Robotic Path Planning Demonstration with Dijkstra-Inspired Genetic Algorithm

This demonstration program illustrates the application of a Dijkstra-inspired genetic algorithm in robotic path planning scenarios. The implementation combines Dijkstra's shortest-path methodology with genetic algorithm optimization techniques to solve complex pathfinding problems in constrained environments. Users can explore how the algorithm generates initial population paths using Dijkstra-based heuristics, then applies genetic operators like crossover and mutation to evolve optimal solutions. The program features comprehensive visualization tools that display real-time path evolution, fitness progression, and obstacle avoidance mechanisms. Through interactive parameter adjustment, users can modify genetic algorithm parameters (population size, mutation rate, selection criteria) and observe their impact on convergence speed and solution quality. The code structure includes modular components for map generation, fitness evaluation using path length and collision penalties, and Dijkstra-based initialization for accelerated convergence. This educational tool helps researchers and developers understand hybrid algorithm design principles and their practical implementation in autonomous navigation systems.