Multi-objective dynamic optimization with genetic algorithms for automatic parking

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 carlike robot controller. This solution leads to a dynamic multiobjective 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.

Artificial immune system in dynamic environments solving time-varying non-linear constrained multi-objective problems

“…When stationary MEAs are directly applied to DMO problems, methods such as NSGAII and adaptive genetic algorithms are adopted usually (Mitra et al 2004;Maravall and de Lope 2006). However, they lose their genetic diversity easily and thereby their adaptiveness, because of DMO's inherent dynamic behaviors (Bui et al 2008).…”

Research on Parking Guidance System Based on Ultrasonic-Ranging

“…STM32 has the advantages of high performance, low price, low power consumption and so on. It is helpful to improve the accuracy of ultrasonic ranging system [7]. The ultrasonic transmitting and receiving circuit is controlled by the STM32 timer, and the reception and transmission are carried out simultaneously, which eliminates the starting time of transmitting and receiving, and improves the ranging precision.…”

Analysis and solution of a predator–protector–prey multi-robot system by a high-level reinforcement learning architecture and the adaptive systems theory

“…Along this line, we have previously proposed a framework [1,2], from which the term bio-mimetic robot navigation or reactive utilitarian navigation gets its meaning in this paper, that formalizes this methodology as an effective tool to solve complex robot navigation problems. However, under this control architecture, all the system's performance depends on precise, constant and immediate information received through the negative feedback cycle and cannot operate properly when such information is delayed, noisy, nonconstant and, especially, when the final result of its behavior is only known after an unpredictable (maybe long) period of time (i.e.…”