Evolution of Voronoi-Based Fuzzy Controllers

Kavka, Carlos; Schoenauer, Marc

doi:10.1007/978-3-540-30217-9_55

Cited by 5 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1). The "cell" associated to a model i is bounded by the adjacent sigmoids ψ ij , similar to the Voronoi cells of (Kavka & Schoenauer, 2004). However, adapting Voronoi sites incrementally to design appropriate boundaries is a complex coupled problem.…”

Section: Overview Of the Modelmentioning

confidence: 99%

“…Learning a deterministic partitioning of the input space x → i has been addressed before: (Bemporad et al, 2003) use a greedy search algorithm to find a polygonal partitioning constrained by an absolute error bound. (Kavka & Schoenauer, 2004) recently proposed a Voronoi cell partitioning with local fuzzy controllers learned with an Evolutionary Algorithm. Also decision trees (Model Trees, (Quinlan, 1992)) are possible choices to represent a partitioning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning discontinuities with products-of-sigmoids for switching between local models

Toussaint

Vijayakumar

2005

Proceedings of the 22nd International Conference on Machine Learning - ICML '05

View full text Add to dashboard Cite

Sensorimotor data from many interesting physical interactions comprises discontinuities. While existing locally weighted learning approaches aim at learning smooth functions, we propose a model that learns how to switch discontinuously between local models. The local responsibilities, usually represented by Gaussian kernels, are learned by a product of local sigmoidal classifiers that can represent complex shaped and sharply bounded regions. Local models are incrementally added. A locality prior constrains them to learn only local data-which is the key ingredient for incremental learning with local models.

show abstract

Section: Overview Of the Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning discontinuities with products-of-sigmoids for switching between local models

Toussaint

Vijayakumar

2005

Proceedings of the 22nd International Conference on Machine Learning - ICML '05

View full text Add to dashboard Cite

show abstract

“…The Voronoi diagram is used in other path planners including the roadmap [14] and HGVG algorithms [5]. A formal definition of the Voronoi diagram can be found in [5], [14], and [16]. Related to the Voronoi diagram is the Delaunay triangulation.…”

Section: Introductionmentioning

confidence: 99%

“…Related to the Voronoi diagram is the Delaunay triangulation. As defined in [16], the Delaunay triangulation T is the maximum planar subdivision of n points P = {P 1 …P n } such that no points of P are bounded by the circumcircle of any triangle in T. The Delaunay triangulation will be used to restrict the domain of our algorithms and will be expanded upon throughout this paper. Examples of each of these are shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

O3: An optimal and opportunistic path planner (with obstacle avoidance) using voronoi polygons

Coleman

Wunderlich

2008

2008 10th IEEE International Workshop on Advanced Motion Control

View full text Add to dashboard Cite

Abstract-Traditional mobile robot research focuses on a robot navigating its environment to reach a single goal while avoiding obstacles. This paper proposes a new method called O 3 to solve the challenges presented at the Intelligent Ground Vehicle Competition (IGVC) where a navigation course includes multiple goals to be found in an optimal order. The O 3 technique includes improvements on traditional path planning and obstacle avoidance techniques while providing an explicit ability to change course as obstacles are discovered. This method uses modern trajectories such as minimum-weighted Hamiltonian circuits, A* algorithm for obstacle avoidance, and local points of opportunity to update the globally optimal path using Voronoi polygons. Environmental mapping is also used to speed up the search algorithms in static environments. Overall, the O 3 technique exploits local points of opportunity while avoiding obstacles and ultimately finding a globally optimal path through an unknown environment.This methodology will be implemented on an autonomous web-based tour guide robot to serve the Internet community reviewing Elizabethtown College. This methodology can be extended to other research areas where multiple locations need to be traversed independent of their order such as city map, trip planners, and distribution networks (power, internet, etc) due to its balance between weighted graphs and obstacle avoidance (objects, traffic, construction, etc).

show abstract

“…In this work, we propose the Recurrent Fuzzy Voronoi (RFV) model, a representation for recurrent fuzzy systems. It is an extension of the FV model [13] that extends the application domain to include temporal problems. The FV model is a representation for fuzzy controllers based on Voronoi diagrams that can represent fuzzy systems with synergistic rules, fulfilling the ǫ-completeness property and providing a simple way to introduce a priory knowledge.…”

mentioning

confidence: 99%

Evolution of Voronoi based fuzzy recurrent controllers

Kavka

Roggero

Schoenauer

2005

Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

A fuzzy controller is usually designed by formulating the knowledge of a human expert into a set of linguistic variables and fuzzy rules. One of the most successful methods to automate the fuzzy controllers development process are evolutionary algorithms. In this work, we propose the Recurrent Fuzzy Voronoi (RFV) model, a representation for recurrent fuzzy systems. It is an extension of the FV model [13] that extends the application domain to include temporal problems. The FV model is a representation for fuzzy controllers based on Voronoi diagrams that can represent fuzzy systems with synergistic rules, fulfilling the ǫ-completeness property and providing a simple way to introduce a priory knowledge. In the proposed representation, the temporal relations are embedded by including internal units that provide feedback by connecting outputs to inputs. These internal units act as memory elements. In the RFV model, the semantic of the internal units can be specified together with the apriori rules. The geometric interpretation of the rules allows the use of geometric genetic operators during the evolution. The representation and the algorithms have been validated in two problems in the area of system identification and evolutionary robotics.

show abstract

Evolution of Voronoi-Based Fuzzy Controllers

Cited by 5 publications

References 7 publications

Learning discontinuities with products-of-sigmoids for switching between local models

Learning discontinuities with products-of-sigmoids for switching between local models

O3: An optimal and opportunistic path planner (with obstacle avoidance) using voronoi polygons

Evolution of Voronoi based fuzzy recurrent controllers

Contact Info

Product

Resources

About