A newly proposed complete-coverage path-planning algorithm based on local path cost, termed CCPP-LPC, improves autonomous operation and navigation for mobile robots and unmanned surface vehicles. Complete coverage path planning represents a core enabling technology for autonomous robotic systems. However, in large-scale and complex environments, existing heuristic path planners face significant operational hurdles because their population evolution lacks directional guidance. As a direct consequence of this limitation, conventional planners frequently suffer from slow algorithmic convergence, become prematurely trapped in local optima, and produce excessive turning maneuvers along the completed tour.
To address the blindness inherent in conventional mutation operators, the study proposes a complete-coverage path-planning algorithm based on local path cost (CCPP-LPC). As an initial step, the authors constructed a dedicated local path cost evaluation model. This model adaptively quantifies the possible impact that each individual node may exert on the overall path length. By evaluating these localized contributions, the model effectively identifies path nodes that possess high optimization potential for subsequent refinement.
In addition to the evaluation model, the research team designed an adaptive dual-guided perturbation node selection strategy. This approach derives two distinct probability distributions directly from the assessed local costs: an optimization-oriented distribution and a diversity-oriented distribution. By deploying these dual distributions, the algorithm guides the candidate population to preferentially refine high-cost path segments while simultaneously preserving essential gene diversity, ensuring that population variation is maintained throughout the evolutionary process.
To evaluate the capabilities of CCPP-LPC, the investigators performed comprehensive experimental comparisons against six state-of-the-art heuristic algorithms. The testing regime evaluated the planners across four simulated grid maps characterized by varying scales and degrees of complexity. To mirror operational conditions, the researchers also tested the algorithms on four additional simulation maps established from real-world environments.
The resulting experimental data revealed that CCPP-LPC consistently enhanced computational efficiency while achieving the best performance across critical navigational metrics, notably path length and repeated coverage ratio. These experimental outcomes demonstrate that the algorithm successfully overcomes the limitations of traditional heuristic planners, highlighting CCPP-LPC as a practically valuable method for complete-coverage optimization within complex, multi-constrained operational environments.
Subject of Research: Complete coverage path planning for autonomous vehicles
Article Title: A complete-coverage path-planning algorithm based on local path cost
Article References: Wang, X., Zhu, Y., Tang, J., Dai, Z., & Li, C. (2026). A complete-coverage path-planning algorithm based on local path cost. Scientific Reports. https://doi.org/10.1038/s41598-026-71501-6
Image Credits: AI Generated
DOI: 10.1038/s41598-026-71501-6
Keywords: complete coverage path planning, path planning, local path cost, mobile robots, unmanned surface vehicles, heuristic algorithms, population evolution, mutation operators, local optima, repeated coverage ratio, path length optimization, computational efficiency, perturbation node selection, gene diversity, grid map simulation, autonomous navigation
Cite Scienmag News
Juliet Wilcox. (November 21, 2026). Local Path Cost Planning Improves Efficiency and Coverage for Autonomous Vehicles. Scienmag. https://scienmag.com/local-path-cost-planning-improves-efficiency-and-coverage-for-autonomous-vehicles/
Juliet Wilcox. "Local Path Cost Planning Improves Efficiency and Coverage for Autonomous Vehicles." Scienmag, 21 November 2026, https://scienmag.com/local-path-cost-planning-improves-efficiency-and-coverage-for-autonomous-vehicles/. Accessed 21 November 2026.
Juliet Wilcox. "Local Path Cost Planning Improves Efficiency and Coverage for Autonomous Vehicles." Scienmag. November 21, 2026. https://scienmag.com/local-path-cost-planning-improves-efficiency-and-coverage-for-autonomous-vehicles/








