Pub Date : 2014-03-01DOI: 10.1109/TAMD.2013.2280614
S. Ivaldi, S. Nguyen, Natalia Lyubova, Alain Droniou, V. Padois, David Filliat, Pierre-Yves Oudeyer, Olivier Sigaud
This paper addresses the problem of active object learning by a humanoid child-like robot, using a developmental approach. We propose a cognitive architecture where the visual representation of the objects is built incrementally through active exploration. We present the design guidelines of the cognitive architecture, its main functionalities, and we outline the cognitive process of the robot by showing how it learns to recognize objects in a human-robot interaction scenario inspired by social parenting. The robot actively explores the objects through manipulation, driven by a combination of social guidance and intrinsic motivation. Besides the robotics and engineering achievements, our experiments replicate some observations about the coupling of vision and manipulation in infants, particularly how they focus on the most informative objects. We discuss the further benefits of our architecture, particularly how it can be improved and used to ground concepts.
{"title":"Object Learning Through Active Exploration","authors":"S. Ivaldi, S. Nguyen, Natalia Lyubova, Alain Droniou, V. Padois, David Filliat, Pierre-Yves Oudeyer, Olivier Sigaud","doi":"10.1109/TAMD.2013.2280614","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2280614","url":null,"abstract":"This paper addresses the problem of active object learning by a humanoid child-like robot, using a developmental approach. We propose a cognitive architecture where the visual representation of the objects is built incrementally through active exploration. We present the design guidelines of the cognitive architecture, its main functionalities, and we outline the cognitive process of the robot by showing how it learns to recognize objects in a human-robot interaction scenario inspired by social parenting. The robot actively explores the objects through manipulation, driven by a combination of social guidance and intrinsic motivation. Besides the robotics and engineering achievements, our experiments replicate some observations about the coupling of vision and manipulation in infants, particularly how they focus on the most informative objects. We discuss the further benefits of our architecture, particularly how it can be improved and used to ground concepts.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"26 1","pages":"56-72"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2280614","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62762391","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}
Pub Date : 2014-03-01DOI: 10.1109/TAMD.2013.2284065
S. Boucenna, P. Gaussier, L. Hafemeister
In this paper, we study how emotional interactions with a social partner can bootstrap increasingly complex behaviors such as social referencing. Our idea is that social referencing as well as facial expression recognition can emerge from a simple sensory-motor system involving emotional stimuli. Without knowing that the other is an agent, the robot is able to learn some complex tasks if the human partner has some “empathy” or at least “resonate” with the robot head (low level emotional resonance). Hence, we advocate the idea that social referencing can be bootstrapped from a simple sensory-motor system not dedicated to social interactions.
{"title":"Development of First Social Referencing Skills: Emotional Interaction as a Way to Regulate Robot Behavior","authors":"S. Boucenna, P. Gaussier, L. Hafemeister","doi":"10.1109/TAMD.2013.2284065","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2284065","url":null,"abstract":"In this paper, we study how emotional interactions with a social partner can bootstrap increasingly complex behaviors such as social referencing. Our idea is that social referencing as well as facial expression recognition can emerge from a simple sensory-motor system involving emotional stimuli. Without knowing that the other is an agent, the robot is able to learn some complex tasks if the human partner has some “empathy” or at least “resonate” with the robot head (low level emotional resonance). Hence, we advocate the idea that social referencing can be bootstrapped from a simple sensory-motor system not dedicated to social interactions.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"6 1","pages":"42-55"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2284065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62762202","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}
Pub Date : 2014-03-01DOI: 10.1109/TAMD.2014.2310061
Nadja Althaus, D. Mareschal
In the above paper (ibid., vol. 5, no. 4, pp. 288-297, Dec. 2013), Fig. 4 was mistakenly misrepresented. The current correct Fig. 4 is presented here.
在上述文件(同上，第5卷，第2号)中。4, pp. 288-297, 2013年12月)，图4被错误地歪曲了。当前正确的图4呈现在这里。
{"title":"Erratum to \"Modeling cross-modal interactions in early word learning\" [Dec 13 288-297]","authors":"Nadja Althaus, D. Mareschal","doi":"10.1109/TAMD.2014.2310061","DOIUrl":"https://doi.org/10.1109/TAMD.2014.2310061","url":null,"abstract":"In the above paper (ibid., vol. 5, no. 4, pp. 288-297, Dec. 2013), Fig. 4 was mistakenly misrepresented. The current correct Fig. 4 is presented here.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"6 1","pages":"73-73"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2014.2310061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62762448","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}
Pub Date : 2014-03-01DOI: 10.1109/TAMD.2013.2277589
S. Franklin, Tamas Madl, S. D’Mello, Javier Snaider
We describe a cognitive architecture learning intelligent distribution agent (LIDA) that affords attention, action selection and human-like learning intended for use in controlling cognitive agents that replicate human experiments as well as performing real-world tasks. LIDA combines sophisticated action selection, motivation via emotions, a centrally important attention mechanism, and multimodal instructionalist and selectionist learning. Empirically grounded in cognitive science and cognitive neuroscience, the LIDA architecture employs a variety of modules and processes, each with its own effective representations and algorithms. LIDA has much to say about motivation, emotion, attention, and autonomous learning in cognitive agents. In this paper, we summarize the LIDA model together with its resulting agent architecture, describe its computational implementation, and discuss results of simulations that replicate known experimental data. We also discuss some of LIDA's conceptual modules, propose nonlinear dynamics as a bridge between LIDA's modules and processes and the underlying neuroscience, and point out some of the differences between LIDA and other cognitive architectures. Finally, we discuss how LIDA addresses some of the open issues in cognitive architecture research.
