Multi-objective dynamic optimization with genetic algorithms for automatic parking

Authors:
Darío Maravall;Javier de Lope
Affiliations:
Department of Artificial Intelligence, Faculty of Compute Science, Universidad Politécnica de Madrid, Campus de Montegancedo, 28660, Madrid, Spain;Department of Artificial Intelligence, Faculty of Compute Science, Universidad Politécnica de Madrid, Campus de Montegancedo, 28660, Madrid, Spain
Venue:
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Fuzzy-neural computation and robotics
Year:
2006

Citing 0
Cited 5

Hybridizing evolutionary computation and reinforcement learning for the design of almost universal controllers for autonomous robots

Neurocomputing
A Comparison of Genetic Algorithms and Particle Swarm Optimization for Parameter Estimation in Stochastic Biochemical Systems

EvoBIO '09 Proceedings of the 7th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics
Learning to Coordinate Multi-robot Competitive Systems by Stimuli Adaptation

IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part II: Bioinspired Applications in Artificial and Natural Computation
Analysis and solution of a predator-protector-prey multi-robot system by a high-level reinforcement learning architecture and the adaptive systems theory

Robotics and Autonomous Systems
A cultural algorithm applied in a bi-objective uncapacitated facility location problem

EMO'11 Proceedings of the 6th international conference on Evolutionary multi-criterion optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of automatic parking by a back-wheel drive vehicle, using a biomimetic model based on direct coupling between vehicle perceptions and actions. This problem is solved by means of a bio-inspired approach in which the vehicle controller does not need to know the car kinematics and dynamic, neither does it call for a priori knowledge of the environment map. The key point in the proposed approach is the definition of performance indices that for automatic parking happen to be functions of the strategic orientations to be injected, in real time, to the car-like robot controller. This solution leads to a dynamic multi-objective optimization problem, which is extremely hard to be dealt analytically. A genetic algorithm is therefore applied, thanks to which we obtain a very simple and efficient solution.