Towards Robust Layered Learning

Because imitation has shown to be able to drastically cut down the exploration space it has been embraced largely by the robotics community to speed up autonomous learning. This has been done mostly in fixed demonstratorimitator relationships, where a predefined demonstrator is performing the same action over and over again until the robot has learned it sufficiently. In practical multi-robot scenarios, however, the imitation process should not interrupt the observed robot as it will affect its autonomy. Therefore the imitating robot often has only a limited amount of behaviors of the same type to learn from. As this usually does not provide enough information for learning a generalized version of observed lowlevel actions, it can help the observer to optimize its strategy based on the recognized actions. In this case, first of all the imitating robot has to interpret the observed behavior in terms of its own behavior knowledge. This means that low-level observations have to be segmented into episodes of apparently similar behavior. For these episodes corresponding skills in the observing robot's own behavior repertoire have to be found. And for the episodes sequence corresponding state changes in the observing robot's own strategy have to be determined. How the former can be done has been shown by the authors in a previous paper. In this paper we will describe how our approach for Evolving Societies of Learning Autonomous Systems (ESLAS) is extended to be capable of multi-robot imitation. We demonstrate how the recognition results can be used in a multi-robot scenario to decentrally align the robots' behaviors, to speed up the overall learning process, and thus increase the overall autonomy.

show abstract

“…Thereby, we extend our previous layered architecture [13], [15] to be usable for imitation in multirobot scenarios.…”

Section: The Eslas Architecturementioning

confidence: 98%

Increasing the Autonomy of Mobile Robots by Imitation in Multi-robot Scenarios

Richert

Scheller

Koch

et al. 2009

2009 Fifth International Conference on Autonomic and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the lowest level an abstract skill learning module is used that can be connected to the strategy module independent of the actual strategy implementation, as described in the authors' previous work [8]. In the following we will provide a short overview and explain the necessary enhancements to the previous work.…”

Section: The Skill Learning Modulementioning

confidence: 99%

“…We will at first describe the architecture and the integration of autonomous strategies into our previous works [8]. Then we will describe the experiments in which a robot is forced to drive to a goal in a complex maze.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Increasing the Autonomy of Mobile Robots by On-line Learning Simultaneously at Different Levels of Abstraction

Richert

Luke

Nordmeyer

et al. 2008

Fourth International Conference on Autonomic and Autonomous Systems (ICAS'08)

Self Cite

View full text Add to dashboard Cite

We present a framework that is able to handle system and environmental changes by learning autonomously at different levels of abstraction. It is able to do so in continuous and noisy environments by 1) an active strategy learning module that uses reinforcement learning and 2) a dynamically adapting skill module that proactively explores the robot's own action capabilities and thereby providing actions to the strategy module. We present results that show the feasibility of simultaneously learning low-level skills and high-level strategies in order to reach a goal while reacting to disturbances like hardware damages. Thereby, the robot drastically increases its overall autonomy.

show abstract

“…The main contribution of this paper is an architecture concept that enables the robot to adapt and learn at the different abstraction layers while paying attention to metrics concerning society's attributes like spatial relative divergence, task allocation or local task performance. Although the architecture is not yet fully implemented, the skill learning part [19], the strategy, and the drive based imitation process [20] are already up and running, and have been evaluated by simulation and partly by our soccer robots Paderkicker [14]. This paper draws the whole picture explaining how emergence could happen in real environments with robots that adapt themselves locally while paying attention to the society's needs.…”

Section: Introductionmentioning

confidence: 99%

Adaptivity at every layer

Richert

Kleinjohann

2008

Proceedings of the 2008 International Workshop on Software Engineering for Adaptive and Self-Managing Systems

Self Cite

View full text Add to dashboard Cite

We describe a developmental architecture that enables individual robots to fulfill tasks assigned to the robot society in a robust, decentralized manner. The architecture is meant to show emergent properties according to Organic Computing principles that are positive for the society's robustness and performance. This requires the architecture to feature those adaptation and learning processes that are not only selfishly useful for the individual robot, but also incorporate the robot society's actual needs at all layers.

show abstract

Towards Robust Layered Learning

Cited by 4 publications

References 9 publications

Increasing the Autonomy of Mobile Robots by Imitation in Multi-robot Scenarios

Increasing the Autonomy of Mobile Robots by Imitation in Multi-robot Scenarios

Increasing the Autonomy of Mobile Robots by On-line Learning Simultaneously at Different Levels of Abstraction

Adaptivity at every layer

Contact Info

Product

Resources

About