{"title":"Validating the use of off-the-shelf sensors for biometric data collection in affective computing","authors":"Liz Felton, Pamela A. Hardaker, Yingjie Yang","doi":"10.31256/zy6yv5z","DOIUrl":"https://doi.org/10.31256/zy6yv5z","url":null,"abstract":"","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124972862","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":"Visually-based Prediction of Artist’s Drawing","authors":"Chipp Jansen, E. Sklar","doi":"10.31256/rq9yg6i","DOIUrl":"https://doi.org/10.31256/rq9yg6i","url":null,"abstract":"","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125271850","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}
M. Khalid, Leonardo Guevara, Marc Hanheide, Simon Parsons
—This paper describes our work to assure safe autonomy in soft fruit production. The first step was hazard analysis, where all the possible hazards in representative scenarios were identified. Following this analysis, a three-layer safety architecture was identified that will minimise the occurrence of the identified hazards. Most of the hazards are minimised by upper layers, while unavoidable hazards are handled using emergency stops. In parallel, we are using probabilistic model checking to check the probability of a hazard’s occurrence. The results from the model checking will be used to improve safety system architecture
{"title":"Assuring autonomy of robots in soft fruit production","authors":"M. Khalid, Leonardo Guevara, Marc Hanheide, Simon Parsons","doi":"10.31256/ml6ik7g","DOIUrl":"https://doi.org/10.31256/ml6ik7g","url":null,"abstract":"—This paper describes our work to assure safe autonomy in soft fruit production. The first step was hazard analysis, where all the possible hazards in representative scenarios were identified. Following this analysis, a three-layer safety architecture was identified that will minimise the occurrence of the identified hazards. Most of the hazards are minimised by upper layers, while unavoidable hazards are handled using emergency stops. In parallel, we are using probabilistic model checking to check the probability of a hazard’s occurrence. The results from the model checking will be used to improve safety system architecture","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130721216","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}
M. Abadi, Mohammad Alashti, Patrick Holthaus, Catherine Menon, F. Amirabdollahian
{"title":"Affordable Robot Mapping using Omnidirectional Vision","authors":"M. Abadi, Mohammad Alashti, Patrick Holthaus, Catherine Menon, F. Amirabdollahian","doi":"10.31256/if7nm5z","DOIUrl":"https://doi.org/10.31256/if7nm5z","url":null,"abstract":"","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121960403","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}
A common approach to the problem of fruit detection in images is to design a deep learning network and train a model to locate objects, using bounding boxes to identify regions containing fruit. However, this requires sufficient data and presents challenges for small datasets. Transfer learning, which acquires knowledge from a source domain and brings that to a new target domain, can produce improved performance in the target domain. The work discussed in this paper shows the application of transfer learning for fruit detection with small datasets and presents analysis between the number of training images in source and target domains. This investigation is based on three datasets: two containing tomatoes and one containing strawberries. Experimental results indicate that transfer learning can enhance prediction with limited data.
{"title":"Small datasets for fruit detection with transfer learning.","authors":"Dan Dai, Junfeng Gao, Simon Parsons, E. Sklar","doi":"10.31256/nf6uh8q","DOIUrl":"https://doi.org/10.31256/nf6uh8q","url":null,"abstract":"A common approach to the problem of fruit detection in images is to design a deep learning network and train a model to locate objects, using bounding boxes to identify regions containing fruit. However, this requires sufficient data and presents challenges for small datasets. Transfer learning, which acquires knowledge from a source domain and brings that to a new target domain, can produce improved performance in the target domain. The work discussed in this paper shows the application of transfer learning for fruit detection with small datasets and presents analysis between the number of training images in source and target domains. This investigation is based on three datasets: two containing tomatoes and one containing strawberries. Experimental results indicate that transfer learning can enhance prediction with limited data.","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121845980","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":"Using Plan Libraries for Improved Plan Execution","authors":"I. Moraru, Gerard Canal, Simon Parsons","doi":"10.31256/ts2po9m","DOIUrl":"https://doi.org/10.31256/ts2po9m","url":null,"abstract":"","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130961831","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":"Towards Localisation of Remote Centre of Motion and Trocar in Vitreoretinal Surgery","authors":"J. Birch, K. Rhode, C. Bergeles, L. Cruz","doi":"10.31256/qv4tp7h","DOIUrl":"https://doi.org/10.31256/qv4tp7h","url":null,"abstract":"","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128933576","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}
Multi-robot task allocation mechanisms are de-signed to distribute a set of activities fairly amongst a set of robots. Frequently, this can be framed as a multi-criteria optimisation problem, for example minimising cost while maximising rewards. In soft fruit farms, tasks, such as picking ripe fruit at harvest time, are assigned to human labourers. The work presented here explores the application of multi-robot task allocation mechanisms to the complex problem of managing a heterogeneous workforce to undertake activities associated with harvesting soft fruit.
