Active adaptation in human-agent collaborative interaction

When a human user interacts with an adaptive agent to achieve human-agent collaboration, active adaptation is considered to be one of the critical characteristics of the agent. In order to investigate the principal features of active adaptation, we developed a human-agent collaborative experimental environment called WAITER (waiter agent interactive training experimental restaurant) and conducted two types of experiments, a Wizard of OZ (WOZ) agent experiment and an autonomous agent experiment. The objective of these experiments is to observe how human users perceive the agents and change their instructions when interacting with adaptive agents. The results indicate that humans can recognize changes in the agent’s actions and change their instruction methods accordingly. This implies that active adaptation of the agents may encourage the adaptation of the human users and help to build an adaptation loop between them. The experimental results also suggest that active adaptation may play an important role in a human-agent collaborative task.     

WOZ experiments for understanding mutual adaptation

A robot that is easy to teach not only has to be able to adapt to humans but also has to be easily adaptable to. In order to develop a robot with mutual adaptation ability, we believe that it will be beneficial to first observe the mutual adaptation behaviors that occur in human–human communication. In this paper, we propose a human–human WOZ (Wizard-of-Oz) experiment setting that can help us to observe and understand how the mutual adaptation procedure occurs between human beings in nonverbal communication. By analyzing the experimental results, we obtained three important findings: alignment-based action, symbol-emergent learning, and environmental learning.     

Bio-inspired robotic impedance adaptation for human-robot collaborative tasks

To improve the robotic flexibility and dexterity in a human-robot collaboration task,it is important to adapt the robot impedance in a real-time manner to its p...     

Using emotions for the development of human-agent societies

Human-agent societies refer to applications where virtual agents and humans coexist and interact transparently into a fully integrated environment. One of the most important aspects in this kind of applications is including emotional states of the agents (humans or not) in the decision-making process. In this sense, this paper presents the applicability of the JaCalIVE (Jason Cartago implemented intelligent virtual environment) framework for developing this kind of society. Specifically, the paper presents an ambient intelligence application where humans are immersed into a system that extracts and analyzes the emotional state of a human group. A social emotional model is employed to try to maximize the welfare of those humans by playing the most appropriate music in every moment.     

Probing changes in neural interaction during adaptation

A procedure is developed to probe the changes in the functional interactions among neurons in primary motor cortex of the monkey brain during adaptation. A monkey is trained to learn a new skill, moving its arm to reach a target under the influence of external perturbations. The spike trains of multiple neurons in the primary motor cortex are recorded simultaneously. We utilize the methodology of directed transfer function, derived from a class of linear stochastic models, to quantify the causal interactions between the neurons. We find that the coupling between the motor neurons tends to increase during the adaptation but return to the original level after the adaptation. Furthermore, there is evidence that adaptation tends to affect the topology of the neural network, despite the approximate conservation of the average coupling strength in the network before and after the adaptation.     

Analysis of interaction dynamics in collaborative and distributed design process

This paper proposes a computational interaction analysis approach for extraction of emergent patterns and organization structures during collaborative and distributed design process based on its emergent state-problems. A better source of information on both collaborative and distributed design process as a time-based activity and the agent-agent interactions during the design process will allow design researchers to develop richer models of designing which in turn will provide the basis for a better understanding of collaborative and distributed design process and developing intelligent tools to support this process. Therefore, the proposed approach consists of discerning from the real interactions the different state-problems characterizing the mentioned process. The modelling of interactions corresponding to state-problems, permitted to observe the emergent patterns of collaborative and distributed design process: micro-groups and pivot agent. The collaborative and distributed design process is characterized by the new micro-group formation on the one hand, and by their evolution in the time on the other. Based on the properties of interaction, the approach has discerned three types of cooperation: complete, bilateral and quasi null. Results from some real collaborative and distributed design process, allow us to observe certain properties related to micro-groups, such as self-organization, dynamics and self-similarity. Self-organization results from interaction among adaptive human agents. It is an emergent structuration in response to non-linear collaborative and distributed design process. Dynamics results from the variation of micro-groups formation and the collaborative and distributed design process seems to articulate around one or several pivot agents. Self-similarity results from the similar emergent pattern in every discussion. This research served as core for developments of multi-agents system ISIAD (Intelligent System for Interactions Analysis in Design).     

