To address the issues of the traditional A* algorithm, such as insufficient adaptability to complex environments due to its reliance on the orthogonal node layout of grid maps, as well as redundant node traversal, long search time, and poor path smoothness, a path planning and speed collaborative optimization method based on topological maps and an improved A* algorithm was proposed. Firstly, the obstacle point cloud map and OpenDrive map were fused to construct a topological map, and road center points and boundary points were extracted to generate a core point set, which solves the problem of redundant storage in grid maps. Secondly, the search neighborhood was optimized to adapt to non-orthogonal node scenarios, and a dynamic direction heuristic function with adaptive weights was introduced into the evaluation function to suppress invalid exploration that deviates from the target and improve search efficiency. Thirdly, the path smoothness was optimized using cubic spline curves with curvature constraints, and speed planning was conducted based on the curvature distribution of the optimized path. Finally, a preview tracking strategy was adopted to verify the effectiveness of the path and speed planning. Simulation results show that the path smoothness is significantly improved, verifying the collaborative optimization effect of the method in terms of efficiency, smoothness, and safety.
LAI Fei, LIU Tao.
Path Planning and Tracking Control Based on Topological Map and Improved A* Algorithm[J].
Science Technology and Engineering, 2026, 26(29): 12791-12802 DOI:10.12404/j.issn.1671-1815.2507740
目前路径规划算法一般可分为全局路径规划算法和局部路径规划算法[2-3]两类。全局路径规划基于已知的完整环境地图,搜索一条能够避开障碍物并抵达目标点的最优路径。路径规划算法包括A*算法、Dijkstra算法[4-5]、快速探索随机树(rapidly-exploring random tree,RRT)[6]、遗传算法[7]、蚁群算法[8]、粒子群优化算法[9]等。A*算法在全局路径规划算法中应用最为广泛,但其存在随着地图尺寸的增大,算法所消耗的计算资源和路径搜索的时间也会快速增加的问题。研究者针对这些问题提出了许多改进方法。例如,陆辉山等[10]通过插点筛选+跳点搜索,剔除大量冗余节点,节点扩展数量显著低于传统A*算法。Tang等[11]通过提出过滤函数消除不规则路径,分别针对交叉路径和锯齿路径进行优化,但其优化逻辑针对港口网格场景设计,难以直接迁移至非港口场景。Allus等[12]设计改进剪枝算法,去除冗余节点与折线冗余,有效减少路径自交问题,但其角度排序的条件依赖几何直觉,无法保证最优性,需依赖后剪枝修正。Dossis等[13]通过基于估计成本动态调整权重系数平衡搜索效率与探索,但缺乏场景自适应性。Feng等[14]提出融合定向偏置变步长采样策略、分阶段采样、人工势场法及基于三角不等式的剪枝策略,实现了初始路径生成速度的大幅提升及最优路径的优化。上述A*系列算法从代价函数、启发函数、数据结构等方面进行了改进,但是其搜索节点预设的4、8方向离散搜索方向,难以适配复杂场景(城市匝道口等)节点连续变化的场景。
综上,现针对传统A*算法依赖栅格地图导致复杂环境适配性差、搜索效率低及路径平滑性不足等问题,结合拓扑地图构建与算法多维度改进,实现路径规划性能的协同优化。构建融合障碍物点云与OpenDrive地图的拓扑地图,解决传统栅格地图的冗余存储问题。对A*算法核心机制进行改进:动态邻接搜索突破固定方向约束,实现连续角度节点适配;引入含自适应权重的动态方向启发函数,平衡搜索效率与路径最优性。提出曲率约束的三次样条优化策略,采用连续最小二乘法(sequential least squares programming,SLSQP)求解约束优化模型,并对优化后的路径进行速度规划。采用预瞄跟踪控制策略,对优化后的路径与速度曲线进行仿真测试,验证路径的可跟踪性与行驶稳定性。
TangY, ZakariaM A, YounasM. Path planning trends for autonomous mobile robot navigation: a review[J]. Sensors, 2025, 25(4): 1206.
