| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Duran, Boris, et al.
(författare)
-
Learning Temporal Intervals in Neural Dynamics
- 2018
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers. - 2379-8920 .- 2379-8939. ; 10:2, s. 359-372
-
Tidskriftsartikel (refereegranskat)
|
|
| 5. |
- Högman, Virgile, et al.
(författare)
-
A sensorimotor learning framework for object categorization
- 2016
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920 .- 2379-8939. ; 8:1, s. 15-25
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a framework that enables a robot to discover various object categories through interaction. The categories are described using action-effect relations, i.e. sensorimotor contingencies rather than more static shape or appearance representation. The framework provides a functionality to classify objects and the resulting categories, associating a class with a specific module. We demonstrate the performance of the framework by studying a pushing behavior in robots, encoding the sensorimotor contingencies and their predictability with Gaussian Processes. We show how entropy-based action selection can improve object classification and how functional categories emerge from the similarities of effects observed among the objects. We also show how a multidimensional action space can be realized by parameterizing pushing using both position and velocity.
|
|
| 6. |
- Khan, Muhammad Sikandar Lal, 1988-, et al.
(författare)
-
Action Augmented Real Virtuality Design for Presence
- 2018
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920 .- 2379-8939. ; 10:4, s. 961-972
-
Tidskriftsartikel (refereegranskat)abstract
- This paper addresses the important question of how to design a video teleconferencing setup to increase the experience of spatial and social presence. Traditional video teleconferencing setups are lacking in presenting the nonverbal behaviors that humans express in face-to-face communication, which results in decrease in presence-experience. In order to address this issue, we first present a conceptual framework of presence for video teleconferencing. We introduce a modern presence concept called real virtuality and propose a new way of achieving this based on body or artifact actions to increase the feeling of presence, and we named this concept presence through actions. Using this new concept, we present the design of a novel action-augmented real virtuality prototype that considers the challenges related to the design of an action prototype, action embodiment, and face representation. Our action prototype is a telepresence mechatronic robot (TEBoT), and action embodiment is through a head-mounted display (HMD). The face representation solves the problem of face occlusion introduced by the HMD. The novel combination of HMD, TEBoT, and face representation algorithm has been tested in a real video teleconferencing scenario for its ability to solve the challenges related to spatial and social presence. We have performed a user study where the invited participants were requested to experience our novel setup and to compare it with a traditional video teleconferencing setup. The results show that the action capabilities not only increase the feeling of spatial presence but also increase the feeling of social presence of a remote person among local collaborators.
|
|
| 7. |
- Luo, Dingsheng, et al.
(författare)
-
Guest Editorial Special Issue on Emerging Topics on Development and Learning
- 2023
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920 .- 2379-8939. ; 15:4, s. 1795-1800
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- This special issue will encompass state-of-the-art research on emerging topics related to development and learning in natural and artificial systems. The primary focus of this special issue is to explore the facets of development and learning from a multidisciplinary perspective by convening researchers from the fields of computer science, robotics, psychology, and developmental studies. We invited researchers to share knowledge and research on how humans and animals develop sensing, reasoning, and actions, and how to exploit robots as research tools to test models of development and learning. We expected the submitted contributions to emphasize the interaction with social and physical environments and how cognitive and developmental capabilities can be transferred to computing systems and robotics. This approach is in harmony with the dual objectives of comprehending human and animal development while leveraging this understanding to enhance future intelligent technologies, particularly for robots that will engage in close interactions with humans.
|
|
| 8. |
- Nair, Vipul, et al.
(författare)
-
Kinematic primitives in action similarity judgments : A human-centered computational model
- 2023
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : IEEE. - 2379-8920 .- 2379-8939. ; 15:4, s. 1981-1992
-
Tidskriftsartikel (refereegranskat)abstract
- This paper investigates the role that kinematic features play in human action similarity judgments. The results of three experiments with human participants are compared with the computational model that solves the same task. The chosen model has its roots in developmental robotics and performs action classification based on learned kinematic primitives. The comparative experimental results show that both model and human participants can reliably identify whether two actions are the same or not. Specifically, most of the given actions could be similarity judged based on very limited information from a single feature domain (velocity or spatial). Both velocity and spatial features were however necessary to reach a level of human performance on evaluated actions. The experimental results also show that human performance on an action identification task indicated that they clearly relied on kinematic information rather than on action semantics. The results show that both the model and human performance are highly accurate in an action similarity task based on kinematic-level features, which can provide an essential basis for classifying human actions.
|
|
| 9. |
- Persson, Andreas, 1980-, et al.
