Proceedings Article10.1109/IROS.2008.4651231
Structure from behavior in autonomous agents
Georg Martius,K. Fiedler,J.M. Herrmann +2 more
- 01 Sep 2008
- pp 858-862
TL;DR: A learning algorithm is described that generates behaviors by self-organization of sensorimotor loops in an autonomous robot that provides a discrete representation of the behavioral manifold of the robot and is suited to form building blocks for complex behaviors.
read more
Abstract: We describe a learning algorithm that generates behaviors by self-organization of sensorimotor loops in an autonomous robot The behavior of the robot is analyzed by a multi-expert architecture, where a number of controllers compete for the data from the physical robot Each expert stabilizes the representation of the acquired sensorimotor mapping in dependence of the achieved prediction error and forms eventually a behavioral primitive The experts provide a discrete representation of the behavioral manifold of the robot and are suited to form building blocks for complex behaviors
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Dissertation
Goal-Oriented Control of Self-Organizing Behavior in Autonomous Robots
Georg Martius
- 18 May 2010
TL;DR: Adaptive control algorithms within a dynamical systems approach for autonomous robots that cause the self-organization of coordinated behaviors without specific goals or particular information about the physical body are studied.
16
Intuitive control of mobile robots: an architecture for autonomous adaptive dynamic behaviour integration
TL;DR: A novel approach to human–robot control, with the potential for a change in the paradigm of robotic control, and a new level in the taxonomy of human in the loop systems is found.
13
Self-exploration of the Stumpy Robot with Predictive Information Maximization
Georg Martius,Luisa Jahn,Luisa Jahn,Helmut Hauser,Verena V. Hafner +4 more
- 22 Jul 2014
TL;DR: This work studies an intrinsic motivation system for behavioral self-exploration based on the maximization of the predictive information using the Stumpy robot, which is the first evaluation of the algorithm on a real robot.
•Proceedings Article
Tipping the Scales: Guidance and Intrinsically Motivated Behavior
Georg Martius,J. Michael Herrmann +1 more
- 01 Jan 2011
TL;DR: A systematic analysis of the learning algorithm in a robot control task is presented and its remarkable scalability with respect to the degrees of freedom of the system is demonstrated.
10
Proposal of an Intrinsically Motivated System for Exploration of Sensorimotor State Spaces
Matthias Kubisch,Manfred Hild,Sebastian Höfer +2 more
- 01 Jan 2010
TL;DR: This paper investigated the method of self-exploration by intrinsic motivation, whereby the individual is driven to select appropriate actions to support its own learning progress, implemented an unsupervised neural multi-expert architecture and tested the learning algorithm on an abstract artificial individual.
References
Perceiving, Acting and Knowing : Toward an Ecological Psychology
Robert E. Shaw,John D. Bransford +1 more
TL;DR: In this article, the authors express a collective attitude that a careful scrutiny of the fundamental tenets of contemporary psychology may be needed, and suggest specific faults in the foundations of an area are discussed and suggestions are made for remedying them.
2.6K
Can robots make good models of biological behaviour
TL;DR: It is argued that in building robot models biological relevance is more effective than loose biological inspiration; multiple levels can be integrated; that generality cannot be assumed but might emerge from studying specific instances; abstraction is better done by simplification than idealisation; accuracy can be approached through iterations of complete systems; that the model should be able to match and predict target behaviour; and that a physical medium can have significant advantages.
Self-organized acquisition of situated behaviors
TL;DR: Based on a quantitative measure of behavioral situatedness a learning dynamics is introduced which enables the controller to sustain the situatedness of the agent.
46
•Journal Article
Rocking stamper and jumping snake from a dynamical system approach to artificial life
TL;DR: This paper presents a general approach to the self-regulation of dynamical systems so that the design problem is circumvented and is implemented in an extremely robust and versatile algorithm for the parameter dynamics of the controller.
40
Homeostatic plasticity improves signal propagation in continuous-time recurrent neural networks.
Hywel T. P. Williams,Jason Noble +1 more
TL;DR: Analogous mechanisms are implemented in a variety of CTRNN architectures and are shown to increase node sensitivity and improve signal propagation, with implications for robotics.
27