[2]
HuangJ, ChenC, ShenJ, et al. A self-adaptive neighborhood search A-star algorithm for mobile robots global path planning[J]. Computers and Electrical Engineering, 2025, 123: 110018.
[3]
LuY, DaC. Global and local path planning of robots combining ACO and dynamic window algorithm[J]. Scientific Reports, 2025, 15(1): 9452.
[4]
AhmadJ, Ab WahabM N. Enhancing the safety and smoothness of path planning through an integration of Dijkstra's algorithm and piecewise cubic Bezier optimization[J]. Expert Systems with Applications, 2025, 289: 128315.
[5]
ZhouX, YanJ, YanM, et al. Path planning of rail-mounted logistics robots based on the improved Dijkstra algorithm[J]. Applied Sciences, 2023, 13(17): 9955.
[6]
WangJ, LiT, LiB, et al. GMR-RRT*: sampling-based path planning using Gaussian mixture regression[J]. IEEE Transactions on Intelligent Vehicles, 2022, 7(3): 690-700.
[7]
Ab WahabM N, NazirA, KhalilA, et al. Improved genetic algorithm for mobile robot path planning in static environments[J]. Expert Systems with Applications, 2024, 249: 123762.
[8]
CuiJ, WuL, HuangX, et al. Multi-strategy adaptable ant colony optimization algorithm and its application in robot path planning[J]. Knowledge-based Systems, 2024, 288: 111459.
[9]
ZhaoJ, DengC, YuH, et al. Path planning of unmanned vehicles based on adaptive particle swarm optimization algorithm[J]. Computer Communications, 2024, 216: 112-129.
LuHuishan, ZhangYanfei, WangFujie, et al. Path planning of improved A* algorithm by integrating interpolation and jump points[J]. Science Technology and Engineering, 2023, 23(24): 10387-10393.
[12]
TangG, TangC, ClaramuntC, et al. Geometric A-star algorithm: an improved A-star algorithm for AGV path planning in a port environment[J]. IEEE Access, 2021, 9: 59196-59210.
[13]
AllusA, UnelM. Angle-based multi-goal ordering and path-planning using an improved A-star algorithm[J]. Robotics and Autonomous Systems, 2025, 190: 105001.
[14]
ChatzisavvasA, DossisM, DasygenisM. Optimizing mobile robot navigation based on A-star algorithm for obstacle avoidance in smart agriculture[J]. Electronics, 2024, 13(11): 2057.
[15]
FengZ, ZhouL, QiJ, et al. DBVS-APF-RRT*: a global path planning algorithm with ultra-high speed generation of initial paths and high optimal path quality[J]. Expert Systems with Applications, 2024, 249: 123571.
GuoXiaoyu, LiuFeng, HuangXiangquan, et al. Path planning of oil well automatic inspection robot based on map weighted genetic algorithm[J]. Science Technology and Engineering, 2023, 23(7): 2910-2915.
SunJiedong, ZhangXudong, ZhangShuo, et al. Reference line generation algorithm for unstructured roads based on cost map[J]. Automotive Engineering, 2026, 48(1): 37-49, 60.
[23]
AnL, HuangX, YangP, et al. Adaptive Bézier curve-based path following control for autonomous driving robots[J]. Robotics and Autonomous Systems, 2025, 189: 104969.
[24]
HuoF, ZhuS, DongH, et al. A new approach to smooth path planning of Ackerman mobile robot based on improved ACO algorithm and B-spline curve[J]. Robotics and Autonomous Systems, 2024, 175: 104655.
[25]
RedaM, OnsyA, HaikalA Y, et al. A novel reinforcement learning-based multi-operator differential evolution with cubic spline for the path planning problem[J]. Artificial Intelligence Review, 2025, 58(5): 142.