Research on the Application of SSG‐RRT Path Planning Algorithm Integrated With Dynamic Obstacle Avoidance in Wheeled Picking Robot

ABSTRACT

Picking robots often encounter significant challenges when navigating unstructured agricultural environments due to obstacles such as dense branches, immature crops, and other obstacles. This paper presents a Sampling Step Guiding Rapidly‐exploring Random Tree (SSG‐RRT) path planning algorithm for wheeled picking robots. The proposed algorithm addresses key issues, including excessive redundancy in sampling points, low tree expansion efficiency, poor convergence guidance, and abrupt path turns by constructing a Sampling Step Rapidly‐exploring Random Tree (SS‐RRT) algorithm that combines a greedy biased sampling strategy and adaptive step size, and further integrating the Artificial Potential Field (APF) algorithm to achieve convergence‐oriented optimization. Additionally, a reconnection optimization strategy is employed to eliminate unnecessary path nodes that do not account for obstacles, and cubic B‐spline curve smoothing is applied to refine the generated path. To further improve local obstacle avoidance, the Dynamic Window Approach (DWA) is integrated with SSG‐RRT. The DWA algorithm tracks the globally planned path generated by SSG‐RRT while dynamically adjusting the local path based on velocity constraints to avoid obstacles in real time. Compared with the SS‐RRT algorithm, simulation results demonstrate that the SSG‐RRT algorithm reduces path length by 21.6%, sampling time by 87.5%, and overall planning time by 84.1%. The proposed approach is successfully applied to real‐time obstacle avoidance for both static and dynamic obstacles, effectively addressing challenges such as poor convergence, excessive path inflection points, and weak dynamic obstacle avoidance capabilities in complex and dynamic picking environments.