Scholarlink

In order to solve the problem of coupling optimization of hard time/cost constraints and 0–1 circular paths in self-driving tour route planning, this study introduces IACO (Improved Ant Colony Optimization), balances exploration and development capabilities through a dynamic volatility coefficient mechanism, constructs a circular path model integrating MTZ (Miller-Tucker-Zemlin) constraints, and strictly handles multi-constraint conflicts by combining penalty function method and feasibility rules. Based on the real commuting data of 8 major tourist cities in China, IACO performs best in time-cost dual-objective optimization, and the total cost is reduced compared with ACO (Ant Colony Optimization) and GA (Genetic Algorithm). The convergence times of IACO in this paper are 87, the total time is 29.0 h, and the total cost is 3653 yuan. The results show that IACO significantly improves the efficiency of multi-objective optimization through parameter dynamicization and strict constraints, and provides a scalable solution for intelligent tourism transportation system, which has theoretical innovation and engineering application value.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimal Path Planning for Self-driving Tours Under Multiple Constraints: Solution Based on Improved Ant Colony Algorithm

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ye Li,
  • Tingting Guo

摘要

In order to solve the problem of coupling optimization of hard time/cost constraints and 0–1 circular paths in self-driving tour route planning, this study introduces IACO (Improved Ant Colony Optimization), balances exploration and development capabilities through a dynamic volatility coefficient mechanism, constructs a circular path model integrating MTZ (Miller-Tucker-Zemlin) constraints, and strictly handles multi-constraint conflicts by combining penalty function method and feasibility rules. Based on the real commuting data of 8 major tourist cities in China, IACO performs best in time-cost dual-objective optimization, and the total cost is reduced compared with ACO (Ant Colony Optimization) and GA (Genetic Algorithm). The convergence times of IACO in this paper are 87, the total time is 29.0 h, and the total cost is 3653 yuan. The results show that IACO significantly improves the efficiency of multi-objective optimization through parameter dynamicization and strict constraints, and provides a scalable solution for intelligent tourism transportation system, which has theoretical innovation and engineering application value.