristics from long-distance using a mobile application.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132212015","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}
{"title":"HW/SW Co-design and FPGA Acceleration of a Feature-Based Visual Odometry","authors":"Chiang-Heng Chien, Chiang-Ju Chien, C. Hsu","doi":"10.1109/ICRAE48301.2019.9043811","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043811","url":null,"abstract":"In the field of visual odometry (VO) or SLAM, deriving camera poses from image features is the basic issue. Even though feature-based VO or SLAM are more efficient than non-feature-based methods, they are still unfortunately computationally demanding. This paper addresses the concerns of computational efficiency, computational resources and power-consumption problem of a VO algorithm by designing a hardware-software (HW/SW) co-design architecture for the implementation on a field-programmable gate array (FPGA) and a Nios II CPU. Given images from Nios II, features are extracted and matched by SIFT and linear exhausted search (LES) algorithms via hardware. The design of LES module is improved so that the speed is accelerated compared to our previous work. Subsequently, camera poses are estimated using an ICP algorithm, where the derivation of nearest orthogonal matrix is achieved by integrating Denman-Beavers (DB) approach and Taylor approximation method. As such, the required hardware resources are lesser. After hardware computations, the results are then transferred back to Nios II. To show the effectiveness of the proposed approach, experiments using KITTI dataset are conducted. The results show that, taking the advantages of efficient computation of hardware, the computational time is greatly reduced, compared to a full-software implementation. Moreover, usage of hardware resources are also lesser than existing methods.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132575349","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}
{"title":"Automated Generation of Energy Efficient Drive Cycles for Electric Vehicles Considering Limiting Factors","authors":"S. Srivastava, Pranav Maheshwari, S. Sengupta","doi":"10.1109/ICRAE48301.2019.9043841","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043841","url":null,"abstract":"Electric Vehicles (EV) are considered as future of the automotive industry due to clean and environment-friendly propulsion but are criticized for their limited range compared to conventional fuel-driven vehicles. In this paper, first of all, the development and validation of a longitudinal vehicle dynamics model for a practical EV is described. Based on the model, the EV dynamic performance characteristics like maximum gradient it can handle and maximum achievable acceleration and speed are evaluated through theoretical expressions. Further, the driving pattern dramatically influences the energy consumed in electric vehicles over a path. In this paper, a simple framework is proposed for automatically generating energy-efficient drive cycles for a practical EV, considering several limiting factors together. Since the most energy-efficient drive cycle may not be the fastest one, a user-defined weight factor based on time and energy tradeoff is incorporated in the framework to generate drive cycles based on user requirements. Such automated drive cycles generated, can provide targeted speed profiles to drivers of EVs before their start of the journey, thus saving energy. The performance of the described method is illustrated and analyzed through results.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131053751","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}
{"title":"A Comprehensive Positioning Accuracy Compensation Method Based on BP Neural Network of Industrial Robots","authors":"Xiangzhen Chen, Q. Zhan, Yifan Wang, Yanbin Yao","doi":"10.1109/ICRAE48301.2019.9043840","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043840","url":null,"abstract":"Aiming at the problem that the absolute positioning accuracy of industrial robots cannot meet the requirements of high-precision positioning, a comprehensive positioning accuracy compensation method based on back propagation (BP) neural network was proposed, which considers both the geometric parameters factors and the stiffness performance factors influencing the absolute positioning accuracy of robots. This method uses the actual positioning coordinates and the stiffness performance evaluation index of an industrial robot as the input, and the theoretical positioning coordinates of the robot as output to train a BP neural network. Then the trained BP neural network is used to compensate the absolute positioning accuracy of the robot. This method was tested on a KUKA KR500L340-2 industrial robot, and the experimental results show that the absolute positioning accuracy of the robot is increased from 1.155∽2.892mm before compensation to 0.068∽0.465mm after compensation. The absolute positioning accuracy of the robot has been significantly improved.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"91 19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128787379","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}
