2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)最新文献_第4页

Critical Brain Hypotheses on the Emergence of Cognitive Functions in Simple Circuits for Backward Time Perception 关于回溯时间感知简单回路中认知功能出现的关键脑假说

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761039

M. Hirabayashi, H. Ohashi

{"title":"Critical Brain Hypotheses on the Emergence of Cognitive Functions in Simple Circuits for Backward Time Perception","authors":"M. Hirabayashi, H. Ohashi","doi":"10.1109/DEVLRN.2018.8761039","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761039","url":null,"abstract":"To reveal the cognitive mechanisms is one of challenging problems in various fields of science, such as neuroscience, cognitive science, and artificial intelligence. Focusing on the cognitive mechanisms of time-series events, we present an analysis on the backward time perception with the flash-lag illusion. In the flash-lag experiment, we experience the visual illusion that a stationary flashed object is perceived to lag behind a spatially aligned moving object. When this moving object changes the direction of motion, the time reversing recognition called postdiction is observed. In other words, the postdiction is a phenomenon that the future stimulus affects the present one backward in time. Although several models have been presented to explain this illusion, the neural basis is not clear. Here we propose the assumption that the simple dual-path process in the critical states can provide the backward time perception and other important features of the visual illusion related to the flash-lag experiment. The dual-path process consists of two pathways: a fast-processing pathway and a slow-processing pathway. The backward time perception can occur as a result of the integration of the information from these two pathways. We implemented the dual-path process in the critical state using a simple lattice model and succeeded in the reproduction of the postdictive property and other features of visual illusions related to the flash-lag effect. According to the criticality hypothesis proposed by Beggs, the brain operates in the critical state. If the critical state accelerates the fast pathway and decelerates the slow pathway, simple circuits can provide the complicated cognitive functions. The concept that simple systems can realize advanced functions utilizing the critical states will contribute to the discovery of the fundamental principles of neural mechanisms and the improvement of cognitive functions of artificial intelligence.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115539899","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

Skill Memories for Parameterized Dynamic Action Primitives on the Pneumatically Driven Humanoid Robot Child Affetto 气动仿人机器人子Affetto参数化动态动作原语的技能记忆

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761040

J. Queißer, B. Hammer, H. Ishihara, M. Asada, Jochen J. Steil

引用次数: 5

Multimodal Sensory Representation for Object Classification via Neocortically-inspired Algorithm 基于新皮层启发算法的物体分类多模态感官表征

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761024

M. Kirtay, Lorenzo Vannucci, Ugo Albanese, E. Falotico, C. Laschi

{"title":"Multimodal Sensory Representation for Object Classification via Neocortically-inspired Algorithm","authors":"M. Kirtay, Lorenzo Vannucci, Ugo Albanese, E. Falotico, C. Laschi","doi":"10.1109/DEVLRN.2018.8761024","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761024","url":null,"abstract":"This study reports our initial work on multimodal sensory representation for object classification. To form a sensory representation we used the spatial pooling phase of the Hierarchical Temporal Memory - a Neocortically-inspired algorithm. The classification task was carried out on the Washington RGB-D dataset in which the employed method provides extraction of non-hand engineered representations (or features) from different modalities which are pixel values (RGB) and depth (D) information. These representations, both early and lately fused, were used as inputs to a machine learning algorithm to perform object classification. The obtained results show that using multimodal representations significantly improve (by 5 %) the classification performance compared to a when a single modality is used. The results also indicate that the performed method is effective for multimodal learning and different sensory modalities are complementary for the object classification. Therefore, we envision that this method can be employed for object concept formation that requires multiple sensory information to execute cognitive tasks.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116225403","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

Modeling the Development of Infant Imitation using Inverse Reinforcement Learning 利用逆强化学习对婴儿模仿的发展进行建模

