Coverage path planning (CPP) for orchard-picking robots directly influences picking efficiency, operational costs and robot endurance. To maximize coverage while minimizing redundant movements and operational time, this study proposes a novel coverage path planning method for grape-picking that integrates fruit distribution and robotic arm operational parameters. Using grape distribution data acquired from a structured-light camera, a working area division algorithm is developed by defining fruit distribution as the region of interest (ROI), thereby reducing the number of working areas while ensuring complete coverage. Within each working area, the optimal navigation point where the chassis should stop, defined as the location that minimizes the robotic arm’s total motion time to reach the picking targets, is determined. To optimize the visiting sequence of navigation points, an improved ant colony optimization (ACO) algorithm incorporating multi-population exploration and a forgetting mechanism is developed. Experimental validation based on real orchard data from three grape trellis structures (T, inverted-L, and Y) demonstrates the effectiveness of the proposed method. Results indicate that the proposed method reduces total path length by up to 13.4% compared with the boustrophedon method, and by 10.4% compared with ROI-based approaches using standard ACO.
Zhao et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: