Parallel Elite Genetic Algorithm and Its Application to Global Path Planning for Autonomous Robot Navigation

Abstract

This paper presents a parallel elite genetic algorithm (PEGA) and its application to global path planning for autonomous mobile robots navigating in structured environments. This PEGA, consisting of two parallel EGAs along with a migration operator, takes advantages of maintaining better population diversity, inhibiting premature convergence, and keeping parallelism in comparison with conventional GAs. This initial feasible path generated from the PEGA planner is then smoothed using the cubic B-spline technique, in order to construct a nearoptimal collision-free continuous path. Both global path planner and smoother are implemented in one field-programmable gate array chip utilizing the system-on-a-programmable-chip technology and the pipelined hardware implementation scheme, thus significantly expediting computation speed. Simulations and experimental results are conducted to show the merit of the proposed PEGA path planner and smoother for global path planning of autonomous mobile robots

Hybridisation of genetic algorithm with simulated annealing for vertical-handover in heterogeneous wireless networks

“…Unlike the other algorithms, GAs are biologically inspired algorithms for conducting random search and optimisation guided by the principles of natural evolution and genetics. As mentioned before, GA has a strong global search ability in solving the aforementioned problems, but also has limitations such as a premature and slow convergence rate, local optimum and ignoring cooperation between populations as well as weak local search ability (Tsai et al, 2011). On the other hand, SA has strong local search ability and no premature problems.…”

ROBIL: Robot Path Planning Based on PBIL Algorithm

“…Unfortunately, the performance of these methods depends greatly the upon population size and the number of iterations, as the GA may be unable to find a qualified path within the designated number of iterations or else may end up with a path of relatively low quality. Although researchers have tried to improve conventional GAs by introducing problem-specific operators [11][12][13][14][15][16][17][18][19][20] and initialization techniques [15][16][17][21][22][23], the high number of parameters required by these operators has limited any performance improvements, as well as creating new problems for population initialization.…”

The Fine-Grained Parallel Micro-Genetic Algorithm and Its Application to Broadband Conical Corrugated-Horn Antenna

“…So the behavior of the master-slave algorithm is essentially the same as a serial GA. The coarse-grained parallel GA was applied in [19,20]. This parallel model divides a large population into some sub-populations, and independently performs selection, crossover and mutation on each subpopulation.…”