2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)最新文献_第5页

Building specific contexts for on-line learning of dynamical tasks through non-verbal interaction 通过非语言互动建立动态任务在线学习的特定语境

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-11-04 DOI: 10.1109/DEVLRN.2013.6652564

A. D. Rengervé, Souheil Hanoune, P. Andry, M. Quoy, P. Gaussier

引用次数: 1

The significance of social input, early motion experiences, and attentional selection 社会输入、早期运动经验和注意选择的意义

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-11-04 DOI: 10.1109/DEVLRN.2013.6652556

Joseph M. Burling, Hanako Yoshida, Y. Nagai

引用次数: 2

Frustration as a way toward autonomy and self-improvement in robotic navigation 挫折是机器人导航走向自主和自我完善的一种方式

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-11-04 DOI: 10.1109/DEVLRN.2013.6652540

Adrien Jauffret, Marwen Belkaid, N. Cuperlier, P. Gaussier, P. Tarroux

{"title":"Frustration as a way toward autonomy and self-improvement in robotic navigation","authors":"Adrien Jauffret, Marwen Belkaid, N. Cuperlier, P. Gaussier, P. Tarroux","doi":"10.1109/DEVLRN.2013.6652540","DOIUrl":"https://doi.org/10.1109/DEVLRN.2013.6652540","url":null,"abstract":"Autonomy and self-improvement capabilities are still challenging in the field of robotics. Allowing a robot to autonomously navigate in wide and unknown environments not only requires a set of robust strategies to cope with miscellaneous situations, but also needs mechanisms of self-assessment for guiding learning and for monitoring strategies. Monitoring strategies requires feedbacks on the behavior's quality, from a given fitness system in order to take correct decisions. In this work, we focus on how an emotional controller can be used to modulate robot behaviors. Following an incremental and constructivist approach, we present a generic neural architecture, based on an online novelty detection algorithm that may be able to evaluate any sensory-motor strategies. This architecture learns contingencies between sensations and actions, giving the expected sensation from the past perception. Prediction error, coming from surprising events, provides a direct measure of the quality of the underlying sensory-motor contingencies involved. We show how a simple emotional controller based on the prediction progress allows the system to regulate its behavior to solve complex navigation tasks and to communicate its disability in deadlock situations. We propose that this model could be a key structure toward self-monitoring. We made several experiments that can account for such properties with different behaviors (road following and place cells based navigation).","PeriodicalId":106997,"journal":{"name":"2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906341","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

Learning semantic components from subsymbolic multimodal perception 从亚符号多模态感知中学习语义成分

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-18 DOI: 10.1109/DEVLRN.2013.6652563

Olivier Mangin, Pierre-Yves Oudeyer

引用次数: 29

Autonomous reuse of motor exploration trajectories 运动探索轨迹的自主重用

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-18 DOI: 10.1109/DEVLRN.2013.6652567

Fabien C. Y. Benureau, Pierre-Yves Oudeyer

引用次数: 5

A generative probabilistic framework for learning spatial language 空间语言学习的生成概率框架

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-01 DOI: 10.1109/DEVLRN.2013.6652560

C. Dawson, Jeremy B. Wright, Antons Rebguns, M. Valenzuela-Escarcega, Daniel Fried, P. Cohen

引用次数: 19

Extracting image features in static images for depth estimation 在静态图像中提取图像特征进行深度估计

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-01 DOI: 10.1109/DEVLRN.2013.6652551

M. Ogino, Junji Suzuki, M. Asada

引用次数: 0

Aquila 2.0 software architecture for cognitive robotics 认知机器人的Aquila 2.0软件架构

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-01 DOI: 10.1109/DEVLRN.2013.6652565

M. Peniak, Anthony F. Morse, A. Cangelosi

引用次数: 5

Emergence of flexible prediction-based discrete decision making and continuous motion generation through actor-Q-learning 基于柔性预测的离散决策和通过actor- q学习的连续运动生成的出现

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-01 DOI: 10.1109/DEVLRN.2013.6652559

K. Shibata, Kenta Goto

{"title":"Emergence of flexible prediction-based discrete decision making and continuous motion generation through actor-Q-learning","authors":"K. Shibata, Kenta Goto","doi":"10.1109/DEVLRN.2013.6652559","DOIUrl":"https://doi.org/10.1109/DEVLRN.2013.6652559","url":null,"abstract":"In this paper, the authors first point the importance of three factors for filling the gap between humans and robots in the flexibility in the real world. Those are (1)parallel processing, (2)emergence through learning and solving “what” problems, and (3)abstraction and generalization on the abstract space. To explore the possibility of human-like flexibility in robots, a prediction-required task in which an agent (robot) gets a reward by capturing a moving target that sometimes becomes invisible was learned by reinforcement learning using a recurrent neural network. Even though the agent did not know in advance that “prediction is required” or “what information should be predicted”, appropriate discrete decision making, in which `capture' or `move' was chosen, and also continuous motion generation in two-dimensional space, could be acquired. Furthermore, in this task, the target sometimes changed its moving direction randomly when it became visible again from invisible state. Then the agent could change its moving direction promptly and appropriately without introducing any special architecture or technique. Such emergent property is what general parallel processing systems such as Subsumption architecture do not have, and the authors believe it is a key to solve the “Frame Problem” fundamentally.","PeriodicalId":106997,"journal":{"name":"2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127952319","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: 15

Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot 学习识别物体通过好奇心驱动操作与iCub人形机器人

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL) Pub Date : 2013-08-01 DOI: 10.1109/DEVLRN.2013.6652525

S. Nguyen, S. Ivaldi, Natalia Lyubova, Alain Droniou, Damien Gérardeaux-Viret, David Filliat, V. Padois, Olivier Sigaud, Pierre-Yves Oudeyer

{"title":"Learning to recognize objects through curiosity-driven manipulation with the iCub humanoid robot","authors":"S. Nguyen, S. Ivaldi, Natalia Lyubova, Alain Droniou, Damien Gérardeaux-Viret, David Filliat, V. Padois, Olivier Sigaud, Pierre-Yves Oudeyer","doi":"10.1109/DEVLRN.2013.6652525","DOIUrl":"https://doi.org/10.1109/DEVLRN.2013.6652525","url":null,"abstract":"In this paper we address the problem of learning to recognize objects by manipulation in a developmental robotics scenario. In a life-long learning perspective, a humanoid robot should be capable of improving its knowledge of objects with active perception. Our approach stems from the cognitive development of infants, exploiting active curiosity-driven manipulation to improve perceptual learning of objects. These functionalities are implemented as perception, control and active exploration modules as part of the Cognitive Architecture of the MACSi project. In this paper we integrate these functionalities into an active perception system which learns to recognise objects through manipulation. Our work in this paper integrates a bottom-up vision system, a control system of a complex robot system and a top-down interactive exploration method, which actively chooses an exploration method to collect data and whether interacting with humans is profitable or not. Experimental results show that the humanoid robot iCub can learn to recognize 3D objects by manipulation and in interaction with teachers by choosing the adequate exploration strategy to enhance competence progress and by focusing its efforts on the most complex tasks. Thus the learner can learn interactively with humans by actively self-regulating its requests for help.","PeriodicalId":106997,"journal":{"name":"2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131943364","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: 33