2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)最新文献_第2页

A Robust Client-Server Architecture for Map Information Processing and Transmission for Distributed Visual SLAM 分布式可视化SLAM中地图信息处理与传输的鲁棒客户机-服务器体系结构

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932869

Jintae Kim, Youngmin Kim, Natnael S. Zewge, Jong-Hwan Kim

引用次数: 1

Emerging UAV Applications in Agriculture 新兴无人机在农业中的应用

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932853

Lebsework Negash, Ho-Yeon Kim, Han-Lim Choi

引用次数: 12

Cross-Domain Knowledge Transfer for Incremental Deep Learning in Facial Expression Recognition 面向面部表情识别增量深度学习的跨领域知识转移

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932731

Nehemia Sugianto, D. Tjondronegoro

{"title":"Cross-Domain Knowledge Transfer for Incremental Deep Learning in Facial Expression Recognition","authors":"Nehemia Sugianto, D. Tjondronegoro","doi":"10.1109/RITAPP.2019.8932731","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932731","url":null,"abstract":"For robotics and AI applications, automatic facial expression recognition can be used to measure user’s satisfaction on products and services that are provided through the human-computer interactions. Large-scale datasets are essentially required to construct a robust deep learning model, which leads to increased training computation cost and duration. This requirement is of particular issue when the training is supposed to be performed on an ongoing basis in devices with limited computation capacity, such as humanoid robots. Knowledge transfer has become a commonly used technique to adapt existing models and speed-up training process by supporting refinements on the existing parameters and weights for the target task. However, most state-of-the-art facial expression recognition models are still based on a single stage training (train at once), which would not be enough for achieving a satisfactory performance in real world scenarios. This paper proposes a knowledge transfer method to support learning using cross-domain datasets, from generic to specific domain. The experimental results demonstrate that shorter and incremental training using smaller-gap-domain from cross-domain datasets can achieve a comparable performance to training using a single large dataset from the target domain.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"68 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":"121256342","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

Circumscribed Douglas-Peucker Polygonal Approximation for Curvilinear Obstacle Representation 曲线障碍表示的限定Douglas-Peucker多边形近似

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932794

Jin-Woo Jung, Byung-Chul So, Jin-Gu Kang, Woo-Jin Jang

{"title":"Circumscribed Douglas-Peucker Polygonal Approximation for Curvilinear Obstacle Representation","authors":"Jin-Woo Jung, Byung-Chul So, Jin-Gu Kang, Woo-Jin Jang","doi":"10.1109/RITAPP.2019.8932794","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932794","url":null,"abstract":"ECD (Exact Cell Decomposition) based path planning is not applicable in curvilinear obstacles environment. Therefore, after the curvilinear obstacles are approximated to the polygons by using DP (Douglas-Peucker) algorithm, which is a polygon approximation algorithm, the ECD method is applied. However, there is a case of not including all the existing obstacles' area and ignoring the outer area, when it comes to the curvilinear obstacles, approximated to the polygons by using the DP algorithm. In this case, path planning of ECD method cannot guarantee the clearance. This paper proposes a CDP (Circumscribed DP) algorithm to solve this problem. The CDP algorithm has a disadvantage of having more inner area than the DP algorithm, but it can guarantee the clearance because of the fact the algorithm always has 0(%) of outer area (OA). In order to confirm this, the polygonal approximation of DP and CDP algorithms was compared in the same curvilinear obstacles and the result was as the following: When each ε value is 0.05, 0.08, 0.11(m), each result of the inner area ratio (IA) was 2.45, 4.89, 7.19(%) by DP algorithm, 16.3, 18.39, 32.58(%) by CDP algorithm, and result of the outer area ratio (OA) was 0.7, 1.17, 1.54(%) by DP Algorithm, 0, 0, 0(%) by CDP Algorithm. Also, it can be confirmed that the CDP algorithm has always guaranteed for clearance.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"325 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":"116533940","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: 3

Integrated Platform for Understanding Physical Prior & Task Learning 理解物理先验与任务学习的集成平台

