2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)最新文献_第3页

The Sound of Actuators: Disturbance in Human - Robot Interactions? 致动器的声音:人-机器人交互中的干扰?

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850697

Mélanie Jouaiti, P. Hénaff

{"title":"The Sound of Actuators: Disturbance in Human - Robot Interactions?","authors":"Mélanie Jouaiti, P. Hénaff","doi":"10.1109/DEVLRN.2019.8850697","DOIUrl":"https://doi.org/10.1109/DEVLRN.2019.8850697","url":null,"abstract":"Human-Robot interactions promise to increase as robots become more pervasive. One important aspect is gestural communication which is quite popular in rehabilitation and therapeutic robotics. Indeed, synchrony is a key component of interpersonal interactions which affects the interaction on the behavioural level, as well as on the social level. When interacting physically with a robot, one perceives the robot movements but robot actuators also produce sound. In this work, we wonder whether the sound of actuators can hamper human coordination in human-robot rhythmic interactions. Indeed, the human brain processes the auditory input in priority compared to the visual input. This property can sometimes be so powerful so as to alter or even remove the visual perception. However, under given circumstances, the auditory signal and the visual perception can reinforce each other. In this paper, we propose a study where participants were asked to perform a waving-like gesture back at a robot in three different conditions: with visual perception only, auditory perception only and both perceptions. We analyze coordination performance and focus of gaze in each condition. Results show that the combination of visual and auditory perceptions perturbs the rhythmic interaction.","PeriodicalId":318973,"journal":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123987756","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

Robotic Interactive Physics Parameters Estimator (RIPPE) 机器人交互物理参数估计器(RIPPE)

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850710

Atabak Dehban, Carlos Cardoso, Pedro Vicente, A. Bernardino, J. Santos-Victor

引用次数: 1

Musculoskeletal Bias on Infant Sensorimotor Development Driven by Predictive Learning 预测学习驱动下婴儿感觉运动发展的肌肉骨骼偏差

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850722

Kaoruko Higuchi, Hoshinori Kanazawa, Yuma Suzuki, Keiko Fujii, Y. Kuniyoshi

引用次数: 0

A Categorization of Reinforcement Learning Exploration Techniques which Facilitates Combination of Different Methods 促进不同方法组合的强化学习探索技术分类

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850685

Bjørn Ivar Teigen, K. Ellefsen, J. Tørresen

引用次数: 0

Sensorimotor Cross-Behavior Knowledge Transfer for Grounded Category Recognition 基于类别识别的感觉运动跨行为知识转移

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850715

Gyan Tatiya, Ramtin Hosseini, M. C. Hughes, J. Sinapov

{"title":"Sensorimotor Cross-Behavior Knowledge Transfer for Grounded Category Recognition","authors":"Gyan Tatiya, Ramtin Hosseini, M. C. Hughes, J. Sinapov","doi":"10.1109/DEVLRN.2019.8850715","DOIUrl":"https://doi.org/10.1109/DEVLRN.2019.8850715","url":null,"abstract":"Humans use exploratory behaviors coupled with multi-modal perception to learn about the objects around them. Research in robotics has shown that robots too can use such behaviors (e.g., grasping, pushing, shaking) to infer object properties that cannot always be detected using visual input alone. However, such learned representations are specific to each individual robot and cannot be directly transferred to another robot with different actions, sensors, and morphology. To address this challenge, we propose a framework for knowledge transfer across different behaviors and modalities that enables a source robot to transfer knowledge about objects to a target robot that has never interacted with them. The intuition behind our approach is that if two robots interact with a shared set of objects, the produced sensory data can be used to learn a mapping between the two robots' feature spaces. We evaluate the framework on a category recognition task using a dataset containing 9 robot behaviors performed multiple times on a set of 100 objects. The results show that the proposed framework can enable a target robot to perform category recognition on a set of novel objects and categories without the need to physically interact with the objects to learn the categorization model.","PeriodicalId":318973,"journal":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116514510","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: 6

Babbling elicits simplified caregiver speech: Findings from natural interaction and simulation 咿呀学语引出简化的照顾者语言:来自自然互动和模拟的发现

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850677

Steven L. Elmlinger, J. Schwade, M. Goldstein

{"title":"Babbling elicits simplified caregiver speech: Findings from natural interaction and simulation","authors":"Steven L. Elmlinger, J. Schwade, M. Goldstein","doi":"10.1109/DEVLRN.2019.8850677","DOIUrl":"https://doi.org/10.1109/DEVLRN.2019.8850677","url":null,"abstract":"What is the function of babbling in language learning? Our recent findings suggest that infants' immature vocalizations may elicit simplified linguistic responses from their caregivers. The contributions of parental speech to infant development are well established; individual differences in the number of words in infants' ambient language environment predict communicative and cognitive development. It is unclear whether the number or the diversity of words in infants' environments is more critical for understanding infant language development. We present a new solution that observes the relation between the total number of words (tokens) and the diversity of words in infants' environments. Comparing speech corpora containing different numbers of tokens is challenging because the number of tokens strongly influences measures of corpus word diversity. However, here we offer a method for minimizing the effects of corpus size by deriving control samples of words and comparing them to test samples. We find that parents' speech in response to infants' babbling is simpler in that it contains fewer word types; our estimates based on sampling also suggest simplification of word diversity with larger numbers of tokens. Thus, infants, via their immature vocalizations, elicit speech from caregivers that is easier to learn.","PeriodicalId":318973,"journal":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128907434","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

The role of object motion in visuo-haptic exploration during development 发展过程中物体运动在视触觉探索中的作用

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850687

A. Sciutti, G. Sandini

引用次数: 5

Looking Back and Ahead: Adaptation and Planning by Gradient Descent 回顾与展望:梯度下降法的适应与规划

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850693

Shingo Murata, Hiroki Sawa, S. Sugano, T. Ogata

{"title":"Looking Back and Ahead: Adaptation and Planning by Gradient Descent","authors":"Shingo Murata, Hiroki Sawa, S. Sugano, T. Ogata","doi":"10.1109/DEVLRN.2019.8850693","DOIUrl":"https://doi.org/10.1109/DEVLRN.2019.8850693","url":null,"abstract":"Adaptation and planning are crucial for both biological and artificial agents. In this study, we treat these as an inference problem that we solve using a gradient-based optimization approach. We propose adaptation and planning by gradient descent (APGraDe), a gradient-based computational framework with a hierarchical recurrent neural network (RNN) for adaptation and planning. This framework computes (counterfactual) prediction errors by looking back on past situations based on actual observations and by looking ahead to future situations based on preferred observations (or goal). The internal state of the higher level of the RNN is optimized in the direction of minimizing these errors. The errors for the past contribute to the adaptation while errors for the future contribute to the planning. The proposed APGraDe framework is implemented in a humanoid robot and the robot performs a ball manipulation task with a human experimenter. Experimental results show that given a particular preference, the robot can adapt to unexpected situations while pursuing its own preference through the planning of future actions.","PeriodicalId":318973,"journal":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133742064","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

Motor Coordination Learning for Rhythmic Movements 韵律运动的运动协调学习

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850678

Mélanie Jouaiti, P. Hénaff

引用次数: 2

A Cognitive Architecture for Socially Adaptable Robots 社会适应性机器人的认知架构

2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2019-08-01 DOI: 10.1109/DEVLRN.2019.8850688

Ana Tanevska, F. Rea, G. Sandini, Lola Cañamero, A. Sciutti

引用次数: 14