2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)最新文献_第6页

Developing neural networks with neurons competing for survival 发展神经元竞争生存的神经网络

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346133

Zhen Peng, Daniel A. Braun

引用次数: 0

A biologically inspired approach to learning spatio-temporal patterns 学习时空模式的生物学启发方法

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346159

Banafsheh Rekabdar, M. Nicolescu, M. Nicolescu, Richard Kelley

引用次数: 3

Learning to pick up objects through active exploration 通过主动探索学习捡起物品

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346151

John G. Oberlin, Stefanie Tellex

{"title":"Learning to pick up objects through active exploration","authors":"John G. Oberlin, Stefanie Tellex","doi":"10.1109/DEVLRN.2015.7346151","DOIUrl":"https://doi.org/10.1109/DEVLRN.2015.7346151","url":null,"abstract":"Robots need to perceive and manipulate objects in their environment, yet robust object manipulation remains a challenging problem. Many aspects of a perception and manipulation system need to be customized for a particular object and environment, such as where to grasp an object, what algorithm to use for segmentation, and at which height to visually servo above an object on the table. To address these limitations, we propose an approach for enabling a robot to learn about objects through active exploration and adapt its grasping model accordingly. We frame the problem of model adaptation as a bandit problem, specifically the identification of the best of the arms of an N-armed bandit, [5] where the robot aims to minimize simple regret after a finite exploration period [1]. Our robot can obtain a high-quality reward signal (although sometimes at a higher cost in time and sensing) by actively collecting additional information from the environment, and use this reward signal to adaptively identify grasp points that are likely to succeed. This paper provides an overview of our previous work [3] using this approach to actively infer grasp points and adds a description of our efforts learning the height at which to servo to an object.","PeriodicalId":164756,"journal":{"name":"2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117145256","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

The dynamics of idealized attention in complex learning environments 复杂学习环境中理想化注意力的动态

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346147

Madeline Pelz, S. Piantadosi, Celeste Kidd

引用次数: 4

First steps towards the development of the sense of object permanence in robots 这是机器人物体永恒感发展的第一步

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346157

Sarah Bechtle, G. Schillaci, V. Hafner

引用次数: 3

Modeling infant visual preference as perceptual oscillation 婴儿视觉偏好的知觉振荡模型

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7345451

B. Balas, L. Oakes

{"title":"Modeling infant visual preference as perceptual oscillation","authors":"B. Balas, L. Oakes","doi":"10.1109/DEVLRN.2015.7345451","DOIUrl":"https://doi.org/10.1109/DEVLRN.2015.7345451","url":null,"abstract":"Infants' visual recognition abilities are typically studied using variations of preferential looking paradigms. In this broad class of tasks, the extent to which infants discriminate between, categorize, and recognize complex images is determined by which of two test images they prefer to look at. This preference is usually expressed by calculating the proportion of total looking time allocated to a target stimulus (e.g., the stimulus that is more novel) on each trial. Although this coarse description of infant looking behavior has been sufficient to reveal a wide range of important effects, it also potentially obscures great deal of important visual behavior. As a result, we know less about changes in infant looking over learning and development than we would if visual behavior were measured in other ways. We argue that deeper understanding of learning and development of infants' visual behavior requires appreciation of the dynamics of that behavior: During any individual trial, infants look back and forth between stimuli several times. These oscillations between stimuli may reflect aspects of visual processing that have been heretofore overlooked. We suggest that modeling the distribution of look durations made across trials provides a rich description of looking behavior that makes it possible to approach preferential looking as a form of perceptual oscillation, and may provide additional understanding into learning and development. Here we show how fitting the parameters of a gamma distribution to infants' look durations in a face recognition task allows us to see effects that are not evident when simpler descriptors are used and discuss how this approach supports the interpretation of infant behavioral data in the context of neural models of visual competition.","PeriodicalId":164756,"journal":{"name":"2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115524467","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

Comparison of absolute and relative strategies to encode sensorimotor transformations in tool-use 工具使用中感觉运动转换编码的绝对策略和相对策略的比较

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346154

R. Braud, Alexandre Pitti, P. Gaussier

引用次数: 2

Mastering human-robot interaction control techniques using Chinese Tai Chi Chuan: Mutual learning, intention detection, impedance adaptation, and force borrowing 掌握中国太极拳人机交互控制技术:相互学习、意图检测、阻抗适应和力的借用

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346123

Ker-Jiun Wang, Mingui Sun, Lan Zhang, Zhihong Mao

引用次数: 1

COSMO, a Bayesian computational model of speech communication: Assessing the role of sensory vs. motor knowledge in speech perception 语言交流的贝叶斯计算模型:评估感觉与运动知识在语言感知中的作用

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346149

Marie-Lou Barnaud, J. Diard, P. Bessière, J. Schwartz

引用次数: 3

Use of speech and motion cues for bootstrapping complex action learning in iCub 在iCub中使用语音和动作提示引导复杂动作学习

2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2015-08-01 DOI: 10.1109/DEVLRN.2015.7346119

Emre Ugur, Jimmy Baraglia, Lars Schillingmann, Y. Nagai

{"title":"Use of speech and motion cues for bootstrapping complex action learning in iCub","authors":"Emre Ugur, Jimmy Baraglia, Lars Schillingmann, Y. Nagai","doi":"10.1109/DEVLRN.2015.7346119","DOIUrl":"https://doi.org/10.1109/DEVLRN.2015.7346119","url":null,"abstract":"Parental scaffolding is an important mechanism that speeds up infant sensorimotor development. Infants pay stronger attention to the features of the objects highlighted by parents, and their skills develop earlier than they would in isolation due to caregivers support. Parents are known to make modifications in infant-directed actions, called “motionese”, which is characterized by a wider range of motion, repetitive actions, and longer and more pauses between movements. Inspired from motionese, we previously realized a robotic system [1] where the affordances and effect prediction capabilities that are learned in the previous stages of development are used to bootstrap complex imitation and action learning with the help a cooperative tutor through motionese. With this system, a robot could learn new skills via imitation learning by extracting the important steps from the observed movement trajectory, and then encoding them as subgoals that it can fulfill. Considering the affordances provided by the objects in the environment, it found and sequentially executed the actions that are predicted to generate the desired effects and achieve the subgoals; achieving the overall goal of complete imitation. We showed that motionese can be used to bridge the gap between the interacting agents with different movement capabilities, such as the human tutors and the arm-hand robot we employed. Furthermore, our experimental data indicated that naïve tutors who are not informed about the imitation mechanisms of the robot, changed their teaching strategy, and started to display motionese.","PeriodicalId":164756,"journal":{"name":"2015 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129319273","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