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932889

Namrata Sharma, Chang Hwa Lee, Sang Wan Lee

引用次数: 0

RiTA 2019 Title Page 《丽塔2019》

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/ritapp.2019.8932897

引用次数: 0

Robot Social Emotional Development through Memory Retrieval* 通过记忆检索的机器人社会情感发展*

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932912

Ha-Duong Bui, Thi Le Quyen Dang, N. Chong

{"title":"Robot Social Emotional Development through Memory Retrieval*","authors":"Ha-Duong Bui, Thi Le Quyen Dang, N. Chong","doi":"10.1109/RITAPP.2019.8932912","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932912","url":null,"abstract":"Robot emotion representation is gaining increasing attention to facilitate long-term human-robot interaction (HRI) in recent years. In particular, human-like robot emotion elicited through HRI is of great use in creating trust between humans and robots. In attempting to represent robot emotions that lead to gaining social acceptance, psychological studies of human emotion have been extensively performed. Among the various factors that affect the way people express their emotional competencies, we conjecture that two factors, social interaction and experience, can be considered important to elicit human emotions, and therefore can be used to represent robot emotions. We believe that social and developmental interaction paradigms, such as social sharing and social referencing, can shape robot emotions toward promoting social acceptance. Besides, the robot’s previous experience can be a key factor contributing to robot personality formation and development. In this paper, we not only focus on the modeling of two eliciting factors affecting the formation of robot emotion but also examine the decline of memory retention over time. Specifically, the relationship between emotion and memory is investigated to design a filter for the memory consolidation process and memory forgetting mechanism. The mechanism is used to enhance robot memory performance based on emotional salience and time parameters. Experiments were performed with a humanoid robot Pepper having verbal and non-verbal interactions with 24 human subjects. Participants rate their perception of the robot in terms of human-likeness, likeability, safety, and emotional expressions through a questionnaire. The results showed that most of the participants enjoyed interacting with the robot and they wished they could have more interactions in the future. They perceived safety and responded favorably toward the robot emotional expressions.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","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":"130077348","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

Dynamic Peloton Formation Configuration Algorithm of Swarm Robots for Aerodynamic Effects Optimization 面向气动效果优化的群体机器人动态队形配置算法

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932871

R. Bedruz, Jose Martin Z. Maningo, A. Fernando, A. Bandala, R. R. Vicerra, E. Dadios

引用次数: 3

Multi-channel Classification Resonance Network* 多通道分类共振网络*

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932859

Joonhyuk Kim, Gyeong-Moon Park, Jong-Hwan Kim

引用次数: 0

D-ALICE: Domain Adaptation-based Labeling the human In Cartoon imagE D-ALICE:基于领域适应的卡通形象人类标记

2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA) Pub Date : 2019-11-01 DOI: 10.1109/RITAPP.2019.8932847

Hyungho Kim, Hyeon Cho, O. Choi, Wonjun Hwang

{"title":"D-ALICE: Domain Adaptation-based Labeling the human In Cartoon imagE","authors":"Hyungho Kim, Hyeon Cho, O. Choi, Wonjun Hwang","doi":"10.1109/RITAPP.2019.8932847","DOIUrl":"https://doi.org/10.1109/RITAPP.2019.8932847","url":null,"abstract":"How did Alice, who went to the Wonderland, solve the problems? In this paper, as Alice solved problems by changing the size of her body in the Wonderland, we classified the person by changing the style using the image translation technique for the cartoon image in pretrained segmentation model. In general, when you test a cartoon image on a pretrained segmentation model based on real image, the results do not appear correctly. To solve this problem, the ground truth for new images should be created and newly trained. This approach is costly and time consuming. So, we propose a method based on domain adaptation to label the human in cartoon image (D-ALICE) without training a new segmentation model by transforming images using a CycleGAN-based model that can be trained with an unpaired dataset. The quantitative and qualitative evaluation of pre and post conversion images resulted from the segmentation model trained as MIT ADE20K were conducted, and the mean-IoU was increased by more than 35%. The results of this research can be applied to other domains without newly training the deep learning model, and furthermore it can help to provide the ground truth for the data which does not have ground truth which does not have before.","PeriodicalId":234023,"journal":{"name":"2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA)","volume":"5 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":"125324265","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