{"title":"Auction-based Task Allocation Mechanisms for Managing Fruit Harvesting Tasks","authors":"Helen Harman, E. Sklar","doi":"10.31256/DG2ZP9Q","DOIUrl":"https://doi.org/10.31256/DG2ZP9Q","url":null,"abstract":"Multi-robot task allocation mechanisms are de-signed to distribute a set of activities fairly amongst a set of robots. Frequently, this can be framed as a multi-criteria optimisation problem, for example minimising cost while maximising rewards. In soft fruit farms, tasks, such as picking ripe fruit at harvest time, are assigned to human labourers. The work presented here explores the application of multi-robot task allocation mechanisms to the complex problem of managing a heterogeneous workforce to undertake activities associated with harvesting soft fruit.","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134269293","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}
— To facilitate long-term engagement with social robots, robots can be modelled on ‘successful’ social animals – specifically, pet dogs. Unfortunately, scientific understanding is limited to qualities of dogs that are ‘liked’, opposed to behaviours that facilitate and maintain the human-dog bond. To better understand dog behaviours that are important for building bonds between owner and pet, we collected open-ended responses from dog owners (n=153). Thematic analysis identified 7 behaviour categories: the importance of 1) attunement, 2) communication, 3) consistency and predictability, 4) physical affection, 5) positivity and enthusiasm, 6) proximity, and 7) shared activities. We consider the feasibility of translating dog behaviours into a robotic platform, and potential barriers moving forward. In addition to providing insight into important behaviours for human-dog bonding, this work provides a springboard for those hoping to implement dog behaviours into animal-like agents, avatars, and robots.
{"title":"Exploring Behaviours Percieved as Important to the Human-Dog Bond and their Translation to a Robotic Platform","authors":"K. Riddoch, R. Hawkins, Emily S. Cross","doi":"10.31256/pm5de6c","DOIUrl":"https://doi.org/10.31256/pm5de6c","url":null,"abstract":"— To facilitate long-term engagement with social robots, robots can be modelled on ‘successful’ social animals – specifically, pet dogs. Unfortunately, scientific understanding is limited to qualities of dogs that are ‘liked’, opposed to behaviours that facilitate and maintain the human-dog bond. To better understand dog behaviours that are important for building bonds between owner and pet, we collected open-ended responses from dog owners (n=153). Thematic analysis identified 7 behaviour categories: the importance of 1) attunement, 2) communication, 3) consistency and predictability, 4) physical affection, 5) positivity and enthusiasm, 6) proximity, and 7) shared activities. We consider the feasibility of translating dog behaviours into a robotic platform, and potential barriers moving forward. In addition to providing insight into important behaviours for human-dog bonding, this work provides a springboard for those hoping to implement dog behaviours into animal-like agents, avatars, and robots.","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127330418","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}
Leonardo Guevara, M. Khalid, Marc Hanheide, Simon Parsons
—This paper describes a hazard analysis for an agricultural scenario where a crop is treated by a robot using UV-C light. Although human-robot interactions are not expected, it may be the case that unauthorized people approach the robot while it is operating. These potential human-robot interactions have been identified and modeled as Markov Decision Processes (MDP) and tested in the model checking tool PRISM.
{"title":"Assessing the probability of human injury during UV-C treatment of crops by robots","authors":"Leonardo Guevara, M. Khalid, Marc Hanheide, Simon Parsons","doi":"10.31256/pj6cz2l","DOIUrl":"https://doi.org/10.31256/pj6cz2l","url":null,"abstract":"—This paper describes a hazard analysis for an agricultural scenario where a crop is treated by a robot using UV-C light. Although human-robot interactions are not expected, it may be the case that unauthorized people approach the robot while it is operating. These potential human-robot interactions have been identified and modeled as Markov Decision Processes (MDP) and tested in the model checking tool PRISM.","PeriodicalId":447290,"journal":{"name":"UKRAS21 Conference: Robotics at home Proceedings","volume":"247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122078785","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：