Velocity Control of an Omnidirectional RoboCup Player with Recurrent Neural Networks

Oubbati, Mohamed; Schanz, Michael; Buchheim, Thorsten; Levi, Paul

doi:10.1007/11780519_70

Cited by 9 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of this training procedure can be summarized as follows: find the weights of the network using the teacher signal, which brings the robot from the actual velocity at time (n) to a future velocity at time (n ? 1) [20]. The advantage of this approach is that, no knowledge about the dynamic model is required, since the controller is designed only by learning input/output data collected from the robot.…”

Section: Adaptive Motion Control With Esnsmentioning

confidence: 99%

A neural framework for adaptive robot control

Oubbati

Palm

2009

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

This paper investigates how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems such as motion control and behavior generation. We have designed an adaptive motion control approach based on a novel recurrent neural network, called Echo state networks. The advantage is that no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters in the robot. To generate the robot behavior over time, we adopted a biologically inspired approach called neural fields. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction, which navigates a mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles.

show abstract

Section: Adaptive Motion Control With Esnsmentioning

confidence: 99%

A neural framework for adaptive robot control

Oubbati

Palm

2009

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, a equal amount of literature has applied machine learning to a robot's kinematics, dynamics, or structure. The lion's share of this work involves gait development (such as [19,18]), with some work on kicking [6,32], head actuation [5] and omnidirectional velocity control [17]. Third, about sixteen papers have concerned themselves with learning higher-level behaviors (for example [26,28]).…”

Section: Machine Learning At Robocupmentioning

confidence: 99%

Towards Rapid Multi-robot Learning from Demonstration at the RoboCup Competition

Freelan

Wicke

Sullivan

et al. 2015

RoboCup 2014: Robot World Cup XVIII

View full text Add to dashboard Cite

Abstract. We describe our previous and current efforts towards achieving an unusual personal RoboCup goal: to train a full team of robots directly through demonstration, on the field of play at the RoboCup venue, how to collaboratively play soccer, and then use this trained team in the competition itself. Using our method, HiTAB, we can train teams of collaborative agents via demonstration to perform nontrivial joint behaviors in the form of hierarchical finite-state automata. We discuss HiTAB, our previous efforts in using it in RoboCup 2011 and 2012, recent experimental work, and our current efforts for 2014, then suggest a new RoboCup Technical Challenge problem in learning from demonstration.Imagine that you are at an unfamiliar disaster site with a team of robots, and are faced with a previously unseen task for them to do. The robots have only rudimentary but useful utility behaviors implemented. You are not a programmer. Without coding them, you have only a few hours to get your robots doing useful collaborative work in this new environment. How would you do this?Our interest lies in rapid, real-time multi-robot training from demonstration. Here a single human trainer teaches a team of robots, via teleoperation, how to collectively perform tasks in previously unforeseen environments. This is difficult for two reasons. First, nontrivial behaviors can present a high-dimensional space to learn, yet one can only provide a few samples, as online training samples are costly to collect. This is a worst case for the so-called "curse of dimensionality". Second, when training multiple interactive robots, even if you can quantify the emergent macro-level group behavior you wish to achieve, in order to do learning, each agent needs to know the micro-level behavior he is being asked to do. One may have a micro→macro function (a simulator), but it is unlikely that one has the inverse macro→micro function, resulting in what we call the "multiagent inverse problem". These two challenges mean that real-time multi-robot learning from demonstration has proven very difficult and has a very sparse literature.Over the past several years we have participated in the Kid-Size Humanoid League with a single objective: to successfully do a personal RoboCup-style technical challenge of our own invention, independent of those offered at RoboCup: can we train multiple generic robots, through demonstration on the field, how to play collaborative soccer at RoboCup solely within the preparatory time prior to the competition itself ?

show abstract

“…The RC methods were originally designed to predict future inputs, and also exhibited a number of remarkable properties, like real-time recognition and prediction [16], handling real-world data [17], [18], [19], [20], universality in learning any temporal function of the input [16], the ability to extract different high-level information (spatial or temporal) from a single reservoir [21]. In addition to outperforming previous algorithms in performing temporal tasks [16], they also appear biologically more plausible than other conventional methods.…”

mentioning

confidence: 99%

Hierarchical Bayesian reservoir memory

Nouri

Nikmehr

2009

2009 14th International CSI Computer Conference

View full text Add to dashboard Cite

In a quest for modeling human brain, we are going to introduce a brain model based on a general framework for brain called Memory-Prediction Framework. The model is a hierarchical Bayesian structure that uses Reservoir Computing methods as the state-of-theart and the most biological plausible Temporal Sequence Processing method for online and unsupervised learning. So, the model is called Hierarchical Bayesian Reservoir Memory (HBRM). HBRM uses a simple stochastic gradient descent learning algorithm to learn and organize common multi-scale spatio-temporal patterns/features of the input signals in a hierarchical structure in an unsupervised manner to provide robust and real-time prediction of future inputs. We suggest HBRM as a real-time high-dimensional stream processing model for the basic brain computations. In this paper we will describe the model and assess its prediction accuracy in a simulated real-world environment.

show abstract

Velocity Control of an Omnidirectional RoboCup Player with Recurrent Neural Networks

Cited by 9 publications

References 4 publications

A neural framework for adaptive robot control

A neural framework for adaptive robot control

Towards Rapid Multi-robot Learning from Demonstration at the RoboCup Competition

Hierarchical Bayesian reservoir memory

Contact Info

Product

Resources

About