Group mirrors to support interaction regulation in collaborative problem solving

Two experimental studies test the effect of group mirrors upon quantitative and qualitative aspects of participation in collaborative problem solving. Mirroring tools consist of a graphical representation of the group’s actions which is dynamically updated and displayed to the collaborators. In addition, metacognitive tools display a standard for desirable behavior. Results show that a mirroring tool did not substantively affect the behavior of subjects while a metacognitive tool led to increased participation in dialogue, including more frequent and precise planning.     

Virtual interpersonal touch: Haptic interaction and copresence in collaborative virtual environments

As digital communication becomes more commonplace and sensory rich, understanding the manner in which people interact with one another is crucial. In the current study, we examined the manners in which people touch digital representations of people, and compared those behaviors to the manner in which they touch digital representations of nonhuman objects. Results demonstrated that people used less force when touching people than other nonhuman objects, and that people touched the face with less force than the torso area. Finally, male digital representations were touched with more force than female representations by subjects of both genders. We discuss the implications of these data to the development of haptic communication systems as well as for a methodology of measuring the amount of copresence in virtual environments.

Carpeno: interfacing remote collaborative virtual environments with table-top interaction

Creativity is enhanced by communication and collaboration. Thus, the increasing number of distributed creative tasks requires better support from computer-mediated communication and collaborative tools. In this paper we introduce “Carpeno”, a new system for facilitating intuitive face-to-face and remote collaboration on creative tasks. Normally the most popular and efficient way for people to collaborate is face-to-face, sitting around a table. Computer augmented surface environments, in particular interactive table-top environments, are increasingly used to support face-to-face meetings. They help co-located teams to develop new ideas by facilitating the presentation, manipulation, and exchange of shared digital documents displayed on the table-top surface. Users can see each other at the same time as the information they are talking about. In this way the task space and communication space can be brought together in a more natural and intuitive way. The discussion of digital content is redirected from a computer screen, back to a table where people can gather around. In contrast, collaborative virtual environments (CVE) are used to support remote collaboration. They frequently create familiar discussion scenarios for remote interlocutors by utilizing room metaphors. Here, virtual avatars and table metaphors are used, where the participants can get together and communicate with each other in a way that allows behaviour that is as close to face-to-face collaboration as possible. The Carpeno system described here combines table-top interaction with a CVE to support intuitive face-to-face and remote collaboration. This allows for simultaneous co-located and remote collaboration around a common, interactive table.

Agent-based modeling of collaborative interaction in ubiquitous learning environment using local dynamic behavior

This paper focuses on modeling collaborative interaction in Ubiquitous Learning Environment (ULE) based on the assumption that the collaborative interaction can be perceived through interpersonal interactions, which can be described as local dynamic behaviors of the team. In this paper, the collaborative interaction is collected from the experiment with 50 students having 5 members per team. Then the collaborative interaction is coded with 16 participation shift (P-shifts) from 5 different types of turns including turn receiving, turn claiming, turn usurping, turn continuing, and turn noreturning to represent the participation status of each member. Three types of participation statuses used in this paper are the contributor, the target and the unaddressed recipient. Then the discovered local dynamic behavior is used for constructing the model by using agent-based modeling. The model consists of student agents working together according to the discovered behavior. Then, the constructed model is verified by comparing the actual behavior with the simulated behavior. Finally, the comparison result shows that the constructed model can reasonably be the model for modeling collaborative interaction in ULE.     

Simulating collaborative systems by means of awareness of interaction among intelligent agents

New specific collaboration models for distributive systems are needed for enabling effective collaboration processes between users of these dynamic environments. However, collaboration in distributive systems depends on several elements such as a negotiation mechanism, a load-balancing strategy, a mutual exclusion mechanism, and a learning strategy. Each of these elements should be analyzed separately in terms of efficiency and effectiveness in order to improve these two features in the global collaborative system. This paper presents a multi-agent based simulation tool and a simulation methodology used to evaluate the efficiency and effectiveness of a collaborative system by analyzing both the global system of each of the strategies or mechanisms involved in the system. Intelligent agents used in the simulation make use of the concept of awareness of interaction for quantifying the degree, nature and quality of the interaction between the agents.     

