Integrated Cognitive Architecture for Robot Learning of Action and Language.
Ontology highlight
ABSTRACT:
SUBMITTER: Miyazawa K
PROVIDER: S-EPMC7805838 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Integrated Cognitive Architecture for Robot Learning of Action and Language.
Miyazawa Kazuki K Horii Takato T Aoki Tatsuya T Nagai Takayuki T
Frontiers in robotics and AI 20191129
The manner in which humans learn, plan, and decide actions is a very compelling subject. Moreover, the mechanism behind high-level cognitive functions, such as action planning, language understanding, and logical thinking, has not yet been fully implemented in robotics. In this paper, we propose a framework for the simultaneously comprehension of concepts, actions, and language as a first step toward this goal. This can be achieved by integrating various cognitive modules and leveraging mainly m ...[more]
Similar Datasets
Project description:The current study investigated how individual differences among children affect the added value of social robots for teaching second language (L2) vocabulary to young children. Specifically, we investigated the moderating role of three individual child characteristics deemed relevant for language learning: first language (L1) vocabulary knowledge, phonological memory, and selective attention. We expected children low in these abilities to particularly benefit from being assisted by a robot in a vocabulary training. An L2 English vocabulary training intervention consisting of seven sessions was administered to 193 monolingual Dutch five-year-old children over a three- to four-week period. Children were randomly assigned to one of three experimental conditions: 1) a tablet only, 2) a tablet and a robot that used deictic (pointing) gestures (the no-iconic-gestures condition), or 3) a tablet and a robot that used both deictic and iconic gestures (i.e., gestures depicting the target word; the iconic-gestures condition). There also was a control condition in which children did not receive a vocabulary training, but played dancing games with the robot. L2 word knowledge was measured directly after the training and two to four weeks later. In these post-tests, children in the experimental conditions outperformed children in the control condition on word knowledge, but there were no differences between the three experimental conditions. Several moderation effects were found. The robot's presence particularly benefited children with larger L1 vocabularies or poorer phonological memory, while children with smaller L1 vocabularies or better phonological memory performed better in the tablet-only condition. Children with larger L1 vocabularies and better phonological memory performed better in the no-iconic-gestures condition than in the iconic-gestures condition, while children with better selective attention performed better in the iconic-gestures condition than the no-iconic-gestures condition. Together, the results showed that the effects of the robot and its gestures differ across children, which should be taken into account when designing and evaluating robot-assisted L2 teaching interventions.
| S-EPMC8421643 | biostudies-literature
Project description:To investigate how a robot's use of feedback can influence children's engagement and support second language learning, we conducted an experiment in which 72 children of 5 years old learned 18 English animal names from a humanoid robot tutor in three different sessions. During each session, children played 24 rounds in an "I spy with my little eye" game with the robot, and in each session the robot provided them with a different type of feedback. These feedback types were based on a questionnaire study that we conducted with student teachers and the outcome of this questionnaire was translated to three within-design conditions: (teacher) preferred feedback, (teacher) dispreferred feedback and no feedback. During the preferred feedback session, among others, the robot varied his feedback and gave children the opportunity to try again (e.g., "Well done! You clicked on the horse.", "Too bad, you pressed the bird. Try again. Please click on the horse."); during the dispreferred feedback the robot did not vary the feedback ("Well done!", "Too bad.") and children did not receive an extra attempt to try again; and during no feedback the robot did not comment on the children's performances at all. We measured the children's engagement with the task and with the robot as well as their learning gain, as a function of condition. Results show that children tended to be more engaged with the robot and task when the robot used preferred feedback than in the two other conditions. However, preferred or dispreferred feedback did not have an influence on learning gain. Children learned on average the same number of words in all conditions. These findings are especially interesting for long-term interactions where engagement of children often drops. Moreover, feedback can become more important for learning when children need to rely more on feedback, for example, when words or language constructions are more complex than in our experiment. The experiment's method, measurements and main hypotheses were preregistered.
