Frank Bomarius

KI 2008: Advances in Artificial Intelligence

The research in this thesis aims to enable robots to imitate humans. Learning by imitation is a fundamental part of human behaviour, since it allows humans to acquire motor skills simply by demonstration; seen from a robotic viewpoint you can easily “program” your fellow humans by showing them what to do. Would it not be great if the same mechanism could be used to program robots? A robot is programmed by specifying the torque of its motors. The torque can be regarded as the force or strength that is the result of muscles contracting or relaxing. Typical approaches to determine motor torques that will lead to a desired behaviour include setting them manually, i.e. on a trial-and-error basis, or specifying them by mathematical equations. Neither of these are intuitive to most humans, so most robot behaviours are programmed by engineers. However, if an engineer was to design a preprogrammed housekeeping robot, it would be very hard to program all the possible behaviours the robot could be expected to perform, even in such a limited domain. It is much more cost-efficient to make the robot learn what to do. This would allow the robot to adapt to its human owner, and not the other way around. Since humans easily learn new behaviours by imitating others, it would be ideal if humans could use the same technique to transfer motor knowledge to robots. I believe research in this area could be of great help to bridge the human-robot interaction gap that currently exists, so that you could have truly intelligent robots that could assist people in everyday life. To understand imitation learning, knowledge of psychology and neuroscience is required. The research in this thesis has taken an interdisciplinary approach, studying the desired mechanism on both a behavioural and neuroscientific level. I have focused on imitation in a musical setting. The system can both see and hear, and seeks to imitate the perceived behaviour. The application has been to create an intelligent virtual drummer, that imitates both the physical playing style (i.e. the movement of the arms) as well as the musical playing style (i.e. the groove) of the teacher. The virtual drummer will then both look and sound like a human drummer. The research in this thesis presents a multi-modal architecture for imitation of human movements. I have been working on simulated robots due to limits of time and money, however the principles of my research have been developed in a platformindependent way, so it should be applicable to real robots as well.

An Event-Driven Approach to Activity Recognition in Ambient Assisted Living

One central challenge of Ambient Assisted Living systems is reliable recognition of the assisted persons current behavior, so that adequate assistance services can be offered in a specific situation. In the context of emergency support, such a situation might be an acute emergency situation or a deviation from the usual behavior. To optimize prevention of emergencies, reliable recognition of charac teristic Activities of Daily Living (ADLs) is promising. In this paper, we present our approach to processing information for the detection of ADLs in the EMERGE project. The approach is based on our multi-agent activity recog nition framework EARS with its special definition language EARL. An evaluation with controlled experiments has proven its suitability.

Knowledge Management for Building Learning Software Organizations

Due to the steadily increasing demands of the market, strategic management of knowledge assets, or learning organizations, are becoming a must in industrial software development. This paper presents work done at Fraunhofer IESE, where learning organizations for software development organizations are being developed and transferred into industrial practice. It describes how learning organizations for the software domain can be built upon both mature approaches from Software Engineering like the experience factory model and industrial strength technology from knowledge management. A system to support the learning software organization is sketched and experiences regarding the implementation of this system and learning software organizations in general are presented.

Get Your Experience Factory Ready for the Next Decade--Ten Years after "How to Build and Run One"--

This one-day tutorial aims at industry practitioners, managers and developers alike, who want to learn more about how to successfully design, implement and run an Experience Factory, to systematically build up and manage the experience of an organization. State-of- the art methods and techniques on how to initially set-up or to further develop and improve an organization¿s Experience Factory are discussed. Participants should come from organizations (not only from the software domain) that are interested in implementing an Experience Factory to help effectively support improvement activities (such as TQM, ISO 9000, CMMI, SPICE, or TSP) to gain competitive advantages.