User interaction in digital libraries: coping with diversity through adaptation

User interface adaptations can be used to address several user interaction challenges in the development of digital library systems. This paper: (a) examines some of the intrinsic characteristics of digital library systems; (b) identifies some of the key Human–Computer Interaction (HCI) challenges in relation to design and architectural abstraction for user interfaces to digital library systems; and (c) develops an argumentation for adaptations in digital library systems. By drawing parallels to recent HCI research into adaptable and adaptive user interaction, the paper illustrates potential areas in which user interface adaptation can provide a useful technique for advancing the quality of human interaction with a digital library system. Received: 18 December 1998 / Revised: 31 May 1999     

Ten challenges for making automation a "team player" in joint human-agent activity

We propose 10 challenges for making automation components into effective "team players" when they interact with people in significant ways. Our analysis is based on some of the principles of human-centered computing that we have developed individually and jointly over the years, and is adapted from a more comprehensive examination of common ground and coordination.     

Extracting complexes that ensure sufficient structural conditions for system mutual informational agreement in multicomplex systems

We study the possibility to organize a solution in a network of arbitrary structure for a given set of interacting tasks with fault- and transient-fault-tolerance characteristics specified for each problem. For each problem, we distinguish a complex where all computers solve copies of this task (task replication), exchange results, and choose the correct one. The key problem in such computations is system mutual information agreement (SMIA) that ensures coherence of system information in all computers of all complexes under admissible faults. We derive sufficient structural conditions for reaching such a MIA and methods for finding them. We propose an algorithm for distinguishing complexes corresponding to problems being solved in computer networks (if at all possible).     

A population randomization-based multi-objective genetic algorithm for gesture adaptation in human-robot interaction

In recent years,vision-based gesture adaptation has attracted great attention from many experts in the field of human-robot interaction,and many methods have be...     

Speech-based interaction in multitask conditions: impact of prompt modality

Speech-based interaction is often recognized as appropriate for hands-busy, eyes-busy multitask situations. The objective of this study was to explore prompt-guided speech-based interaction and the impact of prompt modality on overall performance in such situations. A dual-task paradigm was employed, with tracking as a primary task and speech-based data input as a secondary task. There were three tracking conditions: no tracking, basic, and difficult tracking. Two prompt modalities were used for the speech interaction: a dialogue with spoken prompts and a dialogue with visual prompts. Data entry duration was longer with the speech prompts than with the visual prompts, regardless of whether or not there was tracking or its level of difficulty. However, when tracking was difficult, data entry duration was similar for both spoken and visual prompts. Tracking performance was also affected by the prompt modality, with poorer performance obtained when the prompts were visual. The findings are discussed in terms of multiple resource theory and the possible implications for speech-based interactions in multitask situations. Actual or potential applications of this research include the design of speech-based dialogues for multitask situations such as driving and other hands-busy, eyes-busy situations.     

Deep collaborative filtering with social promoter score-based user-item interaction: a new perspective in recommendation

Most of the existing recommender systems understand the preference level of users based on user-item interaction ratings. Rating-based recommendation systems mostly ignore negative users/reviewers (who give poor ratings). There are two types of negative users. Some negative users give negative or poor ratings randomly, and some negative users give ratings according to the quality of items. Some negative users, who give ratings according to the quality of items, are known as reliable negative users, and they are crucial for a better recommendation. Similar characteristics are also applicable to positive users. From a poor reflection of a user to a specific item, the existing recommender systems presume that this item is not in the user’s preferred category. That may not always be correct. We should investigate whether the item is not in the user’s preferred category, whether the user is dissatisfied with the quality of a favorite item or whether the user gives ratings randomly/casually. To overcome this problem, we propose a Social Promoter Score (SPS)-based recommendation. We construct two user-item interaction matrices with users’ explicit SPS value and users’ view activities as implicit feedback. With these matrices as inputs, our attention layer-based deep neural model deepCF_SPS learns a common low-dimensional space to present the features of users and items and understands the way users rate items. Extensive experiments on online review datasets present that our method can be remarkably futuristic compared to some popular baselines. The empirical evidence from the experimental results shows that our model is the best in terms of scalability and runtime over the baselines.

     

Improving learner quality of experience by content adaptation based on network conditions

Apart from user characteristics, properties of the network over which the content is delivered and device on which the content is displayed affect end-user perceived quality. This paper presents a learner quality of experience (QoE) model that apart from the user-related content adaptation, considers delivery performance-based content personalisation in order to improve user experience when interacting with an online learning system.A comparison-based study on the benefit of using the proposed learner QoE model in adaptive and personalized education was conducted involving the original AHA! and QoEAHA – a version of AHA! enhanced with the learner QoE model. Testing results demonstrate significant benefits in terms of learning achievement, learning performance, learner navigation and user QoE in favour of the learner QoE model-enhanced solution.