(författare)
-
Semantic Relational Object Tracking
- 2020
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : IEEE. - 2379-8920 .- 2379-8939. ; 12:1, s. 84-97
-
Tidskriftsartikel (refereegranskat)abstract
- This paper addresses the topic of semantic world modeling by conjoining probabilistic reasoning and object anchoring. The proposed approach uses a so-called bottom-up object anchoring method that relies on rich continuous attribute values measured from perceptual sensor data. A novel anchoring matching function learns to maintain object entities in space and time and is validated using a large set of trained humanly annotated ground truth data of real-world objects. For more complex scenarios, a high-level probabilistic object tracker has been integrated with the anchoring framework and handles the tracking of occluded objects via reasoning about the state of unobserved objects. We demonstrate the performance of our integrated approach through scenarios such as the shell game scenario, where we illustrate how anchored objects are retained by preserving relations through probabilistic reasoning.
|
|
| 10. |
- Saponaro, Giovanni, et al.
(författare)
-
Beyond the Self: Using Grounded Affordances to Interpret and Describe Others’ Actions
- 2020
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920 .- 2379-8939. ; 12:2, s. 209-221
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a developmental approach that allows a robot to interpret and describe the actions of human agents by reusing previous experience. The robot first learns the association between words and object affordances by manipulating the objects in its environment. It then uses this information to learn a mapping between its own actions and those performed by a human in a shared environment. It finally fuses the information from these two models to interpret and describe human actions in light of its own experience. In our experiments, we show that the model can be used flexibly to do inference on different aspects of the scene. We can predict the effects of an action on the basis of object properties. We can revise the belief that a certain action occurred, given the observed effects of the human action. In an early action recognition fashion, we can anticipate the effects when the action has only been partially observed. By estimating the probability of words given the evidence and feeding them into a pre-defined grammar, we can generate relevant descriptions of the scene. We believe that this is a step towards providing robots with the fundamental skills to engage in social collaboration with humans.
|
|
| 11. |
- Stefanov, Kalin, et al.
(författare)
-
Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially-Aware Language Acquisition
- 2020
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920 .- 2379-8939. ; 12:2, s. 250-259
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a self-supervised method for visual detection of the active speaker in a multi-person spoken interaction scenario. Active speaker detection is a fundamental prerequisite for any artificial cognitive system attempting to acquire language in social settings. The proposed method is intended to complement the acoustic detection of the active speaker, thus improving the system robustness in noisy conditions. The method can detect an arbitrary number of possibly overlapping active speakers based exclusively on visual information about their face. Furthermore, the method does not rely on external annotations, thus complying with cognitive development. Instead, the method uses information from the auditory modality to support learning in the visual domain. This paper reports an extensive evaluation of the proposed method using a large multi-person face-to-face interaction dataset. The results show good performance in a speaker dependent setting. However, in a speaker independent setting the proposed method yields a significantly lower performance. We believe that the proposed method represents an essential component of any artificial cognitive system or robotic platform engaging in social interactions.
|
|
| 12. |
- Wilaiprasitporn, Theerawit, et al.
(författare)
-
Affective EEG-Based Person Identification Using the Deep Learning Approach
- 2020
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2379-8920 .- 2379-8939. ; 12:3, s. 486-496
-
Tidskriftsartikel (refereegranskat)abstract
- Electroencephalography (EEG) is another method for performing person identification (PI). Due to the nature of the EEG signals, EEG-based PI is typically done while a person is performing a mental task such as motor control. However, few studies used EEG-based PI while the person is in different mental states (affective EEG). The aim of this paper is to improve the performance of affective EEG-based PI using a deep learning (DL) approach. We proposed a cascade of DL using a combination of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). CNNs are used to handle the spatial information from the EEG while RNNs extract the temporal information. We evaluated two types of RNNs, namely long short-term memory (LSTM) and gated recurrent unit (GRU). The proposed method is evaluated on the state-of-the-art affective data set DEAP. The results indicate that CNN-GRU and CNN-LSTM can perform PI from different affective states and reach up to 99.90%-100% mean correct recognition rate. This significantly outperformed a support vector machine baseline system that used power spectral density features. Notably, the 100% mean CRR came from 32 subjects in DEAP data set. Even after the reduction of the number of EEG electrodes from 32 to 5 for more practical applications, the model could still maintain an optimal result obtained from the frontal region, reaching up to 99.17%. Amongst the two DL models, we found that CNN-GRU and CNN-LSTM performed similarly while CNN-GRU expended faster training time. In conclusion, the studied DL approaches overcame the influence of affective states in EEG-Based PI reported in the previous works.
