In response to the challenges of path planning in complex scenarios, where grid map algorithms are susceptible to the influence of grid size and intelligent algorithms exhibit uncertainty, this paper proposes a method for finding the shortest path based on obstacle corner points using the Dijkstra algorithm. To address obstacles composed of curves without corner points, we suggest a preliminary linearization fitting process followed by pathfinding. To enhance the applicability of the trajectory, we introduce the constraint of minimum turning radius and conduct smoothing research based on circular arcs, providing smoothing solutions for various scenarios. Finally, considering the practical requirement that the trajectory should maintain a safe distance from obstacle edges, we perform an expansion analysis on the obstacles, linearize the resulting arcs, obtain the trajectory based on obstacle corner points, and apply smoothing treatment. Each step has been validated through simulations, demonstrating the rationality of the proposed approach.