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761045

Ahmet E. Tekden, Emre Ugur, Y. Nagai, Erhan Öztop

{"title":"Modeling the Development of Infant Imitation using Inverse Reinforcement Learning","authors":"Ahmet E. Tekden, Emre Ugur, Y. Nagai, Erhan Öztop","doi":"10.1109/DEVLRN.2018.8761045","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761045","url":null,"abstract":"Little is known about the computational mechanisms of how imitation skills develop along with infant sensorimotor learning. In robotics, there are several well developed frameworks for imitation learning or so called learning by demonstration. Two paradigms dominate: Direct Learning (DL) and Inverse Reinforcement Learning (IRL). The former is a simple mechanism where the observed state and action pairs are associated to construct a copy of the action policy of the demonstrator. In the latter, an optimality principle or reward structure is sought that would explain the observed behavior as the optimal solution governed by the optimality principle or the reward function found. In this study, we explore the plausibility of whether some form of IRL mechanism in infants can facilitate imitation learning and understanding of others' behaviours. We propose that infants project the events taking place in the environment into their internal representations through a set of features that evolve during development. We implement this idea on a grid world environment, which can be considered as a simple model for reaching with obstacle avoidance. The observing infant has to imitate the demonstrator's reaching behavior through IRL by using various set of features that correspond to different stages of development. Our simulation results indicate that the U-shape performance change during imitation development observed in infants can be reproduced with the proposed model.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125722252","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

Which Input Abstraction is Better for a Robot Syntax Acquisition Model? Phonemes, Words or Grammatical Constructions? 哪种输入抽象更适合机器人语法获取模型?音素、单词还是语法结构?

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761025

Xavier Hinaut

{"title":"Which Input Abstraction is Better for a Robot Syntax Acquisition Model? Phonemes, Words or Grammatical Constructions?","authors":"Xavier Hinaut","doi":"10.1109/DEVLRN.2018.8761025","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761025","url":null,"abstract":"There has been a considerable progress these last years in speech recognition systems [13]. The word recognition error rate went down with the arrival of deep learning methods. However, if one uses cloud-based speech API and integrates it inside a robotic architecture [33], one still encounters considerable cases of wrong sentences recognition. Thus speech recognition can not be considered as solved especially when an utterance is considered in isolation of its context. Particular solutions, that can be adapted to different Human-Robot Interaction applications and contexts, have to be found. In this perspective, the way children learn language and how our brains process utterances may help us improve how robot process language. Getting inspiration from language acquisition theories and how the brain processes sentences we previously developed a neuro-inspired model of sentence processing. In this study, we investigate how this model can process different levels of abstractions as input: sequences of phonemes, sequences of words or grammatical constructions. We see that even if the model was only tested on grammatical constructions before, it has better performances with words and phonemes inputs.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880005","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: 7

Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture 基于MaxPain架构的奖惩并行深度强化学习

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761044

Jiexin Wang, Stefan Elfwing, E. Uchibe

{"title":"Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture","authors":"Jiexin Wang, Stefan Elfwing, E. Uchibe","doi":"10.1109/DEVLRN.2018.8761044","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761044","url":null,"abstract":"Traditionally, reinforcement learning treats punishments as negative rewards. However, in biological decision systems, some evidence shows that animals have separate systems for rewards and punishments. The MaxPain architecture parallelizes the predictions of rewards and punishments and scales them into dual-attribute policies, and has been shown to both improve the learning speed and the learning of safer behaviors. This paper extends the MaxPain architecture into a deep reinforcement learning framework using convolutional neural networks to approximate two action-value functions. To derive the behavioral policy, we consider the mixture distributions of the policies computed from the two action-value functions. For evaluation, we compare the MaxPain architecture with count-based exploration and a reward-decomposing structure called Hybrid Reward Architecture (HRA) in grid-world navigation and vision-based navigation in a U-shape maze in the Gazebo robot simulation environment. The simulation results show the superiority of the MaxPain approach over the count-based method because the MaxPain agents efficiently avoid dead-end states by predicting future punishments. In addition, the MaxPain agents learn safe behaviors, while the HRA agents learn similar behaviors, as in the case of no punishments.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126028203","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: 4

Partitioning Sensorimotor Space by Predictability Principle in Intrinsic Motivation Systems 用内在动机系统的可预见性原则划分感觉运动空间