{"title":"LIDA: A Systems-level Architecture for Cognition, Emotion, and Learning","authors":"S. Franklin, Tamas Madl, S. D’Mello, Javier Snaider","doi":"10.1109/TAMD.2013.2277589","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2277589","url":null,"abstract":"We describe a cognitive architecture learning intelligent distribution agent (LIDA) that affords attention, action selection and human-like learning intended for use in controlling cognitive agents that replicate human experiments as well as performing real-world tasks. LIDA combines sophisticated action selection, motivation via emotions, a centrally important attention mechanism, and multimodal instructionalist and selectionist learning. Empirically grounded in cognitive science and cognitive neuroscience, the LIDA architecture employs a variety of modules and processes, each with its own effective representations and algorithms. LIDA has much to say about motivation, emotion, attention, and autonomous learning in cognitive agents. In this paper, we summarize the LIDA model together with its resulting agent architecture, describe its computational implementation, and discuss results of simulations that replicate known experimental data. We also discuss some of LIDA's conceptual modules, propose nonlinear dynamics as a bridge between LIDA's modules and processes and the underlying neuroscience, and point out some of the differences between LIDA and other cognitive architectures. Finally, we discuss how LIDA addresses some of the open issues in cognitive architecture research.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"6 1","pages":"19-41"},"PeriodicalIF":0.0,"publicationDate":"2014-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2277589","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62762073","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}
Pub Date : 2014-01-01DOI: 10.1109/TAMD.2014.2309443
Zhengyou Zhang
{"title":"Introduction of New Associate Editors","authors":"Zhengyou Zhang","doi":"10.1109/TAMD.2014.2309443","DOIUrl":"https://doi.org/10.1109/TAMD.2014.2309443","url":null,"abstract":"","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"21 1","pages":"3-4"},"PeriodicalIF":0.0,"publicationDate":"2014-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86425519","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}
Pub Date : 2013-12-01DOI: 10.1109/TAMD.2013.2264858
Nadja Althaus, D. Mareschal
Infancy research demonstrating a facilitation of visual category formation in the presence of verbal labels suggests that infants' object categories and words develop interactively. This contrasts with the notion that words are simply mapped “onto” previously existing categories. To investigate the computational foundations of a system in which word and object categories develop simultaneously and in an interactive fashion, we present a model of word learning based on interacting self-organizing maps that represent the auditory and visual modalities, respectively. While other models of lexical development have employed similar dual-map architectures, our model uses active Hebbian connections to propagate activation between the visual and auditory maps during learning. Our results show that categorical perception emerges from these early audio-visual interactions in both domains. We argue that the learning mechanism introduced in our model could play a role in the facilitation of infants' categorization through verbal labeling.
{"title":"Modeling Cross-Modal Interactions in Early Word Learning","authors":"Nadja Althaus, D. Mareschal","doi":"10.1109/TAMD.2013.2264858","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2264858","url":null,"abstract":"Infancy research demonstrating a facilitation of visual category formation in the presence of verbal labels suggests that infants' object categories and words develop interactively. This contrasts with the notion that words are simply mapped “onto” previously existing categories. To investigate the computational foundations of a system in which word and object categories develop simultaneously and in an interactive fashion, we present a model of word learning based on interacting self-organizing maps that represent the auditory and visual modalities, respectively. While other models of lexical development have employed similar dual-map architectures, our model uses active Hebbian connections to propagate activation between the visual and auditory maps during learning. Our results show that categorical perception emerges from these early audio-visual interactions in both domains. We argue that the learning mechanism introduced in our model could play a role in the facilitation of infants' categorization through verbal labeling.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"5 1","pages":"288-297"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2264858","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761686","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}
Pub Date : 2013-12-01DOI: 10.1109/TAMD.2013.2257766
Rujiao Yan, Tobias Rodemann, B. Wrede
For sound localization, the binaural auditory system of a robot needs audio-motor maps, which represent the relationship between certain audio features and the position of the sound source. This mapping is normally learned during an offline calibration in controlled environments, but we show that using computational audiovisual scene analysis (CAVSA), it can be adapted online in free interaction with a number of a priori unknown speakers. CAVSA enables a robot to understand dynamic dialog scenarios, such as the number and position of speakers, as well as who is the current speaker. Our system does not require specific robot motions and thus can work during other tasks. The performance of online-adapted maps is continuously monitored by computing the difference between online-adapted and offline-calibrated maps and also comparing sound localization results with ground truth data (if available). We show that our approach is more robust in multiperson scenarios than the state of the art in terms of learning progress. We also show that our system is able to bootstrap with a randomized audio-motor map and adapt to hardware modifications that induce a change in audio-motor maps.