| S-EPMC7806035 | biostudies-literature
Project description:BackgroundWe demonstrate the first self-learning, context-sensitive, autonomous camera-guiding robot applicable to minimally invasive surgery. The majority of surgical robots nowadays are telemanipulators without autonomous capabilities. Autonomous systems have been developed for laparoscopic camera guidance, however following simple rules and not adapting their behavior to specific tasks, procedures, or surgeons.MethodsThe herein presented methodology allows different robot kinematics to perceive their environment, interpret it according to a knowledge base and perform context-aware actions. For training, twenty operations were conducted with human camera guidance by a single surgeon. Subsequently, we experimentally evaluated the cognitive robotic camera control. A VIKY EP system and a KUKA LWR 4 robot were trained on data from manual camera guidance after completion of the surgeon's learning curve. Second, only data from VIKY EP were used to train the LWR and finally data from training with the LWR were used to re-train the LWR.ResultsThe duration of each operation decreased with the robot's increasing experience from 1704 s ± 244 s to 1406 s ± 112 s, and 1197 s. Camera guidance quality (good/neutral/poor) improved from 38.6/53.4/7.9 to 49.4/46.3/4.1% and 56.2/41.0/2.8%.ConclusionsThe cognitive camera robot improved its performance with experience, laying the foundation for a new generation of cognitive surgical robots that adapt to a surgeon's needs.
| S-EPMC8346448 | biostudies-literature
Project description:Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.
| S-EPMC4641699 | biostudies-literature
Project description:According to the US Department of State, a native English speaker can learn Spanish in about 600 h, but would take four times as long to learn Japanese. While it may be intuitive that similarity between a foreign language and a native tongue can influence the ease of acquisition, what is less obvious are the specific cognitive and emotional processes that can lead to different outcomes. Here, we explored the influence of cognitive strategies and affective states on native English speakers' ability to learn artificial foreign words that vary in their similarity to the native language. Explicit word learning strategies were reported more often, and were more effective for learners of a more similar language, and cognitive strategies were especially helpful for learners with lower moods. We conclude that language similarity, strategy, and affect dynamically interact to ultimately determine success at learning novel languages.
| S-EPMC8210683 | biostudies-literature
Project description:ContextA standardized set of picture stimuli for neuro-language disorder has been long overdue.AimsTo develop a standardized set of 303 pictures for use in experiments of Intensive Language Action Therapy (ILAT).Methods and materialSeveral sources with standardized picture stimuli having culturally unbiased features were studied. Among those studies two prime sources (1) Snodgrass & Vanderwart (1980), 127 (89+37) items and (2) Neininger & Pulvermuller (2002), 147 (89+56) items were used extensively. Out of 303 stimuli, 89 items were common to both principle sources. An Indian study by George & Mathuranath (2007) has also been taken as an additional source. Line drawing stimuli were standardized on four variables of central relevance to memory and cognitive processing: name agreement, image agreement, familiarity, and visual complexity.Statistical analysis usedAll measures related to 303 concepts i.e. % correct, H statistics, familiarity, image agreement and visual complexity were analysed descriptively.ResultsLow mean and positive skew on H statistics and visual complexity show that many concepts had a high name agreement (13 concepts have H values of .0, and 55 have H values of 0.68 or below, where 0.68 represents consensus among all but few of the subjects on a picture's name) and were visually simple line drawings. The intercorrelations among the four measures were low, suggesting that they are indices of different attributes of the pictures.ConclusionsUsage of appropriate items/stimuli has immense potential to influence aphasia therapy outcome. This set of pictures and its normative variable has enhanced the ILAT outcome. It could be generalised for other aphasia therapy too to understand its efficacy.
| S-EPMC7731687 | biostudies-literature
Project description:During human-robot interaction, errors will occur. Hence, understanding the effects of interaction errors and especially the effect of prior knowledge on robot learning performance is relevant to develop appropriate approaches for learning under natural interaction conditions, since future robots will continue to learn based on what they have already learned. In this study, we investigated interaction errors that occurred under two learning conditions, i.e., in the case that the robot learned without prior knowledge (cold-start learning) and in the case that the robot had prior knowledge (warm-start learning). In our human-robot interaction scenario, the robot learns to assign the correct action to a current human intention (gesture). Gestures were not predefined but the robot had to learn their meaning. We used a contextual-bandit approach to maximize the expected payoff by updating (a) the current human intention (gesture) and (b) the current human intrinsic feedback after each action selection of the robot. As an intrinsic evaluation of the robot behavior we used the error-related potential (ErrP) in the human electroencephalogram as reinforcement signal. Either gesture errors (human intentions) can be misinterpreted by incorrectly captured gestures or errors in the ErrP classification (human feedback) can occur. We investigated these two types of interaction errors and their effects on the learning process. Our results show that learning and its online adaptation was successful under both learning conditions (except for one subject in cold-start learning). Furthermore, warm-start learning achieved faster convergence, while cold-start learning was less affected by online changes in the current context.
