02-09-2017, 12:28 PM
This PEGA, which consists of two parallel EGAs along with a migration operator, has the advantages of maintaining a better population diversity, inhibiting premature convergence and maintaining parallelism compared to conventional GAs. This initial feasible trajectory generated from the PEGA scheduler is then smoothed out using the cubic B-spline technique, in order to construct an almost optimal non-collision continuous path. Both the global path planner and the smoothing are implemented in a field programmable gate array chip that uses the programmable chip-on-chip technology and the channel hardware implementation scheme, thereby significantly accelerating the calculation speed. Simulations and experimental results are carried out to show the merit of the proposed PEGA path planner and smoother for the global path planning of autonomous mobile robots.