{"title":"Action Segmentation via Robust Constraint Matrix Factorization Clustering Framework","authors":"Liqun Ren, Guopeng Li, Wenjing Yang, Feng Jing","doi":"10.1109/ACIRS49895.2020.9162603","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162603","url":null,"abstract":"Action understanding, which has been applied in a wide range of intelligent systems, has gained much attention for its better performance. However, the existing literature mainly focuses on supervised or semi-supervised frameworks, and effectively designing an unsupervised clustering method for action segmentation is still a challenging problem. In this paper, we propose a novel unsupervised clustering method for action segmentation based on robust structure constraint matrix factorization and the Ncut method by utilizing the similarity information among neighboring frames. Considering that the true neighboring frames are likely to share more similarity in action sequences, a useful structure constraint was designed to guide the action representation learning process. With the semi-nonnegative matrix factorization, more comprehensive low-dimensional representation of actions can be learned. Then, the similarity graph can be obtained from this new representation, and the final action segmentation results can be obtained by graph cut methods. Experiments on several real action datasets demonstrate that the proposed method outperforms state-of-the-art methods.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"168-169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114402881","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":"CNN Based Adaptive Kalman Filter in High-Dynamic Condition for Low-Cost Navigation System on Highspeed UAV","authors":"Zhuoyang Zou, Tiantian Huang, Lingyun Ye, K. Song","doi":"10.1109/ACIRS49895.2020.9162601","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162601","url":null,"abstract":"Kalman Filter (KF) is widely used in navigation as a data-fusion algorithm. When KF is applied in high-speed Unmanned Aerial Vehicle (UAV) mounted with low-cost integrated navigation system, its performance always deteriorates in complicated and high-dynamic conditions. Facing such scenario, we proposed a new algorithm of adaptive Kalman Filter in this paper. The new method is based on 1-dimensional Convolutional Neural Network (CNN). The key component of the algorithm is a deep neural network estimator of system noise covariance. We modeled Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS) integrated navigation system and then trained the estimator using IMU and GNSS data which is sampled in real flight. Further, we tested the proposed algorithm on another real-sampled dataset of UAV and compared its performance with classical KF and Sage-Husa adaptive Filter (SHF). The results show a better adaptiveness of the proposed algorithm in high-dynamic condition and partly liberates researchers from parameter tuning.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117287687","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":"General Coating of Arbitrary Objects Using Robot Swarms","authors":"A. Cheraghi, Gorden Wunderlich, Kalman Graffi","doi":"10.1109/ACIRS49895.2020.9162617","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162617","url":null,"abstract":"(Nano) robot swarms promise new applications in the field of health and entertainment. One of the tasks such a swarm could solve is coating, in which the robots in the swarm locate themselves as close to an object of arbitrary shape as possible. In this paper, we present a swarm coating algorithm for simple robots using only local communication and decentralized coordination only. The robots calculate distances to the coating target object for themselves and all adjacent spaces around them, trying then to move to a lower distance than they are currently at. Through simulations, we show that our approach is able to efficiently coat various object forms with a 100% success rate, even objects with cave-like structures are coated correctly.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123505846","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":"ACIRS 2020 Preface","authors":"","doi":"10.1109/acirs49895.2020.9162597","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162597","url":null,"abstract":"On behalf of the Organizing Committee, it is my pleasure to welcome all our distinguished speakers and authors to the 2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS 2020). The idea of the conference is for scientists, scholars, engineers and students from universities and industries all around the world to present their ongoing research activities, and to foster research relations between the universities and the industry. This conference provides opportunities for the delegates to exchange new ideas and application experiences, to establish business or research relations and to find global partners for future collaboration.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121100361","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 Leader Based Coating Algorithm for Simple and Cave Shaped Objects with Robot Swarms","authors":"A. Cheraghi, Kalman Graffi","doi":"10.1109/acirs49895.2020.9162610","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162610","url":null,"abstract":"Self-organizing swarm systems promise an essential progress in several research areas. They can find application in health context, such as through nano-robots, or material context, such as for health-healing properties. Swarm behavior in nature is well known e.g. bird flocks that protect individual birds, ants that collaboratively transport bigger objects, or predators who hunt in packs. Applying these strategies to future robot swarms promises to open further opportunities. In this paper, we address the problem of object coating, in which a swarm of “subjects” aims to position itself as tightly as possible around an object. We introduce a leader-based coating algorithm that promises near-optimal performance. A leader is elected to coordinate the actions of the swarm; thus, it scans the entire object and plans the placement of the individual swarm members upfront. Through its coordination, each individual subject is placed around the scanned object. While simple shapes are easy to master, a strong emphasis of this paper lies on dealing with cave-shaped objects in which passages or trails might be blocked in a naive approach. We elaborate how to deal with such problems and how our algorithm addresses this issue. In the evaluation we showcase that our approach is able to coat cave shaped objects with a 100% success rate.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127427795","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":"ACIRS 2020 Table of Contents","authors":"","doi":"10.1109/acirs49895.2020.9162615","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162615","url":null,"abstract":"","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"288 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123056969","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":"Computational Acoustic Model for Non-intrusive Inspection of a Fluidic Channel","authors":"O. Ogundare, Srinivasan Jagannathan","doi":"10.1109/ACIRS49895.2020.9162624","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162624","url":null,"abstract":"The shortcomings of traditional pressure wave analysis for the detection of material deposits and structural compromises within a pipeline forms the motivation for this work. In many Oil and Gas pipelines, a pressure pulse generated using a fast-acting valve (hydrodynamic pressure) or an intrusive acoustic source (acoustic pressure) is often used for leak detection, deposition or blockage detection. A data logger records the incident pressure wave and its reflection. The mechanism of wave generation sometimes limits the usefulness of pressure wave analysis for near field pipeline diagnostics. In this regard, acoustic reflectometry performs well for near field analysis. However, the implicit requirement of an intrusive acoustic source limits mainstream adoption in pipelines. To mitigate this problem, a non-intrusive approach to acoustic wave analysis in a pipeline is introduced.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"121 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113991843","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":"[ACIRS 2020 Front matter]","authors":"","doi":"10.1109/acirs49895.2020.9162623","DOIUrl":"https://doi.org/10.1109/acirs49895.2020.9162623","url":null,"abstract":"","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115713043","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}
E. Sita, Trygve Thomessen, A. Pipe, M. Studley, F. Dailami
{"title":"Usability Study of a Robot Companion for Monitoring Industrial Processes","authors":"E. Sita, Trygve Thomessen, A. Pipe, M. Studley, F. Dailami","doi":"10.1109/ACIRS49895.2020.9162607","DOIUrl":"https://doi.org/10.1109/ACIRS49895.2020.9162607","url":null,"abstract":"In this paper we present the findings of a usability study for a monitoring robotic unit tele-operated via a virtual fixtures (VF) based control framework. The study aims at investigating the impact of VF on the robot navigation as well as the impact of multimodal feedback on the user performance in a static inspection task. The findings will help in the design of the monitoring control framework to inspect a robotised welding process, as it has been researched in previous work. The study has been conducted with untrained participants, involved in four different test scenarios. The experiments treated a static case in which users were asked to navigate the monitoring robot in the workspace to find a lit LED of a test-piece. The statistical analysis of the experiment metrics showed a positive impact of the VF control on the navigation of the monitoring robot even for users with no previous experience. Moreover, from the analysis of the task load index forms (TLX) it emerged that the combination of VF control and additional multimodal feedback improved the user performance without negatively impacting the effort required to accomplish the task.","PeriodicalId":293428,"journal":{"name":"2020 5th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116952583","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}