|
|
| 13. |
- Gardenfors, Peter
(författare)
-
An Epigenetic Approach to Semantic Categories
- 2020
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - 2379-8920. ; 12:2, s. 139-147
-
Tidskriftsartikel (refereegranskat)abstract
- It is argued that early language learning in children emerges from five primary knowledge structures: Space, objects, actions, number and events. These structures constitute the basis for the semantic domains that are used to form categories that represent the meanings of early words. The domains are naturally modeled in conceptual spaces that are based on geometric notions rather than on symbolic representations. It is shown how these semantics domains can be used to generate an epigenetic model of language acquisition. The four first primary knowledge systems are used for prepositions, nouns, verbs and quantifiers respectively, while events form the meanings of declarative sentences. This semantic model leads to direct recommendations for how the model can be implemented in robots and other artificial systems.
|
|
| 14. |
- Liu, Jia, et al.
(författare)
-
Reconfiguration of cognitive control networks during a long-duration flanker task
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - 2379-8920. ; , s. 1-10
-
Tidskriftsartikel (refereegranskat)abstract
- Continuous task engagement generally leads to vigilance decrement and deteriorates task performance. However, how conflict effect is modulated by vigilance decrement has no consistent evidence, and little is known about the underlying neural mechanisms. Here we adopted an electroencephalogram dataset collected during a prolonged flanker task to examine the interactions between vigilance and congruency on behavioral performance and neural measures. Specifically, we extracted a sequence of ERPs using temporal principal component analysis (PCA) and performed functional network analysis with graph measures. Behavioral analysis results showed that behavioral performance deteriorated due to vigilance decrement, but the capability of conflict processing was maintained over time. Regarding the neural analysis results, the conflict effect reflected in P3a and P3b was changed and maintained respectively when affected by vigilance decrement. The theta band frontoparietal network was observed in the face of conflicting interference and the conflict effect for graph measures disappeared over time. These results demonstrated deteriorated task performance, impaired cognitive functions, and the reconfiguration of cognitive control networks during a prolonged flanker task. Our findings also support the evidence that temporal PCA and event-related network analysis might be efficient for the investigation of the neural dynamics of complex cognitive processes.
|
|
| 15. |
- Lourenço, Inês, 1994-, et al.
(författare)
-
A Biologically-Inspired Computational Model of Time Perception
- 2021
-
Ingår i: IEEE Transactions on Cognitive and Developmental Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2379-8920. ; , s. 1-1
-
Tidskriftsartikel (refereegranskat)abstract
- Time perception – how humans and animals perceive the passage of time – forms the basis for important cognitive skills such as decision-making, planning, and communication. In this work, we propose a framework for examining the mechanisms responsible for time perception. We first model neural time perception as a combination of two known timing sources: internal neuronal mechanisms and external (environmental) stimuli, and design a decision-making framework to replicate them. We then implement this framework in a simulated robot. We measure the robot’s success on a temporal discrimination task originally performed by mice to evaluate their capacity to exploit temporal knowledge. We conclude that the robot is able to perceive time similarly to animals when it comes to their intrinsic mechanisms of interpreting time and performing time-aware actions. Next, by analysing the behaviour of agents equipped with the framework, we propose an estimator to infer characteristics of the timing mechanisms intrinsic to the agents. In particular, we show that from their empirical action probability distribution we are able to estimate parameters used for perceiving time. Overall, our work shows promising results when it comes to drawing conclusions regarding some of the characteristics present in biological timing mechanisms.
|
|
