Accurate robot simulation through system identification

Kyriacou, Theocharis; Nehmzow, Ulrich; Iglesias, Roberto; Billings, S.A.

doi:10.1016/j.robot.2008.01.005

Cited by 10 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have defined measures for energy, input/output ratio and entropy focusing on the question whether there is an optimal robot for a given environment. Box et al (1994)) to arrive at a general model of behaving robot systems Kyriacou et al 2008), but these models contain many parameters for fitting and parameters do not have any direct physical meaning. Our attempts stop short of a complete model identification approach, which does not seem to be required for our system.…”

Section: Discussionmentioning

confidence: 99%

Behavioral analysis of differential hebbian learning in closed-loop systems

et al. 2010

View full text Add to dashboard Cite

Understanding closed loop behavioral systems is a non-trivial problem, especially when they change during learning. Descriptions of closed loop systems in terms of information theory date back to the 1950s, however, there have been only a few attempts which take into account learning, mostly measuring information of inputs. In this study we analyze a specific type of closed loop system by looking at the input as well as the output space. For this, we investigate simulated agents that perform differential Hebbian learning (STDP). In the first part we show that analytical solutions can be found for the temporal development of such systems for relatively simple cases. In the second part of this study we try to answer the following question: How can we predict which system from a given class would be the best for a particular scenario? This question is addressed using energy, input/output ratio and entropy measures and investigating Tomas Kulvicius and Christoph Kolodziejski have contributed equally to this work. their development during learning. This way we can show that within well-specified scenarios there are indeed agents which are optimal with respect to their structure and adaptive properties. T. Kulvicius (B)·

show abstract

Section: Discussionmentioning

confidence: 99%

Behavioral analysis of differential hebbian learning in closed-loop systems

et al. 2010

View full text Add to dashboard Cite

show abstract

“…The occurrence of isolated and infrequent errors is not generally a problem. However, the accumulation of such errors can lead robots to unacceptable levels of deviations, [Kyriacou et al, 2008]. Thus, this situation has a huge potential to frustrate the expectations of students and negatively affect their learning process.…”

Section: Congresso Brasileiro De Informática Na Educação (Cbie 20mentioning

confidence: 99%

“…The work of Kyriacou et al (2008) argues that a robot`s behaviour is affeted by three aspects: the robot hardware, the implemented algorithm and the environment where this robot operates. According to Kyriacou et al, these three aspect generate a complex non-linear system that does not ensure that results of simulation experiments can be replicated in real environments.…”

Section: From Virtual To Real Robotsmentioning

confidence: 99%

A Study about the Transition of Simulated Algorithms to Real Robotics and its Application in Distance Learning

Siebra¹,

Souza²

2014

Anais Do XXV Simpósio Brasileiro De Informática Na Educação (SBIE 2014)

View full text Add to dashboard Cite

show abstract

“…Some researchers have used genetic algorithms and evolutionary programming [5] to make sensors work in their simulations; others have tried m athem ati cal models [20] of sensors. Simplistic, in the sense of being easy to program, models have been tried [12] but have not led to satisfactory results.…”

Section: Generalmentioning

confidence: 99%

“…In 2008 Kyriacou et al [20] said th a t simulators are useful tools for developing robot behavior. However they also said th a t there are considerable differences between the behavior of the robot in the simulator and the behavior of the robot in the real world.…”

Section: Generalmentioning

confidence: 99%

Improving Sonar Sensor Fidelity in a Robot Simulator.

Kranz¹

View full text Add to dashboard Cite

Accurate robot simulation through system identification

Cited by 10 publications

References 16 publications

Behavioral analysis of differential hebbian learning in closed-loop systems

Behavioral analysis of differential hebbian learning in closed-loop systems

A Study about the Transition of Simulated Algorithms to Real Robotics and its Application in Distance Learning

Improving Sonar Sensor Fidelity in a Robot Simulator.

Contact Info

Product

Resources

About