A case study for learning behaviors in mobile robotics by evolutionary fuzzy systems

Mucientes, Manuel; Alcalá‐Fdez, Jesús; Alcalá, Rafael; Casillas, Jorge

doi:10.1016/j.eswa.2009.06.095

Cited by 13 publications

(14 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These variables usually need to be obtained through a preprocessing of the sensors data. For example, in [3], [4] two successful approaches to learn fuzzy rules for the control of a robot in two different tasks were described. In both cases, the learned rules were conventional fuzzy rules and all the input variables were defined by a human expert.…”

Section: Quantified Fuzzy Rules (Qfrs) a Motivation For Mobile Rmentioning

confidence: 99%

Iterative Rule Learning of Quantified Fuzzy Rules for control in mobile robotics

Rodríguez-Fdez

Mucientes

Bugarín

2011

2011 IEEE 5th International Workshop on Genetic and Evolutionary Fuzzy Systems (GEFS)

View full text Add to dashboard Cite

Learning controllers in mobile robotics usually requires expert knowledge to define the input variables. However, these definitions could be obtained within the algorithm that generates the controller. This cannot be done using conventional fuzzy propositions, as the expressiveness that is necessary to summarize tens or hundreds of input variables in a proposition is high. In this paper the Quantified Fuzzy Rules (QFRs) model has been used to transform low-level input variables into highlevel input variables, which are more appropriate inputs to learn a controller. The algorithm that learns QFRs is based on the Iterative Rule Learning approach. The algorithm has been tested learning a controller in mobile robotics and using several complex simulated environments. Results show a good performance of our proposal, which has been compared with another three approaches.

show abstract

Section: Quantified Fuzzy Rules (Qfrs) a Motivation For Mobile Rmentioning

confidence: 99%

Iterative Rule Learning of Quantified Fuzzy Rules for control in mobile robotics

Rodríguez-Fdez

Mucientes

Bugarín

2011

2011 IEEE 5th International Workshop on Genetic and Evolutionary Fuzzy Systems (GEFS)

View full text Add to dashboard Cite

show abstract

“…In [12] 360 laser sensor beams are used as input data, and are heuristically combined into 8 sectors as inputs to the learning algorithm. On the other hand, in [9,13,14,15,16,18,19,21] the input variables of the learning algorithm are defined by an expert. Moreover, in [13,14,16,18,20] the evaluation function of the evolutionary algorithm must be defined by an expert for each particular behavior.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, in order to evaluate the performance of a controller with a numerical value a general quality measure was defined. It is based on the error measure defined in [15], but including the number of blockades: (18) where d wall is the reference distance to the wall (50 cm) and v max is the maximum value of the velocity (50 cm/s). The higher the quality, the better the controller.…”

Section: Comparison and Statistical Significancementioning

confidence: 99%

Learning fuzzy controllers in mobile robotics with embedded preprocessing

Rodríguez-Fdez¹,

Mucientes²,

Bugarín³

2015

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

The automatic design of controllers for mobile robots usually requires two stages. In the first stage, sensorial data are preprocessed or transformed into high level and meaningful values of variables which are usually defined from expert knowledge. In the second stage, a machine learning technique is applied to obtain a controller that maps these high level variables to the control commands that are actually sent to the robot. This paper describes an algorithm that is able to embed the preprocessing stage into the learning stage in order to get controllers directly starting from sensorial raw data with no expert knowledge involved. Due to the high dimensionality of the sensorial data, this approach uses Quantified Fuzzy Rules (QFRs), that are able to transform low-level input variables into high-level input variables, reducing the dimensionality through summarization. The proposed learning algorithm, called Iterative Quantified Fuzzy Rule Learning (IQFRL), is based on genetic programming. IQFRL is able to learn rules with different structures, and can manage linguistic variables with multiple granularities. The algorithm has been tested with the implementation of the wall-following behavior both in several realistic simulated environments with different complexity and on a Pioneer 3-AT robot in two real environments. Results have been compared with several well-known learning algorithms combined with different data preprocessing techniques, showing that IQFRL exhibits a better and statistically significant performance. Moreover, three real world applications for which IQFRL plays a central role are also presented: path and object tracking with static and moving obstacles avoidance.

show abstract

“…This case study is focused on the development of the wallfollowing robot as explained in 48 . Wall-following behavior is well known in mobile robotics.…”

Section: A Case Studymentioning

confidence: 99%

“…For the wall-following robot controller, we used 'minimum' connection method (AND : MIN), minimum activation method (ACT : MIN), and maximum accumulation method (ACCU : MAX). We implemented the RB generated in 48 by the algorithm WCOR 49 . Each entry in the RB was converted to a single FCL rule.…”

Section: Robot Fuzzy Control Systemmentioning

confidence: 99%

jFuzzyLogic: a Java Library to Design Fuzzy Logic Controllers According to the Standard for Fuzzy Control Programming

Cingolani¹,

Alcalá‐Fdez²

2013

IJCIS

167

View full text Add to dashboard Cite

Fuzzy Logic Controllers are a specific model of Fuzzy Rule Based Systems suitable for engineering applications for which classic control strategies do not achieve good results or for when it is too difficult to obtain a mathematical model. Recently, the International Electrotechnical Commission has published a standard for fuzzy control programming in part 7 of the IEC 61131 norm in order to offer a well defined common understanding of the basic means with which to integrate fuzzy control applications in control systems. In this paper, we introduce an open source Java library called jFuzzyLogic which offers a fully functional and complete implementation of a fuzzy inference system according to this standard, providing a programming interface and Eclipse plugin to easily write and test code for fuzzy control applications. A case study is given to illustrate the use of jFuzzyLogic.

show abstract

A case study for learning behaviors in mobile robotics by evolutionary fuzzy systems

Cited by 13 publications

References 53 publications

Iterative Rule Learning of Quantified Fuzzy Rules for control in mobile robotics

Iterative Rule Learning of Quantified Fuzzy Rules for control in mobile robotics

Learning fuzzy controllers in mobile robotics with embedded preprocessing

jFuzzyLogic: a Java Library to Design Fuzzy Logic Controllers According to the Standard for Fuzzy Control Programming

Contact Info

Product

Resources

About