| S-EPMC7805941 | biostudies-literature
Project description:Environmental enrichment (EE) conditions have profound beneficial effects for reinstating cognitive ability in neuropathological disorders like Alzheimerâs disease (AD). While EE benefits involve epigenetic gene control mechanisms that comprise histone acetylation, the histone acetyltransferases (HATs) involved remain largely unknown. Here, we examine a role for Tip60 HAT action in mediating activity- dependent beneficial neuroadaptations to EE using the Drosophila CNS mushroom body (MB) as a well-characterized cognition model. We show that flies raised under EE conditions display enhanced MB axonal outgrowth, synapse protein production, histone acetylation induction and transcriptional activation of cognition linked genes when compared to their genotypically identical siblings raised under isolated conditions. Further, these beneficial changes are impaired in both Tip60 HAT mutant flies and APP neurodegenerative flies. While EE conditions provide only slight beneficial neuroadaptive changes in the APP neurodegenerative fly MB, such positive changes are significantly enhanced by increasing MB Tip60 HAT levels. Our results implicate Tip60 as a critical mediator of EE-induced benefits, and provide insight into synergistic behavioral and epigenetic based approaches for treatment of cognitive disorders. EE has been shown to positively impact gene expression profiles in the mouse brain that are enriched in functions such as neuronal structure, synaptic plasticity and neurotransmission. Thus, we asked whether the EE induced beneficial MB structural and synaptic changes we observe are accompanied by neuroadaptive transcriptional benefits in the Drosophila MB, and if so, is Tip60 HAT action required for this process. To address this question, we accessed EE induced beneficial transcriptional changes using microarray. We crossed our UAS-mCD8-GFP;Tip60E431Q flies or control UAS-mCD8-GFP flies to MB GAL4 OK-107 to simultaneously induce Tip60 HAT loss in the MB while tagging MB cells with GFP. Adult progeny were exposed to EE or ISO conditions. After conditioning, the GFP tagged MB Kenyon neurons were FACs purified from conditioned fly brains from each genotype to enrich for detection of an EE induced MB transcriptional response. RNA was isolated from the purified Kenyon MB neurons and transcriptional changes for each genotype were assessed using microarray analysis
2016-01-07 | E-GEOD-76612 | biostudies-arrayexpress
Project description:Research on proficient bilinguals has demonstrated that both languages are always active, even when only one is required. The coactivation of the two languages creates both competition and convergence, facilitating the processing of cognate words, but slowing lexical access when there is a requirement to engage control mechanisms to select the target language. Critically, these consequences are evident in the native language (L1) as well as in the second language (L2). The present study questioned whether L1 changes can be detected at early stages of L2 learning and how they are modulated by L2 proficiency. Native English speakers learning Spanish performed an English (L1) lexical decision task that included cognates while event-related potentials were recorded. They also performed verbal fluency, working memory, and inhibitory control tasks. A group of matched monolinguals performed the same tasks in English only. The results revealed that intermediate learners demonstrate a reduced N400 for cognates compared with noncognates in English (L1), and an emerging effect is visually present in beginning learners as well; however, no behavioral cognate effect was present for either group. In addition, slower reaction times in English (L1) are related to a larger cognate N400 magnitude in English (L1) and Spanish (L2), and to better inhibitory control for learners but not for monolinguals. The results suggest that contrary to the claim that L2 affects L1 only when L2 speakers are highly proficient, L2 learning begins to impact L1 early in the development of the L2 skill.
| S-EPMC4589520 | biostudies-other
Project description:Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action sequences. Punishment signals are typically disembodied, i.e., with no or little relation to the agent-intrinsic limitations, and they are often used to impose behavioral constraints. Here, we provide an alternative approach for nociceptive signals as drivers of learning rather than simple triggers of preprogrammed behavior. Explicitly, we use nociception to expand the state space while we use punishment as a negative reinforcement learning signal. We compare the performance-in terms of task error, the amount of perceived nociception, and length of learned action sequences-of different neural networks imbued with punishment-based reinforcement signals for inverse kinematic learning. We contrast the performance of a version of the neural network that receives nociceptive inputs to that without such a process. Furthermore, we provide evidence that nociception can improve learning-making the algorithm more robust against network initializations-as well as behavioral performance by reducing the task error, perceived nociception, and length of learned action sequences. Moreover, we provide evidence that punishment, at least as typically used within reinforcement learning applications, may be detrimental in all relevant metrics.
| S-EPMC5376586 | biostudies-other