{"title":"Computational Audiovisual Scene Analysis in Online Adaptation of Audio-Motor Maps","authors":"Rujiao Yan, Tobias Rodemann, B. Wrede","doi":"10.1109/TAMD.2013.2257766","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2257766","url":null,"abstract":"For sound localization, the binaural auditory system of a robot needs audio-motor maps, which represent the relationship between certain audio features and the position of the sound source. This mapping is normally learned during an offline calibration in controlled environments, but we show that using computational audiovisual scene analysis (CAVSA), it can be adapted online in free interaction with a number of a priori unknown speakers. CAVSA enables a robot to understand dynamic dialog scenarios, such as the number and position of speakers, as well as who is the current speaker. Our system does not require specific robot motions and thus can work during other tasks. The performance of online-adapted maps is continuously monitored by computing the difference between online-adapted and offline-calibrated maps and also comparing sound localization results with ground truth data (if available). We show that our approach is more robust in multiperson scenarios than the state of the art in terms of learning progress. We also show that our system is able to bootstrap with a randomized audio-motor map and adapt to hardware modifications that induce a change in audio-motor maps.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"5 1","pages":"273-287"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2257766","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761367","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}
Pub Date : 2013-12-01DOI: 10.1109/TAMD.2013.2264321
Piero Savastano, S. Nolfi
We present a neurorobotic model that develops reaching and grasping skills analogous to those displayed by infants during their early developmental stages. The learning process is realized in an incremental manner, taking into account the reflex behaviors initially possessed by infants and the neurophysiological and cognitive maturation occurring during the relevant developmental period. The behavioral skills acquired by the robots closely match those displayed by children. The comparison between incremental and nonincremental experiments demonstrates how some of the limitations characterizing the initial developmental phase channel the learning process toward better solutions.
{"title":"A Robotic Model of Reaching and Grasping Development","authors":"Piero Savastano, S. Nolfi","doi":"10.1109/TAMD.2013.2264321","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2264321","url":null,"abstract":"We present a neurorobotic model that develops reaching and grasping skills analogous to those displayed by infants during their early developmental stages. The learning process is realized in an incremental manner, taking into account the reflex behaviors initially possessed by infants and the neurophysiological and cognitive maturation occurring during the relevant developmental period. The behavioral skills acquired by the robots closely match those displayed by children. The comparison between incremental and nonincremental experiments demonstrates how some of the limitations characterizing the initial developmental phase channel the learning process toward better solutions.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"5 1","pages":"326-336"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2264321","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761537","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}
Pub Date : 2013-12-01DOI: 10.1109/TAMD.2013.2258019
Shingo Murata, Jun Namikawa, H. Arie, S. Sugano, J. Tani
This study proposes a novel type of dynamic neural network model that can learn to extract stochastic or fluctuating structures hidden in time series data. The network learns to predict not only the mean of the next input state, but also its time-dependent variance. The training method is based on maximum likelihood estimation by using the gradient descent method and the likelihood function is expressed as a function of the estimated variance. Regarding the model evaluation, we present numerical experiments in which training data were generated in different ways utilizing Gaussian noise. Our analysis showed that the network can predict the time-dependent variance and the mean and it can also reproduce the target stochastic sequence data by utilizing the estimated variance. Furthermore, it was shown that a humanoid robot using the proposed network can learn to reproduce latent stochastic structures hidden in fluctuating tutoring trajectories. This learning scheme is essential for the acquisition of sensory-guided skilled behavior.
{"title":"Learning to Reproduce Fluctuating Time Series by Inferring Their Time-Dependent Stochastic Properties: Application in Robot Learning Via Tutoring","authors":"Shingo Murata, Jun Namikawa, H. Arie, S. Sugano, J. Tani","doi":"10.1109/TAMD.2013.2258019","DOIUrl":"https://doi.org/10.1109/TAMD.2013.2258019","url":null,"abstract":"This study proposes a novel type of dynamic neural network model that can learn to extract stochastic or fluctuating structures hidden in time series data. The network learns to predict not only the mean of the next input state, but also its time-dependent variance. The training method is based on maximum likelihood estimation by using the gradient descent method and the likelihood function is expressed as a function of the estimated variance. Regarding the model evaluation, we present numerical experiments in which training data were generated in different ways utilizing Gaussian noise. Our analysis showed that the network can predict the time-dependent variance and the mean and it can also reproduce the target stochastic sequence data by utilizing the estimated variance. Furthermore, it was shown that a humanoid robot using the proposed network can learn to reproduce latent stochastic structures hidden in fluctuating tutoring trajectories. This learning scheme is essential for the acquisition of sensory-guided skilled behavior.","PeriodicalId":49193,"journal":{"name":"IEEE Transactions on Autonomous Mental Development","volume":"10 1","pages":"298-310"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TAMD.2013.2258019","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62761375","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：