A Genetic Approach to Gradient-Free Kinodynamic Planning in Uneven Terrains

This paper proposes a genetic algorithm-based kinodynamic planning algorithm (GAKD) for car-like vehicles navigating uneven terrains modeled as triangular meshes. The algorithm's distinct feature is trajectory optimization over a receding horizon of fixed length using a genetic algorithm with heuristic-based mutation, ensuring the vehicle's controls remain within its valid operational range. By addressing the unique challenges posed by uneven terrain meshes, such as changes face normals along the path, GAKD offers a practical solution for path planning in complex environments. Comparative evaluations against the Model Predictive Path Integral (MPPI) and log-MPPI methods show that GAKD achieves up to a 20% improvement in traversability cost while maintaining comparable path length. These results demonstrate the potential of GAKD in improving vehicle navigation on challenging terrains.