No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Scaling High Level Interactions Between Humans and Robots1
Abstract
Much of the current research in human-robot interaction is concerned with single systems and single or few users. These systems and their interfaces are generally tightly- coupled and well-defined. For large-scale human-robot interactions, it may not be possible to know the systems in advance of designing the interface for potential human interaction. This presents a difficult goal for allowing multiple users to interact with many possibly unknown systems. In this paper, we present an interaction infrastructure aligned with providing this interface. It operates in two phases accommodating both many-to-many interactions and allowing for generalized and more personal one-to-one interaction between users and robotic systems. Our previous research has demonstrated the infrastructure to scale to a large number of users and several systems in simulation. The experiments in this paper substantiate these results in a smaller-scale real robotic environment.
Multi-robot behavior adaptation mechanism based on cooperative-neutral-competitive fuzzy-Q learning is proposed for coordinating local communication atmospheres in humans-robots interaction, in which the communication atmosphere is represented by a two-layer fuzzy fusion model and is visualized by shape-color-fill-wave graphics. It aims to realize smooth communication between humans and robots in the local and global communication atmosphere coexistent interaction by decreasing the response time of robots and social distance between humans and robots, as well as visualizing the communication atmosphere. Experiments on multi-robot behavior adaptation are performed in a virtual home party environment. Results show that the proposal saves 47 and 103 learning steps (i.e., the learning rate is increased by 72 % and 85 %) compared to fuzzy production rule based friend-Q learning (FPRFQ) and friend-Q learning (FQ), respectively; the distance between human-generated atmosphere and robot-generated atmosphere is 3 times and 7 times shorter than the FPRFQ and the FQ, respectively. Additionally, subjective estimation of graphic visualization of the atmosphere through questionnaire obtains 85.5 % accuracy for shape, 77.2 % for color, 65.3 % for fill, and 91.7 % for wave. The proposed mechanism is being extended to the robot behavior adaptation to international communication atmosphere, where the atmosphere is generated by people from different countries with different cultural backgrounds.
A web-based dispatching system for autonomous mobile service robots is presented. The system is composed of an extensible number of physical and software components. They represent and control objects like robots, doors, cam-eras and elevators or software components like a job sched-uler and a database manager. Components communicate via radio link and Ethernet. Autonomously operating compo-nents and additional security features result in an adaptable, highly available, multi user/multi service system. In contrast to other web-based systems the mobile robots act really au-tonomously and are not teleoperated by users.
Flexible user interfaces that can be customized to meet the needs of the task at hand are particularly important for real-time group collaboration. This paper presents the user interface of the DISCIPLE (DIstributed System for Collaborative Information Processing and LEarning) system for synchronous groupware along with the multimodal human-computer interface enhancement. DISCIPLE supports sharing of JavaBeans-compliant components [17], i.e., beans and applets, which at runtime get imported into the shared workspace and can be interconnected into more complex components. As a result, importing various components allows user tailoring of the human-computer interface. We present a software architecture for customization of both grouplevel and application-level interfaces. The applicationlevel interface includes a management system for sharing multiple modalities across concurrent applications. This multimodal management system is loadable on demand yet strongly embedded in the DISCIPLE f...
We have completed and exercised a communication framework called;
CHI (CLOS to HTML Interface) by which agents can communicate with humans.;
CHI follows HTTP (HyperText Transfer Protocol) and produces HTML (HyperText;
Markup Language) for use by WWW (World-Wide Web) browsers. CHI enables the;
rapid and dynamic construction of interface mechanisms. The essence of CHI is;
automatic registration of dynamically generated interface elements to named objects;
in the agent's internal environment. The agent can access information in these;
objects at will. State is preserved, so an agent can pursue branching interaction;
sequences, activate failure recovery behaviors, and otherwise act opportunistically to;
maintain a conversation. The CHI mechanism remains transparent in multi-agent,;
multi-user environments because of automatically generated unique identifiers built;
into the CHI mechanism. In this paper we discuss design, language, implementation,;
and extension issues, and, by way of illustration, examine the use of the general;
CHI/HCHI mechanism in a specific international electronic commerce system. We;
conclude that the CHI mechanism is an effective, efficient, and extensible means of;
the agent/human communication.
Using robots for surveillance and reconnaissance applications requires a versatile connection between the human operator and robotic hardware. Some application domains require a fully teleoperated system while others may benefit by giving robots more autonomy. This paper describes a robotic control architecture which merges both paradigms. The whole scheme is implemented using the miniature Scout robot and involves a suite of user interfaces that can be tailored to specific surveillance and reconnaissance missions. Hardware capabilities are presented and a visual servoing strategy, important for semi-autonomous Scout operation, is discussed.
Let me Introduce you to Everyone: An Infrastructure for Scalable Human-System Interaction
- G 'day Mate
G'day Mate. Let me Introduce you to Everyone: An
Infrastructure for Scalable Human-System Interaction.
Technical Report, CRES-02-004, Center for Robotic and
Embedded Systems, University of Southern California,
August.
An Infrastructure for Large-Scale Human-Robot Interaction
- A Tews
- G Sukhatme
- M Matari
Tews, A., Sukhatme, G., and Matari, M. 2002. An
Infrastructure for Large-Scale Human-Robot Interaction.
Technical Report, CRES-02-001, Center for Robotic and
Embedded Systems, University of Southern California.