Download From Motor Learning to Interaction Learning in Robots by Olivier Sigaud, Jan Peters PDF

By Olivier Sigaud, Jan Peters

From an engineering viewpoint, the expanding complexity of robot platforms and the expanding call for for extra autonomously studying robots, has turn into crucial. This publication is essentially according to the profitable workshop “From motor to interplay studying in robots” held on the IEEE/RSJ overseas convention on clever robotic structures. the main goal of the e-book is to offer scholars the themes defined above an opportunity to start speedier and researchers a beneficial compandium.

Show description

Read Online or Download From Motor Learning to Interaction Learning in Robots PDF

Best robotics & automation books

Hard Disk Drive: Mechatronics and Control

The harddisk is likely one of the most interesting examples of the precision regulate of mechatronics, with tolerances below one micrometer completed whereas working at excessive pace. expanding call for for greater information density in addition to disturbance-prone working environments proceed to check designers mettle.

Robot Modeling and Control

In a well timed topic, arrived a few week after i ordered it and the booklet is in reliable conition.

LEGO MINDSTORMS NXT-G Programming Guide (Technology in Action)

LEGO Mindstorms NXT is the preferred robotic out there. James Kelly is the writer of the preferred web publication on NXT (http://thenxtstep. blogspot. com/) with over 30,000 hits a month. The NXT-G visible programming language for the NXT robotic is totally new and there are at present no books on hand at the topic.

Identifikation dynamischer Systeme: Methoden zur experimentellen Modellbildung aus Messdaten

Das Werk gibt eine ausführliche Einführung in die Identifikation linearer und nichtlinearer Ein- und Mehrgrößensysteme. Es werden zahlreiche Identifikationsverfahren vorgestellt, mit denen aus gemessenen Ein- und Ausgangssignalen ein mathematisches Modell zur Beschreibung des Systemverhaltens ermittelt werden kann.

Additional info for From Motor Learning to Interaction Learning in Robots

Example text

In: IEEE World Conference on Computational Intelligence, Proceedings, pp. 147–152. Anchorage, Alaska (1998) 74. : A real-world rational agent: Unifying old and new AI. Cogn. Sci. 27, 561–590 (2003) 75. : Adaptive fields: distributed representations of classically conditioned associations. Network 2(2), 189–206 (1991) 76. : Distributed adaptive control: The selforganization of structured behavior. Rob. Auton. Syst. 9, 181–196 (1993) 77. : Categorization, representations, and the dynamics of system-environment interaction: a case study in autonomous systems.

8 A). The output of the camera was its unique input connected to a neural model (Fig. 8 B). The processing hierarchy was composed of five-layers of leaky integrator units, providing them with a local transient memory, with both inhibitory intra-area and excitatory feed-forward inter-area connections. The convergence of the feed-forward connectivity and the temporal integration constant increase while moving up in the hierarchy. The objective function is evaluated autonomously at each layer. The weights of the feed-forward connections are updated by an online unsupervised learning algorithm (gradient descent) guided by the objective function.

The core of the synthetic insect system is the path integration sub-system. To integrate the path of a journey, information about the heading direction, and distance traveled must be stored in a path memory. Evidently, also a mechanism for the readout of the path memory must be available. Path memory and readout are both implemented based on the concept of population code regarding the neurophysiological constraints [22, 9]. The heading direction assessment is based on a model of the solar compass of insects.

Download PDF sample

Rated 4.78 of 5 – based on 34 votes