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8760504

M. Sener, Emre Ugur

{"title":"Partitioning Sensorimotor Space by Predictability Principle in Intrinsic Motivation Systems","authors":"M. Sener, Emre Ugur","doi":"10.1109/DEVLRN.2018.8760504","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8760504","url":null,"abstract":"Inspired by infant development, intrinsic motivation (IM) guides the robot with intelligent exploration strategies, enabling efficient and effective learning in high-dimensional search spaces. A particular method in IM, namely Intelligent Adaptive Curiosity (IAC), adaptively partitions agents sensorimotor space $(mathrm{S}mathbb{M})$ into regions of exploration, and guides the agent to select the regions that are in the moderate level of difficulty, and learns separate experts for different regions. Therefore, the means of partitioning the $mathbb{SM}$ and the mechanisms behind region generation is of utmost importance. In this study, we propose a method for partitioning the space that allows maximizing the performances of the experts that will be responsible for learning skills. In brief, for each potential partitioning, the error of the experts are calculated and the partitioning that would generate the minimal error in the future is selected. Our method is evaluated in a setting with a simulated robot that learns predicting the next state given the current state and the action taken in an environment composed of regions with different properties. We verified the proposed method, SM is partitioned into more semantically meaningful regions adapting environment dynamics, the exploration of the robot in these regions can better exploit IM mechanisms and the system learn more efficiently and effectively i.e. with higher performance in a shorter time, compared to a baseline method.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114775336","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: 4

Autonomous table-cleaning from kinesthetic demonstrations using Deep Learning 使用深度学习的动觉演示自动清理桌子

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761013

Nino Cauli, Pedro Vicente, Jaeseok Kim, B. Damas, A. Bernardino, F. Cavallo, J. Santos-Victor

{"title":"Autonomous table-cleaning from kinesthetic demonstrations using Deep Learning","authors":"Nino Cauli, Pedro Vicente, Jaeseok Kim, B. Damas, A. Bernardino, F. Cavallo, J. Santos-Victor","doi":"10.1109/DEVLRN.2018.8761013","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761013","url":null,"abstract":"We address the problem of teaching a robot how to autonomously perform table-cleaning tasks in a robust way. In particular, we focus on wiping and sweeping a table with a tool (e.g., a sponge). For the training phase, we use a set of kinestethic demonstrations performed over a table. The recorded 2D table-space trajectories, together with the images acquired by the robot, are used to train a deep convolutional network that automatically learns the parameters of a Gaussian Mixture Model that represents the hand movement. After the learning stage, the network is fed with the current image showing the location/shape of the dirt or stain to clean. The robot is able to perform cleaning arm-movements, obtained through Gaussian Mixture Regression using the mixture parameters provided by the network. Invariance to the robot posture is achieved by applying a plane-projective transformation before inputting the images to the neural network; robustness to illumination changes and other disturbances is increased by considering an augmented data set. This improves the generalization properties of the neural network, enabling for instance its use with the left arm after being trained using trajectories acquired with the right arm. The system was tested on the iCub robot generating a cleaning behaviour similar to the one of human demonstrators.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133892538","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: 9

A bio-inspired model towards vocal gesture learning in songbird 鸣禽声音手势学习的仿生模型

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-09-01 DOI: 10.1109/DEVLRN.2018.8761009

Silvia Pagliarini, Xavier Hinaut, Arthur Leblois

{"title":"A bio-inspired model towards vocal gesture learning in songbird","authors":"Silvia Pagliarini, Xavier Hinaut, Arthur Leblois","doi":"10.1109/DEVLRN.2018.8761009","DOIUrl":"https://doi.org/10.1109/DEVLRN.2018.8761009","url":null,"abstract":"The paper proposes a bio-inspired model for an imitative sensorimotor learning, which aims at building a map between the sensory representations of gestures (sensory targets) and their underlying motor pattern through random exploration of the motor space. An example of such learning process occurs during vocal learning in humans or birds, when young subjects babble and learn to copy previously heard adult vocalizations. Previous work has suggested that a simple Hebbian learning rule allows perfect imitation when sensory feedback is a purely linear function of the motor pattern underlying movement production. We aim at generalizing this model to the more realistic case where sensory responses are sparse and non-linear. To this end, we explore the performance of various learning rules and normalizations and discuss their biological relevance. Importantly, the proposed model is robust whatever normalization is chosen. We show that both the imitation quality and the convergence time are highly dependent on the sensory selectivity and dimension of the motor representation.","PeriodicalId":236346,"journal":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128876045","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

Drifting perceptual patterns suggest prediction errors fusion rather than hypothesis selection: replicating the rubber-hand illusion on a robot 漂移的感知模式表明预测错误融合而不是假设选择:在机器人身上复制橡胶手错觉

2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) Pub Date : 2018-06-18 DOI: 10.1109/DEVLRN.2018.8761005

Nina-Alisa Hinz, Pablo Lanillos, H. Mueller, G. Cheng

引用次数: 28