{"title":"Overtaking Behavior Simulation of Vehicle Platoon in Face-to-Face Traffic Flow","authors":"E. Kita, Hiroki Sakamoto, Tatuhiro Tamaki","doi":"10.1109/ICRAE48301.2019.9043810","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043810","url":null,"abstract":"Vehicle Platoon is the important technique for increasing the traffic capacity of road network safely. Our research group has been studying the velocity control model of the vehicle in the vehicle platoon. Previous studies focus on the control of vehicle in the platoon in order to make the platoon stable. The aim of this study is to control the vehicle velocity when a vehicle platoon overtakes a frontal vehicle without colliding with a vehicle traveling in the other lane. The velocity control model is defined as the vehicle following model. The validity of the model is confirmed in the computer simulation and the experiment of LEGO MINDSTORM. The results show that comparison of simulation and experiment shows that the experiment results agree well with the simulation results.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133349225","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}
Zhao Shao-Qing, Cui Yan, Zhou Liuyuan, S. Guan, He Hong-Jun
{"title":"Hopf Bifurcation Analysis of Nonlinear Rössler Systems","authors":"Zhao Shao-Qing, Cui Yan, Zhou Liuyuan, S. Guan, He Hong-Jun","doi":"10.1109/ICRAE48301.2019.9043789","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043789","url":null,"abstract":"The Hopf bifurcation problem of nonlinear Rössler system with time delay is studied. The Hopf bifurcation conditions of the Rössler system with nonlinear delay are given, the Hopf bifurcation points of the system delay parameters are obtained, and the stability of the system near the delay bifurcation points is analyzed. The simulation results show that the supercritical Hopf bifurcation occurs in the time-delay bifurcation point of the nonlinear Rössler system, and the changes of the time-delay parameters near the time-delay bifurcation point will affect the stability of the system.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131492226","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}
N. Win, Kazuki Kida, Matsuhiro Ko, Suzuki Jiei, S. Cosentino, H. Ishii, A. Takanishi
{"title":"A Novel Particle Filter Based SLAM Algorithm for Lunar Navigation and Exploration","authors":"N. Win, Kazuki Kida, Matsuhiro Ko, Suzuki Jiei, S. Cosentino, H. Ishii, A. Takanishi","doi":"10.1109/ICRAE48301.2019.9043804","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043804","url":null,"abstract":"This paper presents a simultaneous localization and mapping (SLAM) system for lunar exploration. The proposed SLAM algorithm presents a significantly lower computational complexity compared to the state-of-the-art solutions, due the use of a Rao-Blackwellised particle filter with adaptive and compound resampling. The proposed SLAM sensor system consists of one light detecting and ranging sensor (LIDAR) and one IMU, to minimize illumination-dependent errors; as the lunar environment, and in particular the target exploration region around the Marius Hills hole, presents very variable illumination conditions. The system was tested via simulation, using existing environmental data from the mare tranquillitatis pit crater.","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134575382","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}
{"title":"Stata Center Frame: A Novel World Assumption for Self-Localization","authors":"A. M. Kaneko, Ryoko Ichinose","doi":"10.1109/ICRAE48301.2019.9043830","DOIUrl":"https://doi.org/10.1109/ICRAE48301.2019.9043830","url":null,"abstract":"Map matching is a commonly applied localization method to mobile robots. Due to the complexity of building maps and the matching task itself, many studies have adopted simplifying assumptions (geometrical and directional) of the world, such as the Manhattan World, the Atlanta World, a Mixture of Manhattan Frames and the Stata Center World. Even though the latter has flexibility to represent several environments, it has been so far limited to scene segmentation and has not yet been applied to self localization. This work explores the capabilities of the Stata Center World for self localization and further proposes a novel concept of Stata Center Frame. This assumption permits orientation estimation with one single line and position estimation by visual and positional patterns from the scene using only one monocular camera. The results show that self-localization can be achieved online with higher accuracy (average 0.12 m error) comparing to traditional techniques (0.13 m, offline).","PeriodicalId":270665,"journal":{"name":"2019 4th International Conference on Robotics and Automation Engineering (ICRAE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123281685","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}